CN112365486A - Dust detection method, device, medium and terminal equipment based on mobile detection - Google Patents
Dust detection method, device, medium and terminal equipment based on mobile detection Download PDFInfo
- Publication number
- CN112365486A CN112365486A CN202011308506.0A CN202011308506A CN112365486A CN 112365486 A CN112365486 A CN 112365486A CN 202011308506 A CN202011308506 A CN 202011308506A CN 112365486 A CN112365486 A CN 112365486A
- Authority
- CN
- China
- Prior art keywords
- detection frame
- dust
- target detection
- moving
- target
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 207
- 239000000428 dust Substances 0.000 title claims abstract description 94
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 5
- 230000003068 static effect Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004297 night vision Effects 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000282898 Sus scrofa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a dust detection method based on motion detection, which comprises the following steps: generating a binary image through background modeling, and carrying out target detection on the binary image to obtain a target detection frame; judging the motion state of each target detection frame to obtain a motion target detection frame; judging the attribute of the moving target detection frame to determine whether the target is dust; according to the technical scheme, under the condition of not using a machine learning method, a target detection frame is generated by using background modeling and a target detection technology, the processing of the image is completed under the condition of not being influenced by resource occupation and detection effect, and then the analysis is carried out according to the attribute of a moving object, so that whether the target is dust or not is judged.
Description
Technical Field
The invention relates to the technical field of video image processing, in particular to a dust detection method, a dust detection device, a dust detection medium and terminal equipment based on motion detection.
Background
At present, the intelligent IPC plays a very important role in the monitoring field, and particularly the monitoring role played by the IPC in the late night greatly liberates manpower. In the intelligent IPC, the mobile detection is one of important functions, the algorithm can capture the changed part in the picture, and if the area of the changed part is large enough, an alarm can be triggered, so that subsequent functions such as sound alarm, light alarm or video recording are linked. However, in a night vision scene, because infrared light irradiates dust to form reflection, a moving small object is formed in a picture, and when the area of the dust is slightly large or several pieces of dust appear at the same time, the moving detection algorithm cannot judge whether the moving object is the information focused by the user, so that the moving dust can trigger false alarm.
The current technology aims at the problem of false alarm caused by dust motion in the current mobile detection, and the mainstream method is to use an enhancement algorithm of a target detection frame, specifically as follows: (1) obtaining a motion region (generally, a binary image with a resolution consistent with the frame resolution, where 1 represents that the pixel is in a motion state in the current frame, and 0 represents that the pixel is in a static state in the current frame) according to a motion detection algorithm; (2) obtaining a target external frame (human type, vehicle or specific animal) by utilizing a machine learning algorithm; (3) for each target external frame, counting the total number of pixels in the moving state in the external frame, classifying the external frames by a certain strategy (for example, whether the total number of the pixels is greater than an absolute threshold or whether the ratio of the total number of the pixels to the area of the external frame is greater than a certain threshold can be judged), regarding the external frame greater than the threshold, regarding that the whole external frame is in the moving state, otherwise, regarding that the external frame is in the static state; (4) if the external frames in the motion state exist in the picture or the sum of the areas of the external frames in all the motion states is larger than a certain value, triggering the motion detection alarm, otherwise not triggering the motion detection alarm. However, the prior art has the following problems: (1) the machine learning algorithm usually brings huge resource consumption, different algorithms may need to be configured for different object types, and if the number of target types expected to be concerned by a user is large, a plurality of machine learning algorithms for detection tasks of different objects may need to be integrated; (2) even if a multi-classification machine learning algorithm is used for controlling the problem of resource consumption, the algorithm cannot achieve perfect effect, the enhancement of the target detection frame can filter out invalid samples and can also cause missed detection of motion detection (for example, if one person walks by, pixels in a motion state appear, but the machine learning algorithm does not detect human figures, the motion pixels where the real human figures are located cannot contribute to triggering the motion detection); (3) if the user only focuses on the human figure, the human figure detection algorithm with good performance is a good choice, but if the user desires to focus on a special object (such as a wild boar and a wild chicken in a rural area), the data collection of the object is difficult due to the particularity of the object, and a model with good performance is difficult to train.
Therefore, there is a need in the market for a dust detection strategy based on motion detection, which can determine whether a moving object captured by motion detection is dust without being affected by resource occupation and detection effect.
Disclosure of Invention
The invention provides a dust detection method based on mobile detection, which aims to solve the technical problem that the prior art cannot judge whether a moving object captured by the mobile detection is dust or not and causes false alarm.
In order to solve the above technical problem, an embodiment of the present invention provides a dust detection method based on motion detection, including:
generating a binary image through background modeling, and carrying out target detection on the binary image to obtain a target detection frame;
judging the motion state of each target detection frame to obtain a motion target detection frame;
and judging the attribute of the moving target detection frame to determine whether the target is dust.
Preferably, the step of determining whether the object is dust by determining the attribute of the moving object detection frame includes:
judging the picture pixel value of the moving target detection frame, determining that the target is not dust when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, and otherwise, judging the area size of the moving target detection frame;
when the area of the moving target detection frame is determined to reach a preset area threshold, determining whether a target is dust or not according to whether a cavity exists in the moving target detection frame or not;
and when the area of the moving target detection frame is determined not to reach a preset area threshold, determining whether the target is dust or not according to the average brightness and the variance of the moving target detection frame.
Preferably, in the step of determining whether the object is dust according to whether a hole exists in the moving object detection frame, when it is determined that the hole exists in the moving object detection frame, it is determined that the object is not dust, otherwise, it is determined that the object is dust.
As a preferred scheme, the step of determining the motion state of each target detection frame to obtain a moving target detection frame includes:
counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
Accordingly, another embodiment of the present invention provides a dust detection apparatus based on motion detection, including:
the target detection module is used for generating a binary image through background modeling and carrying out target detection on the binary image to obtain a target detection frame;
the motion state module is used for judging the motion state of each target detection frame to obtain a motion target detection frame;
and the target determining module is used for judging the attribute of the moving target detection frame and determining whether the target is dust.
Preferably, the target determination module includes:
the pixel judgment unit is used for judging the picture pixel value of the moving target detection frame, when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, the target is determined not to be dust, and otherwise, the area size of the moving target detection frame is judged;
the first determining unit is used for determining whether a target is dust or not according to whether a cavity exists in the moving target detection frame or not when the area of the moving target detection frame is determined to reach a preset area threshold;
and the second determination unit is used for determining whether the target is dust or not according to the average brightness and the variance of the moving target detection frame when the area of the moving target detection frame is determined not to reach the preset area threshold.
Preferably, in the step of determining whether the object is dust or not according to whether a hole exists inside the moving object detection frame, the first determination unit is configured to determine that the object is not dust when it is determined that the hole exists inside the moving object detection frame, and otherwise, determine that the object is dust.
As a preferred scheme, the step of determining the motion state of each target detection frame by the motion state module to obtain a motion target detection frame includes:
counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program; wherein the computer program, when running, controls an apparatus in which the computer readable storage medium is located to perform the dust detection method based on motion detection as described in any one of the above.
An embodiment of the present invention further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor, when executing the computer program, implements the dust detection method based on motion detection as described in any one of the above.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the technical scheme, under the condition of not using a machine learning method, a target detection frame is generated by using background modeling and a target detection technology, the processing of the image is completed under the condition of not being influenced by resource occupation and detection effect, and then the analysis is carried out according to the attribute of a moving object, so that whether the target is dust or not is judged.
Drawings
FIG. 1: the step flow chart of the dust detection method based on the movement detection is provided by the embodiment of the invention;
FIG. 2: the invention provides a schematic flow chart of a dust detection method based on mobile detection;
FIG. 3: the present invention provides a schematic structural diagram of a dust detection apparatus based on motion detection.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, a flowchart of steps of a method for detecting dust based on motion detection according to an embodiment of the present invention includes steps 101 to 103, where the steps are as follows:
step 101, generating a binary image through background modeling, and performing target detection on the binary image to obtain a target detection frame.
Specifically, please refer to fig. 2, which is a schematic flow chart illustrating a dust detection method based on motion detection according to an embodiment of the present invention. In order to determine whether dust exists in the picture, the other two image processing techniques are needed: background modeling and object detection, detailed as follows: 1. the background modeling can maintain a long-term stable background image, when a moving object appears in the image, the foreground region of the current image can be highlighted only by comparing the pixel difference between the moving object and the background image at the corresponding position, and like the frame difference method, the background modeling can also generate a binary image with the resolution of the image (the region of the binary image with 1 has a foreground, and the region with 0 represents that no new pixel appears at the pixel point). 2. After the binary image is generated, the target detection can form an object from the more concentrated foreground points by utilizing algorithms such as a connected domain and the like, meanwhile, scattered foreground points can be filtered out, in the target detection algorithm, the area and the number of the objects expected to be generated can be reserved according to the setting of the algorithm, and the objects can be used as important criteria for subsequent dust suppression judgment.
And 102, judging the motion state of each target detection frame to obtain the motion target detection frame. In this embodiment, the present step includes: counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
Specifically, after the target detection frames are obtained through the above strategy, since the motion detection itself has a moving binary image, the number of moving pixels in each target detection frame is counted (in colloquial, after the position of the target detection frame is fixed, whether the target detection frame contains enough moving pixels is checked, if the number is large enough, the target detection frame is determined as a moving target detection frame, otherwise, the target detection frame is determined as a static target detection frame). If the area of dust is large enough, a moving object can be formed.
And 103, judging the attributes of the moving target detection frame, and determining whether the target is dust. In this embodiment, the step 103 includes steps 1031 to 1033, and each step is as follows:
and 1031, judging the picture pixel value of the moving object detection frame, determining that the object is not dust when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, and otherwise, judging the area size of the moving object detection frame.
Specifically, for each object/target detection frame considered as moving, it is determined whether a picture pixel value of the object is smaller than a background pixel value modeled by a background, if the difference is greater than a certain threshold, it is determined that the object is not dust, and it is mainly considered that dust in a night environment generally appears white-like, so that a pixel value of the dust is generally higher than a pixel value of the background, and since the dust itself is relatively sparse, the dust does not completely cover the background in the picture, but is similar to covering the background with a layer of white yarn, so that one characteristic of the dust is that a corresponding pixel is higher than the background (corresponding to "whether the number of detection frame pixel values greater than the background pixel value satisfies the threshold") if the condition is not satisfied, the target is determined not to be dust, otherwise, the size of the target detection frame is determined.
Step 1032, when it is determined that the area of the moving object detection frame reaches a preset area threshold, determining whether the object is dust according to whether a cavity exists in the moving object detection frame. In this embodiment, when it is determined that there is a hole inside the moving object detection frame, it is determined that the object is not dust, otherwise, it is determined that the object is dust.
Specifically, if the area of the target detection frame is large, whether a hole exists in the object is judged, the hole in the frame is observed from a foreground region modeled by the background, and the structure that the hole exists (foreground-background-foreground or foreground-background-foreground or foreground-a plurality of backgrounds-foreground) is found, while the hole does not exist in the night vision frame generally in dust, if the hole exists, the moving object may be a non-dust object (such as a pedestrian, and a gap can be formed between the body and the arm of the pedestrian).
And 1033, when the area of the moving object detection frame is determined not to reach the preset area threshold, determining whether the object is dust or not according to the average brightness and the variance of the moving object detection frame.
Specifically, if the area of the target detection frame is small, it is impossible to determine whether the object is dust using the two conditions, because the pattern is generally convex when the area is small, and the probability that the negative value exceeds the threshold value is low, and therefore, it is necessary to determine whether the object is dust using the average brightness and the variance when the area of the object is small.
According to the technical scheme, under the condition of considering resource occupation and effect, the dust identification logic suitable for being used in a mobile detection algorithm is provided, and when a moving object in a picture is captured by mobile detection, whether the moving object belongs to dust or not can be judged according to the characteristics of the moving object, so that developers can conveniently carry out post-processing on the dust.
Example two
Accordingly, referring to fig. 3, a schematic structural diagram of a dust detection apparatus based on motion detection according to another embodiment of the present invention includes a target detection module, a motion state module, and a target determination module, where functions of the modules are as follows:
and the target detection module is used for generating a binary image through background modeling and carrying out target detection on the binary image to obtain a target detection frame.
And the motion state module is used for judging the motion state of each target detection frame to obtain the motion target detection frame.
In this embodiment, the present step includes: counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
And the target determining module is used for judging the attribute of the moving target detection frame and determining whether the target is dust.
In this embodiment, the target determining module includes: and the pixel judgment unit is used for judging the picture pixel value of the moving target detection frame, determining that the target is not dust when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, and judging the area size of the moving target detection frame if the number of the picture pixels of which the picture pixel values are larger than the background pixel value is not larger than the preset threshold value. And the first determining unit is used for determining whether the target is dust or not according to whether a cavity exists in the moving target detection frame or not when the area of the moving target detection frame is determined to reach a preset area threshold value. In this embodiment, when it is determined that there is a hole inside the moving object detection frame, it is determined that the object is not dust, otherwise, it is determined that the object is dust. And the second determination unit is used for determining whether the target is dust or not according to the average brightness and the variance of the moving target detection frame when the area of the moving target detection frame is determined not to reach the preset area threshold.
EXAMPLE III
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program; wherein the computer program, when running, controls an apparatus on which the computer-readable storage medium is located to execute the dust detection method based on motion detection according to any of the above embodiments.
Example four
An embodiment of the present invention further provides a terminal device, where the terminal device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor, when executing the computer program, implements the dust detection method based on motion detection according to any of the above embodiments.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program) that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc., the general purpose Processor may be a microprocessor, or the Processor may be any conventional Processor, the Processor is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory may be a high speed random access memory, may also be a non-volatile memory, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), and the like, or may also be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the terminal device is only an example and does not constitute a limitation of the terminal device, and may include more or less components, or combine some components, or different components.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.
Claims (10)
1. A dust detection method based on motion detection is characterized by comprising the following steps:
generating a binary image through background modeling, and carrying out target detection on the binary image to obtain a target detection frame;
judging the motion state of each target detection frame to obtain a motion target detection frame;
and judging the attribute of the moving target detection frame to determine whether the target is dust.
2. The method as claimed in claim 1, wherein the step of determining the attribute of the moving object detection frame to determine whether the object is dust comprises:
judging the picture pixel value of the moving target detection frame, determining that the target is not dust when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, and otherwise, judging the area size of the moving target detection frame;
when the area of the moving target detection frame is determined to reach a preset area threshold, determining whether a target is dust or not according to whether a cavity exists in the moving target detection frame or not;
and when the area of the moving target detection frame is determined not to reach a preset area threshold, determining whether the target is dust or not according to the average brightness and the variance of the moving target detection frame.
3. The method as claimed in claim 2, wherein the step of determining whether the object is dust according to whether there is a hole inside the moving object detection frame determines that the object is not dust when it is determined that there is a hole inside the moving object detection frame, and otherwise determines that the object is dust.
4. The method as claimed in claim 1, wherein the step of determining the motion status of each object detection frame to obtain the motion object detection frame comprises:
counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
5. A dust detection device based on motion detection, comprising:
the target detection module is used for generating a binary image through background modeling and carrying out target detection on the binary image to obtain a target detection frame;
the motion state module is used for judging the motion state of each target detection frame to obtain a motion target detection frame;
and the target determining module is used for judging the attribute of the moving target detection frame and determining whether the target is dust.
6. The motion detection-based dust detection apparatus of claim 5, wherein the target determination module comprises:
the pixel judgment unit is used for judging the picture pixel value of the moving target detection frame, when the number of the picture pixels of which the picture pixel values are larger than the background pixel value of the background modeling is smaller than a preset threshold value, the target is determined not to be dust, and otherwise, the area size of the moving target detection frame is judged;
the first determining unit is used for determining whether a target is dust or not according to whether a cavity exists in the moving target detection frame or not when the area of the moving target detection frame is determined to reach a preset area threshold;
and the second determination unit is used for determining whether the target is dust or not according to the average brightness and the variance of the moving target detection frame when the area of the moving target detection frame is determined not to reach the preset area threshold.
7. The device as claimed in claim 6, wherein the first determining unit is configured to determine whether the object is dust based on whether there is a hole inside the moving object detection frame, and determine that the object is not dust when it is determined that there is a hole inside the moving object detection frame, and determine that the object is dust otherwise.
8. The device as claimed in claim 5, wherein the motion state module is configured to determine the motion state of each object detection frame, and the step of obtaining the motion object detection frame comprises:
counting the number of moving pixels of each target detection frame, and determining the target detection frame as a moving target detection frame when the number of the moving pixels of the target detection frame reaches a preset number threshold.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program; wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the dust detection method based on motion detection according to any one of claims 1-4.
10. A terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the movement detection based dust detection method according to any one of claims 1-4 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308506.0A CN112365486A (en) | 2020-11-20 | 2020-11-20 | Dust detection method, device, medium and terminal equipment based on mobile detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308506.0A CN112365486A (en) | 2020-11-20 | 2020-11-20 | Dust detection method, device, medium and terminal equipment based on mobile detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112365486A true CN112365486A (en) | 2021-02-12 |
Family
ID=74533019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011308506.0A Pending CN112365486A (en) | 2020-11-20 | 2020-11-20 | Dust detection method, device, medium and terminal equipment based on mobile detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365486A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657314A (en) * | 2021-08-20 | 2021-11-16 | 咏峰（大连）科技有限公司 | Method and system for recognizing dynamic and static unsafe behaviors in industrial environment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990038483A (en) * | 1997-11-05 | 1999-06-05 | 구자홍 | Dust discrimination apparatus and method for inspecting image device |
| JP2011124830A (en) * | 2009-12-11 | 2011-06-23 | Sanyo Electric Co Ltd | Imaging apparatus, and foreign matter detection method |
| US20140078353A1 (en) * | 2011-08-16 | 2014-03-20 | Nikon Corporation | Method for detecting existence of dust spots in digital images based on locally adaptive thresholding |
| CN107194886A (en) * | 2017-05-03 | 2017-09-22 | 深圳大学 | A kind of dust detection method and device for camera sensor |
| CN109727275A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Object detection method, device, system and computer readable storage medium |
| CN109829904A (en) * | 2019-01-29 | 2019-05-31 | 京东方科技集团股份有限公司 | Detect the method, apparatus of dust, electronic equipment, readable storage medium storing program for executing on screen |
| CN110322659A (en) * | 2019-06-21 | 2019-10-11 | 江西洪都航空工业集团有限责任公司 | A kind of smog detection method |
| CN111062257A (en) * | 2019-11-21 | 2020-04-24 | 四川极智朗润科技有限公司 | Micro target identification method based on morphological and kinematic characteristics |
| CN111666834A (en) * | 2020-05-20 | 2020-09-15 | 哈尔滨理工大学 | Forest fire automatic monitoring and recognizing system and method based on image recognition technology |
-
2020
- 2020-11-20 CN CN202011308506.0A patent/CN112365486A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR19990038483A (en) * | 1997-11-05 | 1999-06-05 | 구자홍 | Dust discrimination apparatus and method for inspecting image device |
| JP2011124830A (en) * | 2009-12-11 | 2011-06-23 | Sanyo Electric Co Ltd | Imaging apparatus, and foreign matter detection method |
| US20140078353A1 (en) * | 2011-08-16 | 2014-03-20 | Nikon Corporation | Method for detecting existence of dust spots in digital images based on locally adaptive thresholding |
| CN107194886A (en) * | 2017-05-03 | 2017-09-22 | 深圳大学 | A kind of dust detection method and device for camera sensor |
| CN109727275A (en) * | 2018-12-29 | 2019-05-07 | 北京沃东天骏信息技术有限公司 | Object detection method, device, system and computer readable storage medium |
| CN109829904A (en) * | 2019-01-29 | 2019-05-31 | 京东方科技集团股份有限公司 | Detect the method, apparatus of dust, electronic equipment, readable storage medium storing program for executing on screen |
| CN110322659A (en) * | 2019-06-21 | 2019-10-11 | 江西洪都航空工业集团有限责任公司 | A kind of smog detection method |
| CN111062257A (en) * | 2019-11-21 | 2020-04-24 | 四川极智朗润科技有限公司 | Micro target identification method based on morphological and kinematic characteristics |
| CN111666834A (en) * | 2020-05-20 | 2020-09-15 | 哈尔滨理工大学 | Forest fire automatic monitoring and recognizing system and method based on image recognition technology |
Non-Patent Citations (4)
| Title |
|---|
| BALAKRISHNAN RAMALINGAM 等: "Vision-Based Dirt Detection and Adaptive Tiling Scheme for Selective Area Coverage", 《JOURNAL OF SENSORS》, pages 1 - 14 * |
| M.CAMPLANI 等: "Image computing techniques to extrapolate data for dust tracking in case of an experimental accident simulation in a nuclear fusion plant", 《REVIEW OF SCIENTIFIC INSTRUMENTS》, pages 1 - 7 * |
| 张宇波 等: "基于灰度梯度共生矩阵的桌面灰尘检测算法", 《计算机应用》, vol. 39, no. 8, pages 2414 - 2419 * |
| 杨馥溢;杨璐;魏敏;何嘉;: "星空背景的多运动小目标检测方法", 《成都信息工程大学学报》, vol. 31, no. 06, pages 583 - 587 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113657314A (en) * | 2021-08-20 | 2021-11-16 | 咏峰（大连）科技有限公司 | Method and system for recognizing dynamic and static unsafe behaviors in industrial environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI714834B (en) | Human face live detection method, device and electronic equipment | |
| Sen-Ching et al. | Robust techniques for background subtraction in urban traffic video | |
| Kalsotra et al. | Background subtraction for moving object detection: explorations of recent developments and challenges | |
| CN107844794B (en) | Image recognition method and device | |
| Piccinini et al. | Reliable smoke detection in the domains of image energy and color | |
| CN112418069A (en) | High-altitude parabolic detection method and device, computer equipment and storage medium | |
| WO2011028380A2 (en) | Foreground object detection in a video surveillance system | |
| US9378556B2 (en) | Method for reducing false object detection in stop-and-go scenarios | |
| WO2011028379A2 (en) | Foreground object tracking | |
| CN108230607B (en) | Image fire detection method based on regional characteristic analysis | |
| CN111046746A (en) | License plate detection method and device | |
| CN105554414B (en) | Strong Xanthophyll cycle method and device | |
| Lage et al. | Low-cost IoT surveillance system using hardware-acceleration and convolutional neural networks | |
| CN110516572B (en) | Method for identifying sports event video clip, electronic equipment and storage medium | |
| CN109154435B (en) | Automatic lighting and safety device | |
| CN112365486A (en) | Dust detection method, device, medium and terminal equipment based on mobile detection | |
| Ghasemi et al. | A real-time multiple vehicle classification and tracking system with occlusion handling | |
| CN113947744A (en) | Fire image detection method, system, equipment and storage medium based on video | |
| CN116866711A (en) | Energy-saving monitoring method, system, equipment and storage medium | |
| CN110135224B (en) | Method and system for extracting foreground target of surveillance video, storage medium and terminal | |
| Buch et al. | Local feature saliency classifier for real-time intrusion monitoring | |
| US11295454B1 (en) | Object detection method, security device, and readable storage medium | |
| JP2024516642A (en) | Behavior detection method, electronic device and computer-readable storage medium | |
| CN111259832B (en) | Method, device, machine-readable medium and system for identifying dogs | |
| CN114283496A (en) | Intelligent camera module capable of preventing face overexposure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |