CN108537764A - A kind of man-machine hybrid intelligent control loop - Google Patents
A kind of man-machine hybrid intelligent control loop Download PDFInfo
- Publication number
- CN108537764A CN108537764A CN201810183771.7A CN201810183771A CN108537764A CN 108537764 A CN108537764 A CN 108537764A CN 201810183771 A CN201810183771 A CN 201810183771A CN 108537764 A CN108537764 A CN 108537764A
- Authority
- CN
- China
- Prior art keywords
- image
- fusion
- subsystem
- module
- pseudo
- 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.)
- Withdrawn
Links
- 230000000694 effects Effects 0.000 claims abstract description 17
- 230000004927 fusion Effects 0.000 claims description 52
- 238000002156 mixing Methods 0.000 claims description 24
- 239000003086 colorant Substances 0.000 claims description 22
- 238000005070 sampling Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 4
- 238000000701 chemical imaging Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/10—Interpretation of driver requests or demands
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/10048—Infrared image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30196—Human being; Person
-
- 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
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30268—Vehicle interior
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Mechanical Engineering (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of man-machine hybrid intelligent control loops, including sensing subsystem, Activity recognition subsystem, command subsystem and control subsystem, the sensing subsystem is used to obtain travel condition of vehicle information and current traffic information using sensor, and travel condition of vehicle information and current traffic information are sent to control subsystem, the Activity recognition subsystem is for being identified the human body behavior of driver, described instruction subsystem is used to convert human body behavior to steering instructions, and steering instructions are sent to control subsystem, the control subsystem is used for according to travel condition of vehicle information, current traffic information and steering instructions control vehicle.Beneficial effects of the present invention are:It a kind of man-machine hybrid intelligent control loop is provided, this system overcomes the defect trusted is lacked to system in unmanned, improves Decision-making Function of the driver in driving, the significant increase driving experience of user.
Description
Technical field
The present invention relates to intelligent driving technical fields, and in particular to a kind of man-machine hybrid intelligent control loop.
Background technology
With the development of artificial intelligence technology, unmanned technology also develops rapidly, Unmanned Systems and manned
System is compared, be by people exclude except control loop, still, Unmanned Systems showed when in face of complex road condition compared with
Difference.
Human bodys' response is an emerging research direction in artificial intelligence field, be with a wide range of applications with it is non-
The economic value of Chang Keguan, the application field being related to include mainly:Video monitoring, medical diagnosis and monitoring, motion analysis, intelligence
Human-computer interaction, virtual reality etc..The corresponding groundwork flow of Human bodys' response is:Various kinds of sensors is selected to obtain human body row
For data information, and the behavioral trait of sensor characteristics and people is combined to establish rational behavior model, on this basis from original
Extracted in gathered data to behavior type have stronger descriptive power feature, and using suitable method to these features into
Row training, and then realize the pattern-recognition to human body behavior.The image preprocessing of high quality is the key that Activity recognition research, existing
The ineffective very big reason of somebody's body Activity recognition is not obtain the image of high quality.
Invention content
In view of the above-mentioned problems, the present invention is intended to provide a kind of man-machine hybrid intelligent control loop.
The purpose of the present invention is realized using following technical scheme:
Provide a kind of man-machine hybrid intelligent control loop, including sensing subsystem, Activity recognition subsystem, instruction subsystem
System and control subsystem, the sensing subsystem are used to obtain travel condition of vehicle information and current road conditions letter using sensor
Breath, and travel condition of vehicle information and current traffic information are sent to control subsystem, the Activity recognition subsystem is used for
The human body behavior of driver is identified, described instruction subsystem is used to convert human body behavior to steering instructions, and will drive
Sail instruction and be sent to control subsystem, the control subsystem be used for according to travel condition of vehicle information, current traffic information and
Steering instructions control vehicle.
Beneficial effects of the present invention are:A kind of man-machine hybrid intelligent control loop is provided, this system overcomes nobody to drive
It the defect trusted is lacked to system in sailing, improves Decision-making Function of the driver in driving, the significant increase driving of user
Experience.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural schematic diagram of the present invention;
Reference numeral:
Sensing subsystem 1, Activity recognition subsystem 2, command subsystem 3, control subsystem 4.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of man-machine hybrid intelligent control loop of the present embodiment, including sensing subsystem 1, Activity recognition
System 2, command subsystem 3 and control subsystem 4, the sensing subsystem 1 are used to obtain travel condition of vehicle using sensor
Information and current traffic information, and travel condition of vehicle information and current traffic information are sent to control subsystem 4, the row
It is that recognition subsystem 2 is used to that the human body behavior of driver to be identified, described instruction subsystem 3 is for converting human body behavior
For steering instructions, and steering instructions are sent to control subsystem 4, the control subsystem 4 is used for according to travel condition of vehicle
Information, current traffic information and steering instructions control vehicle.
A kind of man-machine hybrid intelligent control loop is present embodiments provided, this system overcomes lacked to system in unmanned
The defect of weary trust, improve Decision-making Function of the driver in driving, the significant increase driving experience of user.
Preferably, the Activity recognition subsystem 2 include image capture module, image co-registration module, characteristic extracting module,
Activity recognition module, described image acquisition module are acquired using visible light, infrared multi-spectral imaging system on human body image,
Described image Fusion Module obtains color fusion image, the feature for being merged to visible images and infrared image
Extraction module is used to extract human body target profile according to color fusion image, and the Activity recognition module is used for according to human body target
Human body behavior is identified in profile.
This preferred embodiment Activity recognition subsystem obtains human body image simultaneously using visible light, infrared multi-spectral imaging system
Fusion treatment is carried out to image, the image of high quality is obtained, contributes to the detectivity and tracing property that promote follow-up human body, adopt
With color fusion image, it is more in line with the visual signature of the mankind.
Preferably, described image Fusion Module includes the first Fusion Module, the second Fusion Module, third Fusion Module, institute
It states the first Fusion Module to merge visible images and infrared image in non-down sampling contourlet transformation domain, obtains gray scale and melt
Image is closed, second Fusion Module obtains pseudo-colours blending image, the third Fusion Module root according to grayscale fusion image
Color fusion image is obtained according to pseudo-colours blending image;
First Fusion Module merges visible images and infrared image in non-down sampling contourlet transformation domain,
Specially:
Non-down sampling contourlet decomposition is carried out to visible images P and infrared image Q, obtains corresponding sub-band division coefficientWithLPAnd LQThe low frequency sub-band coefficient of visible images and infrared image is indicated respectively,WithPoint
Not Biao Shi in j-th of scale high-frequency sub-band of visible light and infrared image k-th of direction sub-band coefficients;
Low frequency sub-band is merged using following formula:
In formula, LR(x, y) indicates the corresponding low frequency sub-band coefficients of grayscale fusion image R,Wherein,
P indicates that the average gray value of infrared image, H (x, y) indicate the gray value of pixel (x, y) in infrared image;
High-frequency sub-band is merged using following formula:
In formula,Indicate the directional subband coefficient of fusion grayscale fusion image R, vP(x, y) indicates visible images
The variance yields of directional subband coefficient, v in n × n windows centered on pixel (x, y)Q(x, y) indicates infrared image with pixel
The variance yields of directional subband coefficient in n × n windows centered on point (x, y);
Grayscale fusion image R is reconstructed according to the low frequency sub-band coefficient of grayscale fusion image and high-frequency sub-band coefficient;
The blending image that traditional image interfusion method obtains usually exist target-to-background contrast is relatively low, image more
The deficiencies of fuzzy.This preferred embodiment is improved by carrying out multiple dimensioned, multi-direction fusion to visible images and infrared image
Image co-registration is horizontal, by determining image co-registration mode, can preferably merge the information of the image of different-waveband, the ash of acquisition
It is more abundant to spend blending image details, textural characteristics.
Preferably, second Fusion Module obtains pseudo-colours blending image according to grayscale fusion image, specially:
Pseudo-colours blending image is obtained in YUV color spaces using following formula:
In formula, Y (x, y), U (x, y), V (x, y) indicate pseudo-colours blending image in the component of YUV color spaces, R respectively
(x, y) indicates that the grayscale fusion image of visible images and infrared image, P (x, y) indicate that visible images, Q (x, y) indicate red
Outer image;
The third Fusion Module obtains color fusion image according to pseudo-colours blending image, specially:
Using the color visible image shot under the conditions of a width natural daylight as image is referred to, and the reference picture is become
YUV color spaces are shifted to, according to gray average and variance of the reference picture in each channel of YUV color spaces, adjust pseudo-colours
The corresponding YUV component values of blending image, the pseudo-colours blending image after being adjusted specifically are carried out using following formula:
In formula, S and W correspond to reference picture and pseudo-colours blending image, Y respectively1(x,y)、U1(x,y)、V1(x, y) difference
The pseudo-colours blending image after adjustment is indicated in the component of YUV color spaces, μ and σ indicate each color in YUV color spaces respectively
The gray average and variance in channel;
By the pseudo-colours blending image after adjustment from YUV color notation conversion space to RGB color, color integration figure is obtained
Picture.
Complementary information between this preferred embodiment organic combination different-waveband, enriches the detailed information of image, makes one
Body target is enhanced, to improve accuracy and robustness to target acquisition and tracking;Meanwhile blending image can be meter
Calculation machine visual analysis provides higher-quality source images;In addition, the color fusion image after color adjusts has Natural color
Color visual effect can improve the degree of fatigue that observer watches the perception of scene, reduction observer video, this is for certain
The Activity recognition application that observer participates in is needed to be of great significance.
Drive the vehicle using the man-machine hybrid intelligent control loop of the present invention, with selecting departure place, choose 5 destinations into
Row experiment, respectively destination 1, destination 2, destination 3, destination 4, destination 5, to driving time and driver's satisfaction
It is counted, is compared compared with Unmanned Systems, generation has the beneficial effect that shown in table:
Driving time shortens | Driver's satisfaction improves | |
Destination 1 | 29% | 27% |
Destination 2 | 27% | 26% |
Destination 3 | 26% | 26% |
Destination 4 | 25% | 24% |
Destination 5 | 24% | 22% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of man-machine hybrid intelligent control loop, which is characterized in that including sensing subsystem, Activity recognition subsystem, instruction
Subsystem and control subsystem, the sensing subsystem are used to obtain travel condition of vehicle information and current road conditions using sensor
Information, and travel condition of vehicle information and current traffic information are sent to control subsystem, the Activity recognition subsystem is used
It is identified in the human body behavior of driver, described instruction subsystem is used to convert human body behavior to steering instructions, and will
Steering instructions are sent to control subsystem, and the control subsystem is used for according to travel condition of vehicle information, current traffic information
Vehicle is controlled with steering instructions.
2. man-machine hybrid intelligent control loop according to claim 1, which is characterized in that the Activity recognition subsystem packet
Image capture module, image co-registration module, characteristic extracting module, Activity recognition module are included, described image acquisition module uses can
Light-exposed, infrared multi-spectral imaging system on human body image is acquired, described image Fusion Module be used for visible images and
Infrared image is merged, and color fusion image is obtained, and the characteristic extracting module is used to extract people according to color fusion image
Body objective contour, the Activity recognition module is for being identified human body behavior according to human body target profile.
3. man-machine hybrid intelligent control loop according to claim 2, which is characterized in that described image Fusion Module includes
First Fusion Module, the second Fusion Module, third Fusion Module, first Fusion Module is in non-down sampling contourlet transformation domain
Visible images and infrared image are merged, grayscale fusion image is obtained, second Fusion Module is merged according to gray scale
Image obtains pseudo-colours blending image, and the third Fusion Module obtains color fusion image according to pseudo-colours blending image.
4. man-machine hybrid intelligent control loop according to claim 3, which is characterized in that first Fusion Module is non-
Down sampling contourlet transformation domain merges visible images and infrared image, specially:
Non-down sampling contourlet decomposition is carried out to visible images P and infrared image Q, obtains corresponding sub-band division coefficientWithLPAnd LQThe low frequency sub-band coefficient of visible images and infrared image is indicated respectively,WithPoint
Not Biao Shi in j-th of scale high-frequency sub-band of visible light and infrared image k-th of direction sub-band coefficients;
Low frequency sub-band is merged using following formula:
In formula, LR(x, y) indicates the corresponding low frequency sub-band coefficients of grayscale fusion image R,Wherein, p tables
Show that the average gray value of infrared image, H (x, y) indicate the gray value of pixel (x, y) in infrared image;
High-frequency sub-band is merged using following formula:
In formula,Indicate the directional subband coefficient of fusion grayscale fusion image R, vP(x, y) indicates visible images with picture
The variance yields of directional subband coefficient, v in n × n windows centered on vegetarian refreshments (x, y)Q(x, y) indicates infrared image with pixel
The variance yields of directional subband coefficient in n × n windows centered on (x, y);
Grayscale fusion image R is reconstructed according to the low frequency sub-band coefficient of grayscale fusion image and high-frequency sub-band coefficient.
5. man-machine hybrid intelligent control loop according to claim 4, which is characterized in that second Fusion Module according to
Grayscale fusion image obtains pseudo-colours blending image, specially:
Pseudo-colours blending image is obtained in YUV color spaces using following formula:
In formula, Y (x, y), U (x, y), V (x, y) indicate pseudo-colours blending image in the component of YUV color spaces, R (x, y) respectively
Indicate that the grayscale fusion image of visible images and infrared image, P (x, y) indicate that visible images, Q (x, y) indicate infrared figure
Picture.
6. man-machine hybrid intelligent control loop according to claim 5, which is characterized in that the third Fusion Module according to
Pseudo-colours blending image obtains color fusion image, specially:
Using the color visible image shot under the conditions of a width natural daylight as image is referred to, and the reference picture is converted into
YUV color spaces, according to gray average and variance of the reference picture in each channel of YUV color spaces, adjustment pseudo-colours fusion
The corresponding YUV component values of image, the pseudo-colours blending image after being adjusted specifically are carried out using following formula:
In formula, S and W correspond to reference picture and pseudo-colours blending image, Y respectively1(x,y)、U1(x,y)、V1(x, y) is indicated respectively
For pseudo-colours blending image after adjustment in the component of YUV color spaces, μ and σ indicate each Color Channel in YUV color spaces respectively
Gray average and variance;
By the pseudo-colours blending image after adjustment from YUV color notation conversion space to RGB color, color fusion image is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810183771.7A CN108537764A (en) | 2018-03-06 | 2018-03-06 | A kind of man-machine hybrid intelligent control loop |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810183771.7A CN108537764A (en) | 2018-03-06 | 2018-03-06 | A kind of man-machine hybrid intelligent control loop |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108537764A true CN108537764A (en) | 2018-09-14 |
Family
ID=63486768
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810183771.7A Withdrawn CN108537764A (en) | 2018-03-06 | 2018-03-06 | A kind of man-machine hybrid intelligent control loop |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537764A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255774A (en) * | 2018-09-28 | 2019-01-22 | 中国科学院长春光学精密机械与物理研究所 | A kind of image interfusion method, device and its equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106548644A (en) * | 2016-11-30 | 2017-03-29 | 深圳明创自控技术有限公司 | A kind of automated driving system |
CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
CN107719376A (en) * | 2017-09-18 | 2018-02-23 | 清华大学 | Man-machine mixing enhancing intelligent driving system and electric automobile |
-
2018
- 2018-03-06 CN CN201810183771.7A patent/CN108537764A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106548644A (en) * | 2016-11-30 | 2017-03-29 | 深圳明创自控技术有限公司 | A kind of automated driving system |
CN107253485A (en) * | 2017-05-16 | 2017-10-17 | 北京交通大学 | Foreign matter invades detection method and foreign matter intrusion detection means |
CN107719376A (en) * | 2017-09-18 | 2018-02-23 | 清华大学 | Man-machine mixing enhancing intelligent driving system and electric automobile |
Non-Patent Citations (1)
Title |
---|
吴燕燕等: "结合NSST和颜色对比度增强的彩色夜视方法", 《光电工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255774A (en) * | 2018-09-28 | 2019-01-22 | 中国科学院长春光学精密机械与物理研究所 | A kind of image interfusion method, device and its equipment |
CN109255774B (en) * | 2018-09-28 | 2022-03-25 | 中国科学院长春光学精密机械与物理研究所 | Image fusion method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069746B (en) | Video real-time face replacement method and its system based on local affine invariant and color transfer technology | |
CN101795400B (en) | Method for actively tracking and monitoring infants and realization system thereof | |
CN109241830B (en) | Classroom lecture listening abnormity detection method based on illumination generation countermeasure network | |
CN107103277B (en) | Gait recognition method based on depth camera and 3D convolutional neural network | |
CN104992189B (en) | Shoal of fish abnormal behaviour recognition methods based on deep learning network model | |
CN108830150A (en) | One kind being based on 3 D human body Attitude estimation method and device | |
CN106256606A (en) | A kind of lane departure warning method based on vehicle-mounted binocular camera | |
CN104083258A (en) | Intelligent wheel chair control method based on brain-computer interface and automatic driving technology | |
CN110728241A (en) | Driver fatigue detection method based on deep learning multi-feature fusion | |
CN102982518A (en) | Fusion method of infrared image and visible light dynamic image and fusion device of infrared image and visible light dynamic image | |
CN109949593A (en) | A kind of traffic lights recognition methods and system based on crossing priori knowledge | |
CN103914699A (en) | Automatic lip gloss image enhancement method based on color space | |
CN106874884A (en) | Human body recognition methods again based on position segmentation | |
Dong et al. | Infrared image colorization using a s-shape network | |
CN106815826A (en) | Night vision image Color Fusion based on scene Recognition | |
CN110516633A (en) | A kind of method for detecting lane lines and system based on deep learning | |
CN105069745A (en) | face-changing system based on common image sensor and enhanced augmented reality technology and method | |
CN110378234A (en) | Convolutional neural networks thermal imagery face identification method and system based on TensorFlow building | |
CN109583349A (en) | A kind of method and system for being identified in color of the true environment to target vehicle | |
CN114426069B (en) | Indoor rescue vehicle based on real-time semantic segmentation and image semantic segmentation method | |
CN105930793A (en) | Human body detection method based on SAE characteristic visual learning | |
CN104253994B (en) | A kind of night monitoring video real time enhancing method merged based on sparse coding | |
CN108537764A (en) | A kind of man-machine hybrid intelligent control loop | |
CN108009512A (en) | A kind of recognition methods again of the personage based on convolutional neural networks feature learning | |
Sugirtha et al. | Semantic segmentation using modified u-net for autonomous driving |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180914 |
|
WW01 | Invention patent application withdrawn after publication |