US20200311517A1 - Method for object detection using shallow neural networks - Google Patents
Method for object detection using shallow neural networks Download PDFInfo
- Publication number
- US20200311517A1 US20200311517A1 US16/681,885 US201916681885A US2020311517A1 US 20200311517 A1 US20200311517 A1 US 20200311517A1 US 201916681885 A US201916681885 A US 201916681885A US 2020311517 A1 US2020311517 A1 US 2020311517A1
- Authority
- US
- United States
- Prior art keywords
- input image
- version
- shallow neural
- pixels
- downscaled
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 title claims description 27
- 238000012360 testing method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G06N3/0454—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G06K9/00664—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/12—Bounding box
Definitions
- Object detection is required in various systems and applications.
- the method may include receiving an input image by an input of an object detector; wherein the object detector may include multiple branches; generating at least one downscaled version of the input image; feeding the input image to a first branch of the multiple branches; feeding each one of the at least one downscale version of the input image to a unique branch of the multiple branches, one downscale version of the image per branch; calculating, by the multiple branches, candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; selecting bounding boxes out of the candidate bounding boxes, by a selection unit that followed the multiple branches; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects
- the method may include generating the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- non-transitory computer readable medium for detecting an object by an object detector
- the non-transitory computer readable medium may store instructions for: receiving an input image by an input of the object detector; wherein the object detector may include multiple branches; generating at least one downscaled version of the input image; feeding the input image to a first branch of the multiple branches; feeding each one of the at least one downscale version of the input image to a unique branch of the multiple branches, one downscale version of the image per branch; calculating, by the multiple branches, candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; selecting bounding boxes out of the candidate bounding boxes, by a selection unit that follows the multiple branches; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained
- the non-transitory computer readable medium may store instructions for generating the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- an object detection system may include an input, a downscaling unit, multiple branches, and a selection unit; wherein the input may be configured to receive an input image; wherein the downscaling unit may be configured to generate at least one downscaled version of the input image; wherein the multiple branches may be configured to receive the input image and the at least one downscaled version of the input image, one image per branch; wherein the multiple branches may be configured to calculate candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; wherein the selection unit may be configured to select bounding boxes out of the candidate bounding boxes; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore
- the downscaling unit may be configured to generate the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- the predefined size range may range between (a) about ten by ten pixels, till (b) about one hundred by one hundred pixels.
- the predefined size range may range between (a) about sixteen by sixteen pixels, till (b) about one hundred and twenty pixels by one hundred and twenty pixels.
- the predefined size range may range between (a) about eighty by eighty pixels, till (b) about one hundred by one hundred pixels.
- the multiple branches may be three branches and wherein there may be two downscaled versions of the input image.
- the at least one downscaled version of the image may be multiple downscaled versions of the input image.
- the first downscale version of the input image may have a width that may be one half of a width of the input image and a length that may be one half of a length of a length of an input image.
- the each shallow neural network may have up to four layers.
- the each shallow neural network may have up to five layers.
- FIG. 1 illustrates an example of an object detection system
- FIG. 2 illustrates an example of an image, two objects, two bounding boxes and a bounding box output
- FIG. 3 illustrates an image and various objects
- FIG. 4 illustrates an example of a training process
- FIG. 5 illustrates an example of a method for object detection.
- Any reference in the specification to a method should be applied mutatis mutandis to a device or system capable of executing the method and/or to a non-transitory computer readable medium that stores instructions for executing the method.
- Any reference in the specification to a system or device should be applied mutatis mutandis to a method that may be executed by the system, and/or may be applied mutatis mutandis to non-transitory computer readable medium that stores instructions executable by the system.
- Any reference in the specification to a non-transitory computer readable medium should be applied mutatis mutandis to a device or system capable of executing instructions stored in the non-transitory computer readable medium and/or may be applied mutatis mutandis to a method for executing the instructions.
- the object detection system, non-transitory computer readable medium and method may be provided.
- the object detection system, non-transitory computer readable medium and method also provide a high level semantic multi scale feature maps, without impairing the speed of the detector.
- Each additional convolution layer increases the detector physical receptive field, therefore, enlargement of the maximum object size that is managed by the detector result in increasing the required number of convolution layers.
- each layer of the convolutional network has a fixed receptive field, it is not optimal to detect objects of different scales utilizing only features generated by the last convolutional layer.
- Shallow feature maps have small receptive fields that are used to detect small objects, and deep feature maps have large receptive fields that are used to detect large objects.
- shallow features might have less semantic information, which may impair the detection of small objects.
- That implementation forces ineffective forward propagation of small object features from earlier network's stages to deeper network's stages.
- FIG. 1 illustrates an object detection system 9000 that includes an input 9010 (illustrated as receiving input image 9001 ), a downscaling unit 9011 , multiple branches (such as three branches 9013 ( 1 ), 9013 ( 2 ) and 9013 ( 3 )), and a selection unit 9016 such as a non-maximal suppression unit.
- an input 9010 illustrated as receiving input image 9001
- a downscaling unit 9011 multiple branches (such as three branches 9013 ( 1 ), 9013 ( 2 ) and 9013 ( 3 )), and a selection unit 9016 such as a non-maximal suppression unit.
- Input 910 may be configured to receive an input image by an input of an object detector.
- Downscaling unit 9011 may be configured to generate at least one downscaled version of the input image.
- the multiple branches 9013 ( 1 ), 9013 ( 2 ) and 9013 ( 3 ) may be configured to receive the input image and the at least one downscaled version of the input image, one image per branch.
- Input image 9001 is fed to first branch 9013 ( 1 ) that is configured to calculate first candidate bounding boxes that may be indicative of candidate objects that appear in the input image.
- First downscaled version of the input image (DVII) 9002 is fed to second branch 9013 ( 2 ) that is configured to calculate second candidate bounding boxes that may be indicative of candidate objects that appear in first DVII 9002 .
- Second DVII 9003 is fed to third branch 9013 ( 3 ) that is configured to calculate third candidate bounding boxes that may be indicative of candidate objects that appear in second DVII 9003 .
- the multiple branches may include multiple shallow neural networks that may be followed by multiple region units.
- first branch 9013 ( 1 ) a first shallow neural network 9012 ( 1 ) is followed by first region unit 9014 ( 1 ).
- the first shallow neural network 9012 ( 1 ) outputs a first shallow neural network output (SNNO- 1 ) 9003 ( 1 ) that may be a tensor with multiple features per segment of the input image.
- the first region unit 9014 ( 1 ) is configured to receive SNNO- 1 9003 ( 1 ) and calculate and output first candidate bounding boxes 9005 ( 1 ).
- the second shallow neural network 9012 ( 2 ) outputs a second SNNO (SNNO- 2 ) 9003 ( 2 ) that may be a tensor with multiple features per segment of the first DVII 9002 .
- the second region unit 9014 ( 2 ) is configured to receive SNNO- 2 9003 ( 2 ) and calculate and output second candidate bounding boxes 9005 ( 2 ).
- the third shallow neural network 9012 ( 3 ) outputs a third SNNO (SNNO- 3 ) 9003 ( 3 ) that may be a tensor with multiple features per segment of the second DVII 9003 .
- the third region unit 9014 ( 3 ) is configured to receive SNNO- 3 9003 ( 3 ) and calculate and output third candidate bounding boxes 9005 ( 3 ).
- the multiple shallow neural networks 9012 ( 1 ), 9012 ( 2 ) and 9012 ( 3 ) may be multiple instances of a single trained shallow neural network.
- the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range.
- the selection unit 9016 may be configured to select bounding boxes (denoted BB output 9007 ) out of the first, second and third candidate bounding boxes.
- the selected bounding boxes may be further processed to detect the objects. Additionally or alternatively—the bounding boxes may provide the output of the object detection system.
- the branch that receives the input image is configured to detect objects that have a size that is within the predefined size range.
- the predefined size range may span along certain fractions of the input image (for example—between less than a percent to less than ten percent of the input image—although other fractions may be selected).
- the predefined size range may be tailored to the expected size of images within a certain distance range from the sensor.
- the predefined size range may span along certain numbers of pixels—for example between (a) about 10, 20, 30, 40, 50, 60, 70, 80, and 90 pixels by about 10, 20, 30, 40, 50, 60, 70, 80, and 90, and (b) about 100, 110, 120, 130, 140, 150, 160 pixels by about 100, 110, 120, 130, 140, 150, 160 pixels.
- Each branch that receives a downscaled version of the input image may detect objects have a size (within the downscaled version of the input image) that is within the predefined size range—and thus may detect images that appear in the input image having a size that is within a size range that equals the predefined range multiplied by the downscaling factor.
- the input image is of 576 ⁇ 768 pixels (each pixel is represented by three colors)
- the first DVII is 288 ⁇ 384 pixels (each pixel is represented by three colors)
- the second DVII is 144 ⁇ 192 pixels (each pixel is represented by three colors)
- that SNNO- 1 has 85 features per each segment out 36 ⁇ 48 segments
- that SNNO- 2 has 85 features per each segment out 18 ⁇ 24 segments
- that SNNO- 3 has 85 features per each segment out 9 ⁇ 12 segments.
- each shallow neural network may detect an object having a size between 20 ⁇ 20 to 100 ⁇ 100 pixels and physical receptive field around 200 ⁇ 200 pixels. This assumes automotive objects can be effectively represented using bounding box dimension below 100 ⁇ 100.
- the following architecture contains several identical shallow neural networks.
- the first branch detects small object (as appearing in the input image), the second branch detects medium objects (as appearing in the input image), and the third branch detects large objects (as appearing in the input image)—all may be within a limited predefined size range.
- the number of branches, scales, and the downscale factor may differ from those illustrated in FIG. 1 .
- the downscaling factor may differ from 2 ⁇ 2
- downscaling factors between different images may differ from each other, and the like.
- FIG. 2 illustrates an example of an image 9020 , two objects—pedestrian 9021 and car 9022 , two bounding boxes 9023 (bounding pedestrian 9021 ) and 9024 (bounding car 9022 ) and a bounding box output 9025 .
- the bounding box output 9025 may include coordinates (x,y,h,w) of the bounding boxes, objectiveness and class.
- the coordinate indicate the location (x,y) as well as the height and width of the bounding boxes.
- Objectiveness provides a confidence level that an object exists.
- Class class of object—for example cat, dog, vehicle, person . . . ).
- the (x,y) coordinates may represent the center of the bounding box.
- the object detection may be compliant to any flavor of YOLO—but other object detection schemes may be applied.
- FIG. 3 illustrates an image 9030 and various objects 9031 , 9032 , 9033 and 9034 .
- Objects 9033 and 9034 are outside the predefined size range and should be ignored of.
- the single trained neural network is trained to detect objects 9031 and 9032 (within the predefined size range) and ignore objects 9033 and 9034 .
- FIG. 4 illustrates an example of a training process.
- Test images 9040 are fed to single shallow neural network 9017 that outputs, for each test image, a single shallow neural network output that may be a tensor with multiple features per segment of the test image.
- the region unit 9018 is configured to receive the output from single shallow neural network 9017 and calculate and output candidate bounding boxes per test image. Actual results such as the output candidate bounding boxes per test image or an output of a selecting unit 9019 (that follows region unit 9018 ) may be fed to error calculation unit 9050 .
- Error calculation unit 9050 also receives desired results 9045 —objects of a size of the predefined range that should be detected by the single shallow neural network 9017 .
- Error calculation unit 9050 calculates an error 9055 between the the actual results and the desired results- and the error is fed to the single shallow neural network 9017 during the training process.
- FIG. 5 illustrates an example of a method 9100 for object detection.
- Method 9100 may include the following steps:
- Method 9100 may include training the single trained shallow neural network.
- assert or “set” and “negate” (or “deassert” or “clear”) are used herein when referring to the rendering of a signal, status bit, or similar apparatus into its logically true or logically false state, respectively. If the logically true state is a logic level one, the logically false state is a logic level zero. And if the logically true state is a logic level zero, the logically false state is a logic level one.
- logic blocks are merely illustrative and that alternative embodiments may merge logic blocks or circuit elements or impose an alternate decomposition of functionality upon various logic blocks or circuit elements.
- architectures depicted herein are merely exemplary, and that in fact many other architectures may be implemented which achieve the same functionality.
- any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality is achieved.
- any two components herein combined to achieve a particular functionality may be seen as “associated with” each other such that the desired functionality is achieved, irrespective of architectures or intermedial components.
- any two components so associated can also be viewed as being “operably connected,” or “operably coupled,” to each other to achieve the desired functionality.
- the illustrated examples may be implemented as circuitry located on a single integrated circuit or within a same device.
- the examples may be implemented as any number of separate integrated circuits or separate devices interconnected with each other in a suitable manner.
- any reference signs placed between parentheses shall not be construed as limiting the claim.
- the word ‘comprising’ does not exclude the presence of other elements or steps then those listed in a claim.
- the terms “a” or “an,” as used herein, are defined as one or more than one.
Abstract
Description
- This application claims priority from U.S. provisional patent 62/827,121 filing date Mar. 31 2019.
- Object detection is required in various systems and applications.
- There is a growing need to provide a method and a system that may be able to provide highly accurate object detection at a low cost.
- There may be provided a method for object detection, the method may include receiving an input image by an input of an object detector; wherein the object detector may include multiple branches; generating at least one downscaled version of the input image; feeding the input image to a first branch of the multiple branches; feeding each one of the at least one downscale version of the input image to a unique branch of the multiple branches, one downscale version of the image per branch; calculating, by the multiple branches, candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; selecting bounding boxes out of the candidate bounding boxes, by a selection unit that followed the multiple branches; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range.
- The method may include generating the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- There may be provided a non-transitory computer readable medium for detecting an object by an object detector, wherein the non-transitory computer readable medium may store instructions for: receiving an input image by an input of the object detector; wherein the object detector may include multiple branches; generating at least one downscaled version of the input image; feeding the input image to a first branch of the multiple branches; feeding each one of the at least one downscale version of the input image to a unique branch of the multiple branches, one downscale version of the image per branch; calculating, by the multiple branches, candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; selecting bounding boxes out of the candidate bounding boxes, by a selection unit that follows the multiple branches; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range.
- The non-transitory computer readable medium that may store instructions for generating the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- There may be provided an object detection system that may include an input, a downscaling unit, multiple branches, and a selection unit; wherein the input may be configured to receive an input image; wherein the downscaling unit may be configured to generate at least one downscaled version of the input image; wherein the multiple branches may be configured to receive the input image and the at least one downscaled version of the input image, one image per branch; wherein the multiple branches may be configured to calculate candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image; wherein the selection unit may be configured to select bounding boxes out of the candidate bounding boxes; wherein the multiple branches may include multiple shallow neural networks that may be followed by multiple region units; wherein each branch may include a shallow neural network and a region unit; wherein the multiple shallow neural networks may be multiple instances of a single trained shallow neural network; and wherein the single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range.
- The downscaling unit may be configured to generate the multiple downscaled applying a same downscaling ratio between (a) the input image and a first downscaled version of the image and between (b) the first downscale version of the input image to a second downscale version of the input image.
- The predefined size range may range between (a) about ten by ten pixels, till (b) about one hundred by one hundred pixels.
- The predefined size range may range between (a) about sixteen by sixteen pixels, till (b) about one hundred and twenty pixels by one hundred and twenty pixels.
- The predefined size range may range between (a) about eighty by eighty pixels, till (b) about one hundred by one hundred pixels.
- The multiple branches may be three branches and wherein there may be two downscaled versions of the input image.
- The at least one downscaled version of the image may be multiple downscaled versions of the input image.
- The first downscale version of the input image may have a width that may be one half of a width of the input image and a length that may be one half of a length of a length of an input image.
- The each shallow neural network may have up to four layers.
- The each shallow neural network may have up to five layers.
- The embodiments of the disclosure will be understood and appreciated more fully from the following detailed description, taken in conjunction with the drawings in which:
-
FIG. 1 illustrates an example of an object detection system; -
FIG. 2 illustrates an example of an image, two objects, two bounding boxes and a bounding box output; -
FIG. 3 illustrates an image and various objects; -
FIG. 4 illustrates an example of a training process; and -
FIG. 5 illustrates an example of a method for object detection. - In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the present invention.
- The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features, and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanying drawings.
- It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.
- Because the illustrated embodiments of the present invention may for the most part, be implemented using electronic components and circuits known to those skilled in the art, details will not be explained in any greater extent than that considered necessary as illustrated above, for the understanding and appreciation of the underlying concepts of the present invention and in order not to obfuscate or distract from the teachings of the present invention.
- Any reference in the specification to a method should be applied mutatis mutandis to a device or system capable of executing the method and/or to a non-transitory computer readable medium that stores instructions for executing the method.
- Any reference in the specification to a system or device should be applied mutatis mutandis to a method that may be executed by the system, and/or may be applied mutatis mutandis to non-transitory computer readable medium that stores instructions executable by the system.
- Any reference in the specification to a non-transitory computer readable medium should be applied mutatis mutandis to a device or system capable of executing instructions stored in the non-transitory computer readable medium and/or may be applied mutatis mutandis to a method for executing the instructions.
- Any combination of any module or unit listed in any of the figures, any part of the specification and/or any claims may be provided.
- There may be provided a low power object detection system (detector), non-transitory computer readable medium and method. The object detection system, non-transitory computer readable medium and method also provide a high level semantic multi scale feature maps, without impairing the speed of the detector.
- Each additional convolution layer increases the detector physical receptive field, therefore, enlargement of the maximum object size that is managed by the detector result in increasing the required number of convolution layers.
- Since each layer of the convolutional network has a fixed receptive field, it is not optimal to detect objects of different scales utilizing only features generated by the last convolutional layer.
- Shallow feature maps have small receptive fields that are used to detect small objects, and deep feature maps have large receptive fields that are used to detect large objects.
- Nevertheless, shallow features might have less semantic information, which may impair the detection of small objects.
- The above theorem was very popular at the first object detectors that have been released until 2016. In contrast, at the last few years, we are witness to a new trend of very deep networks integrated into state of the art object detectors. hence state of the art object detectors detect small objects using feature maps extracted from enormous receptive fields.
- That implementation forces ineffective forward propagation of small object features from earlier network's stages to deeper network's stages.
- Thus while managing larger objects required deeper network, the ineffective detection of small objects increase the number of channels along the network or complicating the memory data transition between layers.
- Interesting theorem explaining the motivation of using feature maps that have large receptive fields for small objects suggests that in order to detect a small object we take advantage of the context information surrounding it. For example, we can easily distinguish between small car driving on the roadway and boat sailing on the sea employing the surrounding background information which is notably more differently than the internal context information of that two small objects.
- However, real-time automotive application can't take advantage of deeper/wider/Complex networks because those networks are not applicable due to power consuming limitation requirements.
-
FIG. 1 illustrates anobject detection system 9000 that includes an input 9010 (illustrated as receiving input image 9001), adownscaling unit 9011, multiple branches (such as three branches 9013(1), 9013(2) and 9013(3)), and aselection unit 9016 such as a non-maximal suppression unit. - Input 910 may be configured to receive an input image by an input of an object detector.
-
Downscaling unit 9011 may be configured to generate at least one downscaled version of the input image. - The multiple branches 9013(1), 9013(2) and 9013(3) may be configured to receive the input image and the at least one downscaled version of the input image, one image per branch.
-
Input image 9001 is fed to first branch 9013(1) that is configured to calculate first candidate bounding boxes that may be indicative of candidate objects that appear in the input image. - First downscaled version of the input image (DVII) 9002 is fed to second branch 9013(2) that is configured to calculate second candidate bounding boxes that may be indicative of candidate objects that appear in first DVII 9002.
- Second DVII 9003 is fed to third branch 9013(3) that is configured to calculate third candidate bounding boxes that may be indicative of candidate objects that appear in
second DVII 9003. - The multiple branches may include multiple shallow neural networks that may be followed by multiple region units.
- In first branch 9013(1), a first shallow neural network 9012(1) is followed by first region unit 9014(1).
- The first shallow neural network 9012(1) outputs a first shallow neural network output (SNNO-1) 9003(1) that may be a tensor with multiple features per segment of the input image. The first region unit 9014(1) is configured to receive SNNO-1 9003(1) and calculate and output first candidate bounding boxes 9005(1).
- The second shallow neural network 9012(2) outputs a second SNNO (SNNO-2) 9003(2) that may be a tensor with multiple features per segment of the first DVII 9002. The second region unit 9014(2) is configured to receive SNNO-2 9003(2) and calculate and output second candidate bounding boxes 9005(2).
- The third shallow neural network 9012(3) outputs a third SNNO (SNNO-3) 9003(3) that may be a tensor with multiple features per segment of the
second DVII 9003. The third region unit 9014(3) is configured to receive SNNO-3 9003(3) and calculate and output third candidate bounding boxes 9005(3). - The multiple shallow neural networks 9012(1), 9012(2) and 9012(3) may be multiple instances of a single trained shallow neural network.
- The single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range.
- The
selection unit 9016 may be configured to select bounding boxes (denoted BB output 9007) out of the first, second and third candidate bounding boxes. - The selected bounding boxes may be further processed to detect the objects. Additionally or alternatively—the bounding boxes may provide the output of the object detection system.
- The branch that receives the input image is configured to detect objects that have a size that is within the predefined size range.
- The predefined size range may span along certain fractions of the input image (for example—between less than a percent to less than ten percent of the input image—although other fractions may be selected).
- The predefined size range may be tailored to the expected size of images within a certain distance range from the sensor.
- The predefined size range may span along certain numbers of pixels—for example between (a) about 10, 20, 30, 40, 50, 60, 70, 80, and 90 pixels by about 10, 20, 30, 40, 50, 60, 70, 80, and 90, and (b) about 100, 110, 120, 130, 140, 150, 160 pixels by about 100, 110, 120, 130, 140, 150, 160 pixels.
- Each branch that receives a downscaled version of the input image (assuming of a certain downscaling factor) may detect objects have a size (within the downscaled version of the input image) that is within the predefined size range—and thus may detect images that appear in the input image having a size that is within a size range that equals the predefined range multiplied by the downscaling factor.
- Assuming, for example that the input image is of 576×768 pixels (each pixel is represented by three colors), the first DVII is 288×384 pixels (each pixel is represented by three colors), and the second DVII is 144×192 pixels (each pixel is represented by three colors), that SNNO-1 has 85 features per each segment out 36×48 segments, that SNNO-2 has 85 features per each segment out 18×24 segments, that SNNO-3 has 85 features per each segment out 9×12 segments.
- The assumption above as well as the example below are merely non-limiting examples of various values. Other values may be provided.
- Under these assumptions, each shallow neural network may detect an object having a size between 20×20 to 100×100 pixels and physical receptive field around 200×200 pixels. This assumes automotive objects can be effectively represented using bounding box dimension below 100×100.
- In contrast to a single model trained end to end, the following architecture contains several identical shallow neural networks.
- The first branch detects small object (as appearing in the input image), the second branch detects medium objects (as appearing in the input image), and the third branch detects large objects (as appearing in the input image)—all may be within a limited predefined size range.
- The number of branches, scales, and the downscale factor may differ from those illustrated in
FIG. 1 . For example—there may be two or more than three branches, the downscaling factor may differ from 2×2, downscaling factors between different images may differ from each other, and the like. -
FIG. 2 illustrates an example of animage 9020, two objects—pedestrian 9021 andcar 9022, two bounding boxes 9023 (bounding pedestrian 9021) and 9024 (bounding car 9022) and abounding box output 9025. - The
bounding box output 9025 may include coordinates (x,y,h,w) of the bounding boxes, objectiveness and class. The coordinate indicate the location (x,y) as well as the height and width of the bounding boxes. Objectiveness provides a confidence level that an object exists. Class—class of object—for example cat, dog, vehicle, person . . . ). The (x,y) coordinates may represent the center of the bounding box. - The object detection may be compliant to any flavor of YOLO—but other object detection schemes may be applied.
-
FIG. 3 illustrates animage 9030 andvarious objects -
Objects objects 9031 and 9032 (within the predefined size range) and ignoreobjects -
FIG. 4 illustrates an example of a training process. -
Test images 9040 are fed to single shallowneural network 9017 that outputs, for each test image, a single shallow neural network output that may be a tensor with multiple features per segment of the test image. Theregion unit 9018 is configured to receive the output from single shallowneural network 9017 and calculate and output candidate bounding boxes per test image. Actual results such as the output candidate bounding boxes per test image or an output of a selecting unit 9019 (that follows region unit 9018) may be fed to errorcalculation unit 9050. -
Error calculation unit 9050 also receives desiredresults 9045—objects of a size of the predefined range that should be detected by the single shallowneural network 9017. -
Error calculation unit 9050 calculates anerror 9055 between the the actual results and the desired results- and the error is fed to the single shallowneural network 9017 during the training process. -
FIG. 5 illustrates an example of amethod 9100 for object detection. -
Method 9100 may include the following steps: -
-
Step 9101 of receiving an input image by an input of an object detector. The object detector may include multiple branches. The multiple branches may include multiple shallow neural networks that may be followed by multiple region units. Each branch may include a shallow neural network and a region unit. The multiple shallow neural networks may be multiple instances of a single trained shallow neural network. The single trained shallow neural network may be trained to detect objects having a size that may be within a predefined size range and to ignore objects having a size that may be outside the predefined size range. -
Step 9102 of generating at least one downscaled version of the input image. -
Step 9103 of feeding the input image to a first branch of the multiple branches. -
Step 9104 of feeding each one of the at least one downscale version of the input image to a unique branch of the multiple branches, one downscale version of the image per branch. -
Step 9105 of calculating, by the multiple branches, candidate bounding boxes that may be indicative of candidate objects that appear in the input image and each one of the at least one downscaled version of the input image. -
Step 9106 of selecting bounding boxes out of the candidate bounding boxes, by a selection unit that followed the multiple branches. -
Step 9107 of outputting the bonding boxes and/or further processing the bounding boxes.
-
-
Method 9100 may include training the single trained shallow neural network. - While the foregoing written description of the invention enables one of ordinary skill to make and use what is considered presently to be the best mode thereof, those of ordinary skill will understand and appreciate the existence of variations, combinations, and equivalents of the specific embodiment, method, and examples herein. The invention should therefore not be limited by the above described embodiment, method, and examples, but by all embodiments and methods within the scope and spirit of the invention as claimed.
- In the foregoing specification, the invention has been described with reference to specific examples of embodiments of the invention. It will, however, be evident that various modifications and changes may be made therein without departing from the broader spirit and scope of the invention as set forth in the appended claims.
- Moreover, the terms “front,” “back,” “top,” “bottom,” “over,” “under” and the like in the description and in the claims, if any, are used for descriptive purposes and not necessarily for describing permanent relative positions. It is understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in other orientations than those illustrated or otherwise described herein.
- Furthermore, the terms “assert” or “set” and “negate” (or “deassert” or “clear”) are used herein when referring to the rendering of a signal, status bit, or similar apparatus into its logically true or logically false state, respectively. If the logically true state is a logic level one, the logically false state is a logic level zero. And if the logically true state is a logic level zero, the logically false state is a logic level one.
- Those skilled in the art will recognize that the boundaries between logic blocks are merely illustrative and that alternative embodiments may merge logic blocks or circuit elements or impose an alternate decomposition of functionality upon various logic blocks or circuit elements. Thus, it is to be understood that the architectures depicted herein are merely exemplary, and that in fact many other architectures may be implemented which achieve the same functionality.
- Any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality may be seen as “associated with” each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated can also be viewed as being “operably connected,” or “operably coupled,” to each other to achieve the desired functionality.
- Furthermore, those skilled in the art will recognize that boundaries between the above described operations merely illustrative. The multiple operations may be combined into a single operation, a single operation may be distributed in additional operations and operations may be executed at least partially overlapping in time. Moreover, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be altered in various other embodiments.
- Also for example, in one embodiment, the illustrated examples may be implemented as circuitry located on a single integrated circuit or within a same device. Alternatively, the examples may be implemented as any number of separate integrated circuits or separate devices interconnected with each other in a suitable manner.
- However, other modifications, variations and alternatives are also possible. The specifications and drawings are, accordingly, to be regarded in an illustrative rather than in a restrictive sense.
- In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word ‘comprising’ does not exclude the presence of other elements or steps then those listed in a claim. Furthermore, the terms “a” or “an,” as used herein, are defined as one or more than one. Also, the use of introductory phrases such as “at least one” and “one or more” in the claims should not be construed to imply that the introduction of another claim element by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim element to inventions containing only one such element, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an.” The same holds true for the use of definite articles. Unless stated otherwise, terms such as “first” and “second” are used to arbitrarily distinguish between the elements such terms describe. Thus, these terms are not necessarily intended to indicate temporal or other prioritization of such elements. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage.
- While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.
- It is appreciated that various features of the embodiments of the disclosure which are, for clarity, described in the contexts of separate embodiments may also be provided in combination in a single embodiment. Conversely, various features of the embodiments of the disclosure which are, for brevity, described in the context of a single embodiment may also be provided separately or in any suitable sub-combination.
- It will be appreciated by persons skilled in the art that the embodiments of the disclosure are not limited by what has been particularly shown and described hereinabove. Rather the scope of the embodiments of the disclosure is defined by the appended claims and equivalents thereof
Claims (30)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/681,885 US10789527B1 (en) | 2019-03-31 | 2019-11-13 | Method for object detection using shallow neural networks |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962827112P | 2019-03-31 | 2019-03-31 | |
US201962827121P | 2019-03-31 | 2019-03-31 | |
US16/681,885 US10789527B1 (en) | 2019-03-31 | 2019-11-13 | Method for object detection using shallow neural networks |
Publications (2)
Publication Number | Publication Date |
---|---|
US10789527B1 US10789527B1 (en) | 2020-09-29 |
US20200311517A1 true US20200311517A1 (en) | 2020-10-01 |
Family
ID=72606274
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/681,885 Active US10789527B1 (en) | 2019-03-31 | 2019-11-13 | Method for object detection using shallow neural networks |
Country Status (1)
Country | Link |
---|---|
US (1) | US10789527B1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230186637A1 (en) * | 2021-12-10 | 2023-06-15 | Ford Global Technologies, Llc | Systems and methods for detecting deep neural network inference quality using image/data manipulation without ground truth information |
Family Cites Families (336)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4733353A (en) | 1985-12-13 | 1988-03-22 | General Electric Company | Frame synchronization of multiply redundant computers |
US5078501A (en) | 1986-10-17 | 1992-01-07 | E. I. Du Pont De Nemours And Company | Method and apparatus for optically evaluating the conformance of unknown objects to predetermined characteristics |
US4972363A (en) | 1989-02-01 | 1990-11-20 | The Boeing Company | Neural network using stochastic processing |
US4932645A (en) | 1989-03-29 | 1990-06-12 | Am International Incorporated | Method and apparatus for controlling a multiple delivery collator in response to a downstream fault condition |
US5214746A (en) | 1991-06-17 | 1993-05-25 | Orincon Corporation | Method and apparatus for training a neural network using evolutionary programming |
US5436653A (en) | 1992-04-30 | 1995-07-25 | The Arbitron Company | Method and system for recognition of broadcast segments |
US5307451A (en) | 1992-05-12 | 1994-04-26 | Apple Computer, Inc. | Method and apparatus for generating and manipulating graphical data for display on a computer output device |
AU5803394A (en) | 1992-12-17 | 1994-07-04 | Bell Atlantic Network Services, Inc. | Mechanized directory assistance |
CN1113302C (en) | 1993-07-30 | 2003-07-02 | 佳能株式会社 | Method and apparatus for controlling system |
US20010038876A1 (en) | 1993-10-22 | 2001-11-08 | Richard M. Anderson | Apparatus and method for producing grain based baker food products |
CA2130395C (en) | 1993-12-09 | 1999-01-19 | David G. Greenwood | Multimedia distribution over wide area networks |
US5835901A (en) | 1994-01-25 | 1998-11-10 | Martin Marietta Corporation | Perceptive system including a neural network |
US5412564A (en) | 1994-02-03 | 1995-05-02 | Ecer; Gunes M. | System and method for diet control |
US6052481A (en) | 1994-09-02 | 2000-04-18 | Apple Computers, Inc. | Automatic method for scoring and clustering prototypes of handwritten stroke-based data |
US5759462A (en) | 1994-10-14 | 1998-06-02 | Amoco Corporaiton | Electrically conductive tapes and process |
US5758257A (en) | 1994-11-29 | 1998-05-26 | Herz; Frederick | System and method for scheduling broadcast of and access to video programs and other data using customer profiles |
EP0717337B1 (en) | 1994-12-13 | 2001-08-01 | International Business Machines Corporation | Method and system for the secured distribution of programs |
JP2002083219A (en) | 2000-07-04 | 2002-03-22 | Sony Computer Entertainment Inc | In-content advertisement method, server for in-content advertisement, and transfer medium of program for realizing in-content advertisement |
JPH0981566A (en) | 1995-09-08 | 1997-03-28 | Toshiba Corp | Method and device for translation |
US6985172B1 (en) | 1995-12-01 | 2006-01-10 | Southwest Research Institute | Model-based incident detection system with motion classification |
CA2166247A1 (en) | 1995-12-28 | 1997-06-29 | Ravi Shankar Ananth | Supervisory circuit |
US6076088A (en) | 1996-02-09 | 2000-06-13 | Paik; Woojin | Information extraction system and method using concept relation concept (CRC) triples |
US5852435A (en) | 1996-04-12 | 1998-12-22 | Avid Technology, Inc. | Digital multimedia editing and data management system |
US5870754A (en) | 1996-04-25 | 1999-02-09 | Philips Electronics North America Corporation | Video retrieval of MPEG compressed sequences using DC and motion signatures |
US5926812A (en) | 1996-06-20 | 1999-07-20 | Mantra Technologies, Inc. | Document extraction and comparison method with applications to automatic personalized database searching |
US5991306A (en) | 1996-08-26 | 1999-11-23 | Microsoft Corporation | Pull based, intelligent caching system and method for delivering data over a network |
US5873080A (en) | 1996-09-20 | 1999-02-16 | International Business Machines Corporation | Using multiple search engines to search multimedia data |
US20030093790A1 (en) | 2000-03-28 | 2003-05-15 | Logan James D. | Audio and video program recording, editing and playback systems using metadata |
US6243375B1 (en) | 1996-11-08 | 2001-06-05 | Gregory J. Speicher | Internet-audiotext electronic communications system with multimedia based matching |
US5806061A (en) | 1997-05-20 | 1998-09-08 | Hewlett-Packard Company | Method for cost-based optimization over multimeida repositories |
US6137911A (en) | 1997-06-16 | 2000-10-24 | The Dialog Corporation Plc | Test classification system and method |
US6360234B2 (en) | 1997-08-14 | 2002-03-19 | Virage, Inc. | Video cataloger system with synchronized encoders |
US6507672B1 (en) | 1997-09-10 | 2003-01-14 | Lsi Logic Corporation | Video encoder for digital video displays |
US6070167A (en) | 1997-09-29 | 2000-05-30 | Sharp Laboratories Of America, Inc. | Hierarchical method and system for object-based audiovisual descriptive tagging of images for information retrieval, editing, and manipulation |
US6594699B1 (en) | 1997-10-10 | 2003-07-15 | Kasenna, Inc. | System for capability based multimedia streaming over a network |
US6546405B2 (en) | 1997-10-23 | 2003-04-08 | Microsoft Corporation | Annotating temporally-dimensioned multimedia content |
US6122628A (en) | 1997-10-31 | 2000-09-19 | International Business Machines Corporation | Multidimensional data clustering and dimension reduction for indexing and searching |
US7954056B2 (en) | 1997-12-22 | 2011-05-31 | Ricoh Company, Ltd. | Television-based visualization and navigation interface |
US6329986B1 (en) | 1998-02-21 | 2001-12-11 | U.S. Philips Corporation | Priority-based virtual environment |
US6144767A (en) | 1998-04-02 | 2000-11-07 | At&T Corp | Efficient convolutions using polynomial covers |
US6163510A (en) | 1998-06-30 | 2000-12-19 | International Business Machines Corporation | Multimedia search and indexing system and method of operation using audio cues with signal thresholds |
US6292575B1 (en) | 1998-07-20 | 2001-09-18 | Lau Technologies | Real-time facial recognition and verification system |
US6243713B1 (en) | 1998-08-24 | 2001-06-05 | Excalibur Technologies Corp. | Multimedia document retrieval by application of multimedia queries to a unified index of multimedia data for a plurality of multimedia data types |
US6275599B1 (en) | 1998-08-28 | 2001-08-14 | International Business Machines Corporation | Compressed image authentication and verification |
US7634662B2 (en) | 2002-11-21 | 2009-12-15 | Monroe David A | Method for incorporating facial recognition technology in a multimedia surveillance system |
US7158681B2 (en) | 1998-10-01 | 2007-01-02 | Cirrus Logic, Inc. | Feedback scheme for video compression system |
US7313805B1 (en) | 1998-11-30 | 2007-12-25 | Sony Corporation | Content navigator graphical user interface system and method |
US6524861B1 (en) | 1999-01-22 | 2003-02-25 | Medical Laboratory Automation, Inc. | Blood coagulation analyzer |
AU2330100A (en) | 1999-01-29 | 2000-08-18 | Lg Electronics Inc. | Method of searching or browsing multimedia data and data structure |
US6819797B1 (en) | 1999-01-29 | 2004-11-16 | International Business Machines Corporation | Method and apparatus for classifying and querying temporal and spatial information in video |
KR20010108159A (en) | 1999-01-29 | 2001-12-07 | 다니구찌 이찌로오, 기타오카 다카시 | Method of image feature encoding and method of image search |
US6381656B1 (en) | 1999-03-10 | 2002-04-30 | Applied Microsystems Corporation | Method and apparatus for monitoring input/output (“I/O”) performance in I/O processors |
US6774917B1 (en) | 1999-03-11 | 2004-08-10 | Fuji Xerox Co., Ltd. | Methods and apparatuses for interactive similarity searching, retrieval, and browsing of video |
US6643620B1 (en) | 1999-03-15 | 2003-11-04 | Matsushita Electric Industrial Co., Ltd. | Voice activated controller for recording and retrieving audio/video programs |
US6557042B1 (en) | 1999-03-19 | 2003-04-29 | Microsoft Corporation | Multimedia summary generation employing user feedback |
US6732149B1 (en) | 1999-04-09 | 2004-05-04 | International Business Machines Corporation | System and method for hindering undesired transmission or receipt of electronic messages |
US6128651A (en) | 1999-04-14 | 2000-10-03 | Americom Usa | Internet advertising with controlled and timed display of ad content from centralized system controller |
US6763519B1 (en) | 1999-05-05 | 2004-07-13 | Sychron Inc. | Multiprogrammed multiprocessor system with lobally controlled communication and signature controlled scheduling |
KR100326400B1 (en) | 1999-05-19 | 2002-03-12 | 김광수 | Method for generating caption location information, method for searching thereby, and reproducing apparatus using the methods |
US6314419B1 (en) | 1999-06-04 | 2001-11-06 | Oracle Corporation | Methods and apparatus for generating query feedback based on co-occurrence patterns |
KR100479613B1 (en) | 1999-07-05 | 2005-03-30 | 엘지전자 주식회사 | Method of controlling image feature weight using auto relevance feedback in content based image retrieval |
KR100518860B1 (en) | 1999-07-05 | 2005-09-30 | 엘지전자 주식회사 | Image searching method using feature normalizing information |
US6813395B1 (en) | 1999-07-14 | 2004-11-02 | Fuji Photo Film Co., Ltd. | Image searching method and image processing method |
JP2001049923A (en) | 1999-08-09 | 2001-02-20 | Aisin Seiki Co Ltd | Door closer device |
US6751363B1 (en) | 1999-08-10 | 2004-06-15 | Lucent Technologies Inc. | Methods of imaging based on wavelet retrieval of scenes |
US6147636A (en) | 1999-08-16 | 2000-11-14 | The United States Of America As Represented By The Secretary Of The Navy | Synthetic aperture processing for diffusion-equation-based target detection |
KR100346262B1 (en) | 1999-08-27 | 2002-07-26 | 엘지전자주식회사 | Method of multimedia data keyword self formation |
US6601026B2 (en) | 1999-09-17 | 2003-07-29 | Discern Communications, Inc. | Information retrieval by natural language querying |
US6711291B1 (en) | 1999-09-17 | 2004-03-23 | Eastman Kodak Company | Method for automatic text placement in digital images |
US20030182567A1 (en) | 1999-10-20 | 2003-09-25 | Tivo Inc. | Client-side multimedia content targeting system |
US6665657B1 (en) | 1999-11-19 | 2003-12-16 | Niku Corporation | Method and system for cross browsing of various multimedia data sources in a searchable repository |
KR20020000547A (en) | 2000-01-13 | 2002-01-05 | 요트.게.아. 롤페즈 | Noise reduction |
CA2333338A1 (en) | 2000-02-04 | 2001-08-04 | 3Com Corporation | Internet-based enhanced radio |
US6550018B1 (en) | 2000-02-18 | 2003-04-15 | The University Of Akron | Hybrid multiple redundant computer system |
US7137065B1 (en) | 2000-02-24 | 2006-11-14 | International Business Machines Corporation | System and method for classifying electronically posted documents |
US6523046B2 (en) | 2000-02-25 | 2003-02-18 | Microsoft Corporation | Infrastructure and method for supporting generic multimedia metadata |
US20020032677A1 (en) | 2000-03-01 | 2002-03-14 | Jeff Morgenthaler | Methods for creating, editing, and updating searchable graphical database and databases of graphical images and information and displaying graphical images from a searchable graphical database or databases in a sequential or slide show format |
US20020038299A1 (en) | 2000-03-20 | 2002-03-28 | Uri Zernik | Interface for presenting information |
US6804356B1 (en) | 2000-03-20 | 2004-10-12 | Koninklijke Philips Electronics N.V. | Hierarchical authentication system for images and video |
US6901207B1 (en) | 2000-03-30 | 2005-05-31 | Lsi Logic Corporation | Audio/visual device for capturing, searching and/or displaying audio/visual material |
US7260564B1 (en) | 2000-04-07 | 2007-08-21 | Virage, Inc. | Network video guide and spidering |
US20020072935A1 (en) | 2000-04-12 | 2002-06-13 | Rowse William T. | Method system and software for transmitting digital media between remote locations |
US20060217828A1 (en) | 2002-10-23 | 2006-09-28 | Hicken Wendell T | Music searching system and method |
DE60100416T2 (en) | 2000-04-28 | 2004-06-09 | Matsushita Electric Industrial Co., Ltd., Kadoma | Decoder for variable length codes |
US20020019881A1 (en) | 2000-06-16 | 2002-02-14 | Bokhari Wasiq M. | System, method and computer program product for habitat-based universal application of functions to network data |
US6763069B1 (en) | 2000-07-06 | 2004-07-13 | Mitsubishi Electric Research Laboratories, Inc | Extraction of high-level features from low-level features of multimedia content |
US7035873B2 (en) | 2001-08-20 | 2006-04-25 | Microsoft Corporation | System and methods for providing adaptive media property classification |
US6829780B2 (en) | 2000-07-17 | 2004-12-07 | International Business Machines Corporation | System and method for dynamically optimizing a banner advertisement to counter competing advertisements |
AU2001275982A1 (en) | 2000-07-20 | 2002-02-05 | Rodney D. Johnson | Information archival and retrieval system for internetworked computers |
WO2002008948A2 (en) | 2000-07-24 | 2002-01-31 | Vivcom, Inc. | System and method for indexing, searching, identifying, and editing portions of electronic multimedia files |
US20020157116A1 (en) | 2000-07-28 | 2002-10-24 | Koninklijke Philips Electronics N.V. | Context and content based information processing for multimedia segmentation and indexing |
US7464086B2 (en) | 2000-08-01 | 2008-12-09 | Yahoo! Inc. | Metatag-based datamining |
JP2004533001A (en) | 2000-10-11 | 2004-10-28 | ユナイテッド ビデオ プロパティーズ, インコーポレイテッド | Systems and methods for providing targeted advertisements based on current behavior |
US8711217B2 (en) | 2000-10-24 | 2014-04-29 | Objectvideo, Inc. | Video surveillance system employing video primitives |
US7146349B2 (en) | 2000-11-06 | 2006-12-05 | International Business Machines Corporation | Network for describing multimedia information |
US7043473B1 (en) | 2000-11-22 | 2006-05-09 | Widevine Technologies, Inc. | Media tracking system and method |
EP1340379A2 (en) | 2000-11-28 | 2003-09-03 | United Video Properties, Inc. | Interactive television application with research features |
US20040128511A1 (en) | 2000-12-20 | 2004-07-01 | Qibin Sun | Methods and systems for generating multimedia signature |
AU2002232817A1 (en) | 2000-12-21 | 2002-07-01 | Digimarc Corporation | Methods, apparatus and programs for generating and utilizing content signatures |
JP4329264B2 (en) | 2000-12-27 | 2009-09-09 | セイコーエプソン株式会社 | Access authority level control apparatus and method |
US20020087828A1 (en) | 2000-12-28 | 2002-07-04 | International Business Machines Corporation | Symmetric multiprocessing (SMP) system with fully-interconnected heterogenous microprocessors |
US20020087530A1 (en) | 2000-12-29 | 2002-07-04 | Expresto Software Corp. | System and method for publishing, updating, navigating, and searching documents containing digital video data |
US6753766B2 (en) | 2001-01-15 | 2004-06-22 | 1138037 Ontario Ltd. (“Alirt”) | Detecting device and method of using same |
JP2002229859A (en) | 2001-01-31 | 2002-08-16 | Toshiba Corp | Disk memory and authenticating method applied thereto |
US7003726B2 (en) | 2001-02-21 | 2006-02-21 | Nanonation Incorporated | Computer network having context sensitive and interactive multimedia applications and controls, forming dynamic user interfaces on local computer terminals |
US7681032B2 (en) | 2001-03-12 | 2010-03-16 | Portauthority Technologies Inc. | System and method for monitoring unauthorized transport of digital content |
US7143353B2 (en) | 2001-03-30 | 2006-11-28 | Koninklijke Philips Electronics, N.V. | Streaming video bookmarks |
US7363278B2 (en) | 2001-04-05 | 2008-04-22 | Audible Magic Corporation | Copyright detection and protection system and method |
AU2002307765A1 (en) | 2001-04-11 | 2002-10-28 | Nice Systems Ltd. | Digital video protection for authenticity verification |
US6973574B2 (en) | 2001-04-24 | 2005-12-06 | Microsoft Corp. | Recognizer of audio-content in digital signals |
US6938025B1 (en) | 2001-05-07 | 2005-08-30 | Microsoft Corporation | Method and apparatus for automatically determining salient features for object classification |
US6826576B2 (en) | 2001-05-07 | 2004-11-30 | Microsoft Corporation | Very-large-scale automatic categorizer for web content |
US6993535B2 (en) | 2001-06-18 | 2006-01-31 | International Business Machines Corporation | Business method and apparatus for employing induced multimedia classifiers based on unified representation of features reflecting disparate modalities |
US7529659B2 (en) | 2005-09-28 | 2009-05-05 | Audible Magic Corporation | Method and apparatus for identifying an unknown work |
US20020010715A1 (en) | 2001-07-26 | 2002-01-24 | Garry Chinn | System and method for browsing using a limited display device |
US20030041047A1 (en) | 2001-08-09 | 2003-02-27 | International Business Machines Corporation | Concept-based system for representing and processing multimedia objects with arbitrary constraints |
US6747201B2 (en) | 2001-09-26 | 2004-06-08 | The Regents Of The University Of Michigan | Method and system for extracting melodic patterns in a musical piece and computer-readable storage medium having a program for executing the method |
US6925475B2 (en) | 2001-10-12 | 2005-08-02 | Commissariat A L'energie Atomique | Process and apparatus for management of multimedia databases |
US20030105739A1 (en) | 2001-10-12 | 2003-06-05 | Hassane Essafi | Method and a system for identifying and verifying the content of multimedia documents |
US7495795B2 (en) | 2002-02-21 | 2009-02-24 | Ricoh Company, Ltd. | Interface for printing multimedia information |
US8635531B2 (en) | 2002-02-21 | 2014-01-21 | Ricoh Company, Ltd. | Techniques for displaying information stored in multiple multimedia documents |
US7093001B2 (en) | 2001-11-26 | 2006-08-15 | Microsoft Corporation | Methods and systems for adaptive delivery of multimedia contents |
US6912517B2 (en) | 2001-11-29 | 2005-06-28 | Koninklijke Philips Electronics N.V. | Intelligent information delivery system |
US7353224B2 (en) | 2001-12-04 | 2008-04-01 | Hewlett-Packard Development Company, L.P. | System and method for efficiently finding near-similar images in massive databases |
US7020654B1 (en) | 2001-12-05 | 2006-03-28 | Sun Microsystems, Inc. | Methods and apparatus for indexing content |
US7921288B1 (en) | 2001-12-12 | 2011-04-05 | Hildebrand Hal S | System and method for providing different levels of key security for controlling access to secured items |
US20030115191A1 (en) | 2001-12-17 | 2003-06-19 | Max Copperman | Efficient and cost-effective content provider for customer relationship management (CRM) or other applications |
EP1481336A2 (en) | 2002-01-22 | 2004-12-01 | Koninklijke Philips Electronics N.V. | Method and system for distributing multimedia object |
US20030140257A1 (en) | 2002-01-22 | 2003-07-24 | Petr Peterka | Encryption, authentication, and key management for multimedia content pre-encryption |
US7215828B2 (en) | 2002-02-13 | 2007-05-08 | Eastman Kodak Company | Method and system for determining image orientation |
US7271809B2 (en) | 2002-02-19 | 2007-09-18 | Eastman Kodak Company | Method for using viewing time to determine affective information in an imaging system |
US7023979B1 (en) | 2002-03-07 | 2006-04-04 | Wai Wu | Telephony control system with intelligent call routing |
US7392230B2 (en) | 2002-03-12 | 2008-06-24 | Knowmtech, Llc | Physical neural network liquid state machine utilizing nanotechnology |
US7167574B2 (en) | 2002-03-14 | 2007-01-23 | Seiko Epson Corporation | Method and apparatus for content-based image copy detection |
AU2003207887A1 (en) | 2002-03-27 | 2003-10-08 | Koninklijke Philips Electronics N.V. | Watermaking a digital object with a digital signature |
US20070038614A1 (en) | 2005-08-10 | 2007-02-15 | Guha Ramanathan V | Generating and presenting advertisements based on context data for programmable search engines |
US20050114198A1 (en) | 2003-11-24 | 2005-05-26 | Ross Koningstein | Using concepts for ad targeting |
US7162475B2 (en) | 2002-04-17 | 2007-01-09 | Ackerman David M | Method for user verification and authentication and multimedia processing for interactive database management and method for viewing the multimedia |
KR100820385B1 (en) | 2002-04-25 | 2008-04-10 | 랜드마크 디지털 서비시즈 엘엘씨 | Robust and Invariant Audio Pattern Matching |
US7085771B2 (en) | 2002-05-17 | 2006-08-01 | Verity, Inc | System and method for automatically discovering a hierarchy of concepts from a corpus of documents |
US7370002B2 (en) | 2002-06-05 | 2008-05-06 | Microsoft Corporation | Modifying advertisement scores based on advertisement response probabilities |
EP1523717A1 (en) | 2002-07-19 | 2005-04-20 | BRITISH TELECOMMUNICATIONS public limited company | Method and system for classification of semantic content of audio/video data |
KR100944443B1 (en) | 2002-07-29 | 2010-02-25 | 이데시아 엘티디. | Method and apparatus for electro-biometric identity recognition |
US20060129822A1 (en) | 2002-08-26 | 2006-06-15 | Koninklijke Philips Electronics, N.V. | Method of content identification, device, and software |
US20050226511A1 (en) | 2002-08-26 | 2005-10-13 | Short Gordon K | Apparatus and method for organizing and presenting content |
CN1726508A (en) | 2002-10-18 | 2006-01-25 | 独立行政法人科学技术振兴机构 | Learning/thinking machine and learning/thinking method based on structured knowledge, computer system, and information generation method |
US20040162820A1 (en) | 2002-11-21 | 2004-08-19 | Taylor James | Search cart for search results |
US20040111432A1 (en) | 2002-12-10 | 2004-06-10 | International Business Machines Corporation | Apparatus and methods for semantic representation and retrieval of multimedia content |
KR20050085707A (en) | 2002-12-19 | 2005-08-29 | 코닌클리케 필립스 일렉트로닉스 엔.브이. | Reordered search of media fingerprints |
GB0229625D0 (en) | 2002-12-19 | 2003-01-22 | British Telecomm | Searching images |
US7299261B1 (en) | 2003-02-20 | 2007-11-20 | Mailfrontier, Inc. A Wholly Owned Subsidiary Of Sonicwall, Inc. | Message classification using a summary |
US20070276823A1 (en) | 2003-05-22 | 2007-11-29 | Bruce Borden | Data management systems and methods for distributed data storage and management using content signatures |
US7610306B2 (en) | 2003-06-30 | 2009-10-27 | International Business Machines Corporation | Multi-modal fusion in content-based retrieval |
JP2005071227A (en) | 2003-08-27 | 2005-03-17 | Sony Corp | Metadata distribution management system, metadata distribution management device, metadata management device by individual, client terminal, metadata distribution management method, and computer program |
US8321278B2 (en) | 2003-09-30 | 2012-11-27 | Google Inc. | Targeted advertisements based on user profiles and page profile |
US7582938B2 (en) | 2003-10-01 | 2009-09-01 | Lsi Corporation | I/O and power ESD protection circuits by enhancing substrate-bias in deep-submicron CMOS process |
US7346629B2 (en) | 2003-10-09 | 2008-03-18 | Yahoo! Inc. | Systems and methods for search processing using superunits |
WO2005057358A2 (en) | 2003-12-04 | 2005-06-23 | Perfect Market Technologies, Inc. | Search engine that dynamically generates search listings |
JP4047908B2 (en) | 2004-01-19 | 2008-02-13 | トレック・2000・インターナショナル・リミテッド | Portable data storage device using memory address mapping table |
US7872669B2 (en) | 2004-01-22 | 2011-01-18 | Massachusetts Institute Of Technology | Photo-based mobile deixis system and related techniques |
US7460709B2 (en) | 2004-01-23 | 2008-12-02 | Siemens Medical Solutions Usa, Inc. | System and method for multi-label image segmentation |
US20050198006A1 (en) | 2004-02-24 | 2005-09-08 | Dna13 Inc. | System and method for real-time media searching and alerting |
US7035740B2 (en) | 2004-03-24 | 2006-04-25 | Illumina, Inc. | Artificial intelligence and global normalization methods for genotyping |
US7724943B2 (en) | 2004-04-21 | 2010-05-25 | Siemens Medical Solutions Usa, Inc. | Rapid and robust 3D/3D registration technique |
US7382897B2 (en) | 2004-04-27 | 2008-06-03 | Microsoft Corporation | Multi-image feature matching using multi-scale oriented patches |
US7302089B1 (en) | 2004-04-29 | 2007-11-27 | National Semiconductor Corporation | Autonomous optical wake-up intelligent sensor circuit |
US7340443B2 (en) | 2004-05-14 | 2008-03-04 | Lockheed Martin Corporation | Cognitive arbitration system |
WO2005114450A1 (en) | 2004-05-14 | 2005-12-01 | Nielsen Media Research, Inc. | Methods and apparatus for identifying media content |
CA2567253A1 (en) | 2004-05-18 | 2005-11-24 | Silverbrook Research Pty Ltd | Pharmaceutical product tracking |
US20050262428A1 (en) | 2004-05-21 | 2005-11-24 | Little Chad M | System and method for contextual correlation of web document content |
CN100485574C (en) | 2004-05-28 | 2009-05-06 | 皇家飞利浦电子股份有限公司 | Method and apparatus for content item signature matching |
US20050289590A1 (en) | 2004-05-28 | 2005-12-29 | Cheok Adrian D | Marketing platform |
US20090043637A1 (en) | 2004-06-01 | 2009-02-12 | Eder Jeffrey Scott | Extended value and risk management system |
US20050289163A1 (en) | 2004-06-03 | 2005-12-29 | Eric Gordon | Occasion for media objects |
US20060004745A1 (en) | 2004-06-04 | 2006-01-05 | Agfa Corporation | Structured reporting report data manager |
US20080201299A1 (en) | 2004-06-30 | 2008-08-21 | Nokia Corporation | Method and System for Managing Metadata |
US20060015580A1 (en) | 2004-07-01 | 2006-01-19 | Home Box Office, A Delaware Corporation | Multimedia content distribution |
DE102004036154B3 (en) | 2004-07-26 | 2005-12-22 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Apparatus and method for robust classification of audio signals and method for setting up and operating an audio signal database and computer program |
EP1629730A1 (en) | 2004-08-12 | 2006-03-01 | First-to-Market N.V. | Functional sugar replacement |
US20060218191A1 (en) | 2004-08-31 | 2006-09-28 | Gopalakrishnan Kumar C | Method and System for Managing Multimedia Documents |
US7383179B2 (en) | 2004-09-28 | 2008-06-03 | Clarity Technologies, Inc. | Method of cascading noise reduction algorithms to avoid speech distortion |
US7711835B2 (en) | 2004-09-30 | 2010-05-04 | Citrix Systems, Inc. | Method and apparatus for reducing disclosure of proprietary data in a networked environment |
US7287015B2 (en) | 2004-09-30 | 2007-10-23 | International Business Machines Corporation | Methods and apparatus for transmitting signals through network elements for classification |
US7805446B2 (en) | 2004-10-12 | 2010-09-28 | Ut-Battelle Llc | Agent-based method for distributed clustering of textual information |
US7895138B2 (en) | 2004-11-23 | 2011-02-22 | Koninklijke Philips Electronics N.V. | Device and a method to process audio data, a computer program element and computer-readable medium |
JP4678180B2 (en) | 2004-12-10 | 2011-04-27 | 横河電機株式会社 | Measuring instrument |
US20060212407A1 (en) | 2005-03-17 | 2006-09-21 | Lyon Dennis B | User authentication and secure transaction system |
US20060236343A1 (en) | 2005-04-14 | 2006-10-19 | Sbc Knowledge Ventures, Lp | System and method of locating and providing video content via an IPTV network |
US20060242130A1 (en) | 2005-04-23 | 2006-10-26 | Clenova, Llc | Information retrieval using conjunctive search and link discovery |
US20060253423A1 (en) | 2005-05-07 | 2006-11-09 | Mclane Mark | Information retrieval system and method |
US7783135B2 (en) | 2005-05-09 | 2010-08-24 | Like.Com | System and method for providing objectified image renderings using recognition information from images |
US7657126B2 (en) | 2005-05-09 | 2010-02-02 | Like.Com | System and method for search portions of objects in images and features thereof |
US7660468B2 (en) | 2005-05-09 | 2010-02-09 | Like.Com | System and method for enabling image searching using manual enrichment, classification, and/or segmentation |
US7657100B2 (en) | 2005-05-09 | 2010-02-02 | Like.Com | System and method for enabling image recognition and searching of images |
US20070091106A1 (en) | 2005-10-25 | 2007-04-26 | Moroney Nathan M | Adaptive lexical classification system |
US7433895B2 (en) | 2005-06-24 | 2008-10-07 | Microsoft Corporation | Adding dominant media elements to search results |
KR101209425B1 (en) | 2005-08-17 | 2012-12-06 | 삼성전자주식회사 | Apparatus and method for transmitting/receiving a notification message in a broadcasting system and system thereof |
US7831582B1 (en) | 2005-08-23 | 2010-11-09 | Amazon Technologies, Inc. | Method and system for associating keywords with online content sources |
US20070156720A1 (en) | 2005-08-31 | 2007-07-05 | Eagleforce Associates | System for hypothesis generation |
US7603360B2 (en) | 2005-09-14 | 2009-10-13 | Jumptap, Inc. | Location influenced search results |
GB2430507A (en) | 2005-09-21 | 2007-03-28 | Stephen Robert Ives | System for managing the display of sponsored links together with search results on a mobile/wireless device |
US8023739B2 (en) | 2005-09-27 | 2011-09-20 | Battelle Memorial Institute | Processes, data structures, and apparatuses for representing knowledge |
US20070083611A1 (en) | 2005-10-07 | 2007-04-12 | Microsoft Corporation | Contextual multimedia advertisement presentation |
WO2007048124A2 (en) | 2005-10-21 | 2007-04-26 | Nielsen Media Research, Inc. | Methods and apparatus for metering portable media players |
WO2007049282A2 (en) | 2005-10-26 | 2007-05-03 | Cortica Ltd. | A computing device, a system and a method for parallel processing of data streams |
US8326775B2 (en) | 2005-10-26 | 2012-12-04 | Cortica Ltd. | Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof |
US8266185B2 (en) | 2005-10-26 | 2012-09-11 | Cortica Ltd. | System and methods thereof for generation of searchable structures respective of multimedia data content |
US9256668B2 (en) | 2005-10-26 | 2016-02-09 | Cortica, Ltd. | System and method of detecting common patterns within unstructured data elements retrieved from big data sources |
US9466068B2 (en) | 2005-10-26 | 2016-10-11 | Cortica, Ltd. | System and method for determining a pupillary response to a multimedia data element |
US8818916B2 (en) | 2005-10-26 | 2014-08-26 | Cortica, Ltd. | System and method for linking multimedia data elements to web pages |
US11019161B2 (en) | 2005-10-26 | 2021-05-25 | Cortica, Ltd. | System and method for profiling users interest based on multimedia content analysis |
US8312031B2 (en) | 2005-10-26 | 2012-11-13 | Cortica Ltd. | System and method for generation of complex signatures for multimedia data content |
US7730405B2 (en) | 2005-12-07 | 2010-06-01 | Iac Search & Media, Inc. | Method and system to present video content |
US20070162761A1 (en) | 2005-12-23 | 2007-07-12 | Davis Bruce L | Methods and Systems to Help Detect Identity Fraud |
US20070244902A1 (en) | 2006-04-17 | 2007-10-18 | Microsoft Corporation | Internet search-based television |
US8009861B2 (en) | 2006-04-28 | 2011-08-30 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiresolution, multirate spatial and temporal signatures |
US7746882B2 (en) | 2006-08-22 | 2010-06-29 | Nokia Corporation | Method and device for assembling forward error correction frames in multimedia streaming |
US8483498B2 (en) | 2006-09-21 | 2013-07-09 | Cognitens Ltd. | Methods and systems for defining, identifying and learning geometric features |
US7792868B2 (en) | 2006-11-10 | 2010-09-07 | Microsoft Corporation | Data object linking and browsing tool |
WO2008073366A2 (en) | 2006-12-08 | 2008-06-19 | Sobayli, Llc | Target object recognition in images and video |
US8351513B2 (en) | 2006-12-19 | 2013-01-08 | Allot Communications Ltd. | Intelligent video signal encoding utilizing regions of interest information |
US8468244B2 (en) | 2007-01-05 | 2013-06-18 | Digital Doors, Inc. | Digital information infrastructure and method for security designated data and with granular data stores |
US8024400B2 (en) | 2007-09-26 | 2011-09-20 | Oomble, Inc. | Method and system for transferring content from the web to mobile devices |
US20080201361A1 (en) | 2007-02-16 | 2008-08-21 | Alexander Castro | Targeted insertion of an audio - video advertising into a multimedia object |
US20080201314A1 (en) | 2007-02-20 | 2008-08-21 | John Richard Smith | Method and apparatus for using multiple channels of disseminated data content in responding to information requests |
US20080229371A1 (en) | 2007-02-22 | 2008-09-18 | Mick Colin K | Digital multimedia network including method and apparatus for high speed user download of digital files |
US8418206B2 (en) | 2007-03-22 | 2013-04-09 | United Video Properties, Inc. | User defined rules for assigning destinations of content |
JP2008250654A (en) | 2007-03-30 | 2008-10-16 | Alpine Electronics Inc | Video player and video playback control method |
US8340387B2 (en) | 2007-04-13 | 2012-12-25 | Three Palm Software | Fast preprocessing algorithms for digital mammography CAD and workstation |
US20080294278A1 (en) | 2007-05-23 | 2008-11-27 | Blake Charles Borgeson | Determining Viewing Distance Information for an Image |
US8355706B2 (en) | 2007-07-20 | 2013-01-15 | Broadcom Corporation | Method and system for utilizing context data tags to catalog data in wireless system |
US20090013347A1 (en) | 2007-06-11 | 2009-01-08 | Gulrukh Ahanger | Systems and methods for reporting usage of dynamically inserted and delivered ads |
US8171030B2 (en) | 2007-06-18 | 2012-05-01 | Zeitera, Llc | Method and apparatus for multi-dimensional content search and video identification |
US8358840B2 (en) | 2007-07-16 | 2013-01-22 | Alexander Bronstein | Methods and systems for representation and matching of video content |
JP4416020B2 (en) | 2007-08-03 | 2010-02-17 | トヨタ自動車株式会社 | Travel plan generator |
US8190355B2 (en) | 2007-10-10 | 2012-05-29 | International Business Machines Corporation | Driving assistance and monitoring |
US7853558B2 (en) | 2007-11-09 | 2010-12-14 | Vibrant Media, Inc. | Intelligent augmentation of media content |
US9984369B2 (en) | 2007-12-19 | 2018-05-29 | At&T Intellectual Property I, L.P. | Systems and methods to identify target video content |
US8285718B1 (en) | 2007-12-21 | 2012-10-09 | CastTV Inc. | Clustering multimedia search |
WO2009085336A1 (en) | 2007-12-27 | 2009-07-09 | Inc. Arbor Labs | System and method for advertisement delivery optimization |
DE112009000094T5 (en) | 2008-01-04 | 2010-11-11 | 3M Innovative Properties Co., St. Paul | Refinement of three-dimensional models |
US8954887B1 (en) | 2008-02-08 | 2015-02-10 | Google Inc. | Long press interface interactions |
US8311344B2 (en) | 2008-02-15 | 2012-11-13 | Digitalsmiths, Inc. | Systems and methods for semantically classifying shots in video |
US8009921B2 (en) | 2008-02-19 | 2011-08-30 | Xerox Corporation | Context dependent intelligent thumbnail images |
GB2471036B (en) | 2008-03-03 | 2012-08-22 | Videoiq Inc | Object matching for tracking, indexing, and search |
US10867133B2 (en) | 2008-05-01 | 2020-12-15 | Primal Fusion Inc. | System and method for using a knowledge representation to provide information based on environmental inputs |
WO2009148731A1 (en) | 2008-06-02 | 2009-12-10 | Massachusetts Institute Of Technology | Fast pattern classification based on a sparse transform |
US9785708B2 (en) | 2008-06-18 | 2017-10-10 | Gracenote, Inc. | Scalable, adaptable, and manageable system for multimedia identification |
US8655878B1 (en) | 2010-05-06 | 2014-02-18 | Zeitera, Llc | Scalable, adaptable, and manageable system for multimedia identification |
US8195689B2 (en) | 2009-06-10 | 2012-06-05 | Zeitera, Llc | Media fingerprinting and identification system |
US20110055585A1 (en) | 2008-07-25 | 2011-03-03 | Kok-Wah Lee | Methods and Systems to Create Big Memorizable Secrets and Their Applications in Information Engineering |
US20100082684A1 (en) | 2008-10-01 | 2010-04-01 | Yahoo! Inc. | Method and system for providing personalized web experience |
US20100125569A1 (en) | 2008-11-18 | 2010-05-20 | Yahoo! Inc. | System and method for autohyperlinking and navigation in url based context queries |
US9317684B2 (en) | 2008-12-23 | 2016-04-19 | Valve Corporation | Protecting against polymorphic cheat codes in a video game |
US8812226B2 (en) | 2009-01-26 | 2014-08-19 | GM Global Technology Operations LLC | Multiobject fusion module for collision preparation system |
US20100198626A1 (en) | 2009-02-04 | 2010-08-05 | Apple Inc. | Systems and methods for accessing shopping center services using a portable electronic device |
US8533848B2 (en) | 2009-02-18 | 2013-09-10 | Korea Advanced Institute Of Science And Technology | Method and system for producing multimedia fingerprint based on quantum hashing |
JP4987166B2 (en) | 2009-04-17 | 2012-07-25 | パイオニア株式会社 | Information recording apparatus and copy management program |
US8630489B2 (en) | 2009-05-05 | 2014-01-14 | Microsoft Corporation | Efficient image matching |
US20100312736A1 (en) | 2009-06-05 | 2010-12-09 | The Regents Of The University Of California | Critical Branching Neural Computation Apparatus and Methods |
US8359315B2 (en) | 2009-06-11 | 2013-01-22 | Rovi Technologies Corporation | Generating a representative sub-signature of a cluster of signatures by using weighted sampling |
CN101930444A (en) | 2009-06-18 | 2010-12-29 | 鸿富锦精密工业(深圳)有限公司 | Image search system and method |
US8295611B2 (en) | 2009-08-10 | 2012-10-23 | Pixel Forensics, Inc. | Robust video retrieval utilizing audio and video data |
KR20110080288A (en) | 2010-01-05 | 2011-07-13 | 삼성전자주식회사 | Method for converting sink device and apparatus for providing contents using the same |
US20110218946A1 (en) | 2010-03-03 | 2011-09-08 | Microsoft Corporation | Presenting content items using topical relevance and trending popularity |
US8957981B2 (en) | 2010-03-03 | 2015-02-17 | Intellectual Ventures Fund 83 Llc | Imaging device for capturing self-portrait images |
US8782046B2 (en) | 2010-03-24 | 2014-07-15 | Taykey Ltd. | System and methods for predicting future trends of term taxonomies usage |
US8296422B2 (en) | 2010-05-06 | 2012-10-23 | Sony Computer Entertainment Inc. | Method and system of manipulating data based on user-feedback |
US8990199B1 (en) | 2010-09-30 | 2015-03-24 | Amazon Technologies, Inc. | Content search with category-aware visual similarity |
WO2012056463A1 (en) | 2010-10-29 | 2012-05-03 | Hewlett-Packard Development Company, L.P. | Content recommendation for groups |
US10142687B2 (en) | 2010-11-07 | 2018-11-27 | Symphony Advanced Media, Inc. | Audience content exposure monitoring apparatuses, methods and systems |
US10034034B2 (en) | 2011-07-06 | 2018-07-24 | Symphony Advanced Media | Mobile remote media control platform methods |
US20120131454A1 (en) | 2010-11-24 | 2012-05-24 | Siddharth Shah | Activating an advertisement by performing gestures on the advertisement |
US8396876B2 (en) | 2010-11-30 | 2013-03-12 | Yahoo! Inc. | Identifying reliable and authoritative sources of multimedia content |
EP2656294A4 (en) | 2010-12-20 | 2014-12-10 | Intel Corp | Techniques for management and presentation of content |
US20120167133A1 (en) | 2010-12-23 | 2012-06-28 | Carroll John W | Dynamic content insertion using content signatures |
US8953888B2 (en) | 2011-02-10 | 2015-02-10 | Microsoft Corporation | Detecting and localizing multiple objects in images using probabilistic inference |
US9424471B2 (en) | 2011-03-01 | 2016-08-23 | Sony Corporation | Enhanced information for viewer-selected video object |
US20120239690A1 (en) | 2011-03-16 | 2012-09-20 | Rovi Technologies Corporation | Utilizing time-localized metadata |
US8909025B2 (en) | 2011-03-22 | 2014-12-09 | Georgia Tech Research Corporation | Systems and methods for retrieving causal sets of events from unstructured signals |
ES2397741B1 (en) | 2011-04-05 | 2013-10-02 | Telefónica, S.A. | METHOD AND DEVICE FOR MEASURING THE QUALITY OF TRANSMISSION SERVICES IN THE FLOW OF MEDIA IN REAL TIME. |
US9380356B2 (en) | 2011-04-12 | 2016-06-28 | The Nielsen Company (Us), Llc | Methods and apparatus to generate a tag for media content |
US20120294514A1 (en) | 2011-05-19 | 2012-11-22 | Xerox Corporation | Techniques to enable automated workflows for the creation of user-customized photobooks |
US9547938B2 (en) | 2011-05-27 | 2017-01-17 | A9.Com, Inc. | Augmenting a live view |
US9437009B2 (en) | 2011-06-20 | 2016-09-06 | University Of Southern California | Visual tracking in video images in unconstrained environments by exploiting on-the-fly context using supporters and distracters |
US8564425B2 (en) | 2011-08-19 | 2013-10-22 | Ahmad I. S. I. Al-Jafar | Blind spot monitoring system |
US9335883B2 (en) | 2011-09-08 | 2016-05-10 | Microsoft Technology Licensing, Llc | Presenting search result items having varied prominence |
US8442321B1 (en) | 2011-09-14 | 2013-05-14 | Google Inc. | Object recognition in images |
US20130086499A1 (en) | 2011-09-30 | 2013-04-04 | Matthew G. Dyor | Presenting auxiliary content in a gesture-based system |
EP2764468A4 (en) | 2011-10-05 | 2015-11-18 | Cireca Theranostics Llc | Method and system for analyzing biological specimens by spectral imaging |
US9696897B2 (en) | 2011-10-19 | 2017-07-04 | The Regents Of The University Of California | Image-based measurement tools |
US8914371B2 (en) | 2011-12-13 | 2014-12-16 | International Business Machines Corporation | Event mining in social networks |
US9135344B2 (en) | 2011-12-20 | 2015-09-15 | Bitly, Inc. | System and method providing search results based on user interaction with content |
US8886648B1 (en) | 2012-01-31 | 2014-11-11 | Google Inc. | System and method for computation of document similarity |
US9846696B2 (en) | 2012-02-29 | 2017-12-19 | Telefonaktiebolaget Lm Ericsson (Publ) | Apparatus and methods for indexing multimedia content |
US8457827B1 (en) | 2012-03-15 | 2013-06-04 | Google Inc. | Modifying behavior of autonomous vehicle based on predicted behavior of other vehicles |
US9223986B2 (en) | 2012-04-24 | 2015-12-29 | Samsung Electronics Co., Ltd. | Method and system for information content validation in electronic devices |
US20140019264A1 (en) | 2012-05-07 | 2014-01-16 | Ditto Labs, Inc. | Framework for product promotion and advertising using social networking services |
US8495489B1 (en) | 2012-05-16 | 2013-07-23 | Luminate, Inc. | System and method for creating and displaying image annotations |
US9367626B2 (en) | 2012-07-23 | 2016-06-14 | Salesforce.Com, Inc. | Computer implemented methods and apparatus for implementing a topical-based highlights filter |
US9165406B1 (en) | 2012-09-21 | 2015-10-20 | A9.Com, Inc. | Providing overlays based on text in a live camera view |
US10403042B2 (en) | 2012-11-06 | 2019-09-03 | Oath Inc. | Systems and methods for generating and presenting augmented video content |
EP2920974A1 (en) | 2012-11-16 | 2015-09-23 | Telefónica, S.A. | A method and a system for creating a user profile for recommendation purposes |
US9189021B2 (en) | 2012-11-29 | 2015-11-17 | Microsoft Technology Licensing, Llc | Wearable food nutrition feedback system |
KR101984915B1 (en) | 2012-12-03 | 2019-09-03 | 삼성전자주식회사 | Supporting Portable Device for operating an Augmented reality contents and system, and Operating Method thereof |
AU2012261715B2 (en) | 2012-12-13 | 2015-06-25 | Canon Kabushiki Kaisha | Method, apparatus and system for generating a feature vector |
US9767768B2 (en) | 2012-12-20 | 2017-09-19 | Arris Enterprises, Inc. | Automated object selection and placement for augmented reality |
US20140193077A1 (en) | 2013-01-08 | 2014-07-10 | Canon Kabushiki Kaisha | Image retrieval apparatus, image retrieval method, query image providing apparatus, query image providing method, and program |
US9116924B2 (en) | 2013-01-14 | 2015-08-25 | Xerox Corporation | System and method for image selection using multivariate time series analysis |
US20140250032A1 (en) | 2013-03-01 | 2014-09-04 | Xerox Corporation | Methods, systems and processor-readable media for simultaneous sentiment analysis and topic classification with multiple labels |
US20140282655A1 (en) | 2013-03-15 | 2014-09-18 | Jason Shay Roberts | System and method for targeted mobile ad delivery based on consumer TV programming viewing habits |
US9760803B2 (en) | 2013-05-15 | 2017-09-12 | Google Inc. | Associating classifications with images |
US9542585B2 (en) | 2013-06-06 | 2017-01-10 | Apple Inc. | Efficient machine-readable object detection and tracking |
US9262748B2 (en) | 2013-08-15 | 2016-02-16 | International Business Machines Corporation | Identifying locations of potential user errors during manipulation of multimedia content |
US9679062B2 (en) | 2013-09-18 | 2017-06-13 | Excalibur Ip, Llc | Local recommendation engine |
US9436918B2 (en) | 2013-10-07 | 2016-09-06 | Microsoft Technology Licensing, Llc | Smart selection of text spans |
US9299004B2 (en) | 2013-10-24 | 2016-03-29 | Adobe Systems Incorporated | Image foreground detection |
US20150120627A1 (en) | 2013-10-29 | 2015-04-30 | Qualcomm Incorporated | Causal saliency time inference |
US9691102B2 (en) | 2013-11-07 | 2017-06-27 | Chicago Mercantile Exchange Inc. | Transactionally deterministic high speed financial exchange having improved, efficiency, communication, customization, performance, access, trading opportunities, credit controls, and fault tolerance |
US9796400B2 (en) | 2013-11-27 | 2017-10-24 | Solfice Research, Inc. | Real time machine vision and point-cloud analysis for remote sensing and vehicle control |
US9875445B2 (en) | 2014-02-25 | 2018-01-23 | Sri International | Dynamic hybrid models for multimodal analysis |
US9158971B2 (en) | 2014-03-03 | 2015-10-13 | Xerox Corporation | Self-learning object detectors for unlabeled videos using multi-task learning |
WO2015149307A1 (en) | 2014-04-02 | 2015-10-08 | Google Inc. | Systems and methods for optimizing content layout using behavior metrics |
US9685079B2 (en) | 2014-05-15 | 2017-06-20 | Conduent Business Services, Llc | Short-time stopping detection from red light camera evidentiary photos |
US10725614B2 (en) | 2014-11-06 | 2020-07-28 | Dropbox, Inc. | Searching digital content |
US20160306798A1 (en) | 2015-04-16 | 2016-10-20 | Microsoft Corporation | Context-sensitive content recommendation using enterprise search and public search |
US10394953B2 (en) | 2015-07-17 | 2019-08-27 | Facebook, Inc. | Meme detection in digital chatter analysis |
US10152649B2 (en) | 2015-12-01 | 2018-12-11 | Mobileye Vision Technologies Ltd. | Detecting visual information corresponding to an animal |
GB2549554A (en) * | 2016-04-21 | 2017-10-25 | Ramot At Tel-Aviv Univ Ltd | Method and system for detecting an object in an image |
US9947227B1 (en) | 2016-10-13 | 2018-04-17 | Conti Temic Microelectronic Gmbh | Method of warning a driver of blind angles and a device for implementing the method |
US10346723B2 (en) * | 2016-11-01 | 2019-07-09 | Snap Inc. | Neural network for object detection in images |
US10445565B2 (en) | 2016-12-06 | 2019-10-15 | General Electric Company | Crowd analytics via one shot learning |
US10496880B2 (en) | 2017-06-27 | 2019-12-03 | Canon Kabushiki Kaisha | Method and apparatus for comparing objects in images |
US20190096135A1 (en) | 2017-09-26 | 2019-03-28 | Aquifi, Inc. | Systems and methods for visual inspection based on augmented reality |
US10762396B2 (en) | 2017-12-05 | 2020-09-01 | Utac, Llc | Multiple stage image based object detection and recognition |
US20190304102A1 (en) * | 2018-03-30 | 2019-10-03 | Qualcomm Incorporated | Memory efficient blob based object classification in video analytics |
-
2019
- 2019-11-13 US US16/681,885 patent/US10789527B1/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20230186637A1 (en) * | 2021-12-10 | 2023-06-15 | Ford Global Technologies, Llc | Systems and methods for detecting deep neural network inference quality using image/data manipulation without ground truth information |
Also Published As
Publication number | Publication date |
---|---|
US10789527B1 (en) | 2020-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11755920B2 (en) | Method for object detection using knowledge distillation | |
CN111160379B (en) | Training method and device of image detection model, and target detection method and device | |
Ren et al. | Accurate single stage detector using recurrent rolling convolution | |
CN110879959B (en) | Method and device for generating data set, and testing method and testing device using same | |
CN107038723B (en) | Method and system for estimating rod-shaped pixels | |
US11113546B2 (en) | Lane line processing method and device | |
WO2020048265A1 (en) | Methods and apparatuses for multi-level target classification and traffic sign detection, device and medium | |
US11275955B2 (en) | Lane line processing method and device | |
US9152856B2 (en) | Pedestrian detection system and method | |
US10474930B1 (en) | Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same | |
US20160093046A1 (en) | Apparatus and method for supporting computer aided diagnosis | |
US11727056B2 (en) | Object detection based on shallow neural network that processes input images | |
US10789527B1 (en) | Method for object detection using shallow neural networks | |
Alkhorshid et al. | Road detection through supervised classification | |
US20200311492A1 (en) | Object detector having shallow neural networks | |
US8406534B2 (en) | System and method for video based scene analysis | |
KR101556598B1 (en) | Apparatus and Method for object detection based on dominant pixel information | |
CN112654999B (en) | Method and device for determining labeling information | |
US10984262B2 (en) | Learning method and testing method for monitoring blind spot of vehicle, and learning device and testing device using the same | |
CN114170233B (en) | Image segmentation label generation method and device, electronic equipment and storage medium | |
US11827215B2 (en) | Method for training a driving related object detector | |
US20230119374A1 (en) | Generation of concepts for lane and road boundary prediction | |
US20230162511A1 (en) | Lane boundary detection | |
CN110889422A (en) | Method, device and equipment for judging vehicles in same driving and computer readable medium | |
US20240075925A1 (en) | Polynomial prediction of road lane metadata |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO SMALL (ORIGINAL EVENT CODE: SMAL); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
AS | Assignment |
Owner name: CORTICA LTD., ISRAEL Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RAICHELGAUZ, IGAL;SAIDA, ROI;REEL/FRAME:053516/0454 Effective date: 20200817 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YR, SMALL ENTITY (ORIGINAL EVENT CODE: M2551); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY Year of fee payment: 4 |