CN102629314A - Gesture recognition system based on infrared image and method thereof - Google Patents
Gesture recognition system based on infrared image and method thereof Download PDFInfo
- Publication number
- CN102629314A CN102629314A CN2012100368461A CN201210036846A CN102629314A CN 102629314 A CN102629314 A CN 102629314A CN 2012100368461 A CN2012100368461 A CN 2012100368461A CN 201210036846 A CN201210036846 A CN 201210036846A CN 102629314 A CN102629314 A CN 102629314A
- Authority
- CN
- China
- Prior art keywords
- image
- infrared
- module
- staff
- reference voltage
- 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
Images
Abstract
The invention discloses a gesture recognition system based on an infrared image. The system comprises an infrared illumination module, a front end image processing module and a digital image gesture segmentation and tracking module. An infrared video acquisition unit comprises a CMOS optical sensing chip and a lens assembly. The front end image processing module comprises the infrared video acquisition unit and a FPGA control and output unit. The FPGA control and output unit comprises an image quality assessment module, a reference voltage adjustment module and an output module. The image quality assessment module is used to determine whether a hand area and a hand surrounding area present a same or similar pixel value in a digital image. If the hand area and the hand surrounding area present the same or similar pixel value in the digital image, a reference voltage of the CMOS optical sensing chip is adjusted. If the hand area and the hand surrounding area do not present the same or similar pixel value in the digital image, the digital image is directly output. The invention also discloses a gesture recognition method of the system. In the prior art, under low illumination level or variable illumination environment, recognition is unstable. By using the system and the method of the invention, the above problem can be solved, the quality of infrared digital video data and stability of the system can be increased.
Description
Technical field
The present invention relates to the gesture identification system and method, particularly a kind of gesture identification system and method based on infrared image.
Background technology
Develop rapidly along with human-computer interaction technology; Various novel man-machine interaction modes continue to bring out; As one of them branch, along with the proposition and the improvement of various new algorithms, its importance highlights day by day based on the man-machine interaction mode of gesture identification; And will come into huge numbers of families in the near future, become the main mode of man-machine interaction in the family.
Yet; This type of gesture identification is based on the man-machine interaction mode of Digital Image Processing; Be faced with an insoluble problem always, promptly in the camera scene various photoenvironments for the influence of digital picture quality, comprising appearing of low-light (level) situation hypograph details; Various colorama lightings are to the interference of certain objects color in the image, and imageing sensor is crossed bright for the incompatible integral image that causes of intensity of illumination variation or crossed dark phenomenon etc.To some such problems, academia has proposed many solutions, comprising shades of colour shape constancy algorithm, adaptive color sorter etc.
Color constancy is that this preprocessing technical field is used theoretically comparatively widely; Its basic definition is; When the color of light that is radiated at body surface changes; People still remain unchanged to the intuition of this color of object surface, and the color of object is by incident light decision, but determine by the reflecting attribute of object itself.Based on such definition; People have proposed many methods, comprising Retinex algorithm, grey-world theoretical algorithm, chromatogram mapping algorithm, color correlation algorithm, Bayesian decision making algorithm, neural network color constancy algorithm, based on color constancy algorithm of reference color etc.Adaptive color classification device then is on the basis of original particular color training; Real-time correlation parameter according to scene situation adjusting sorter; Guarantee that sorter can adapt to the variation of scene illumination fully for the classification of color, accomplishes the extraction of certain objects color under the various photoenvironments.Yet such certain methods all is based on Digital Image Processing, and its preferably treatment effect all only to specific operating environment.And this method is started with from front end; On the video acquisition cuicuit, do improvement, guaranteed that the rear end gesture is extracted and the quality of track algorithm input picture, reduced the burden of back-end algorithm; The characteristics that form images down to the infrared illumination environment simultaneously; Select for use corresponding Processing Algorithm to carry out staff and cut apart, reduced its computation complexity, make its realization on engineering become possibility.
Summary of the invention
In order to overcome the above-mentioned deficiency of prior art, the object of the present invention is to provide a kind of gesture identification system based on infrared image, another object of the present invention is to provide the gesture identification method of said system.
The object of the invention is realized through following technical scheme:
A kind of gesture identification system based on infrared image; Comprise that infrared illumination module, front end image processing module and digital picture gesture cut apart and tracking module; It is characterized in that said front end image processing module comprises interconnective infrared video collecting unit, FPGA control and output unit
Said infrared video collecting unit comprises the CMOS optical sensing chip and the lens assembly of adjustable reference voltage, and said CMOS optical sensing chip is integrated with DSP (digital signal processor) chip; Said lens assembly is installed in the place ahead of CMOS optical sensing chip;
Said FPGA (field programmable gate array) control and output unit comprise image quality measure module, reference voltage adjustment module and the output module that connects successively; Said image quality measure module is used for judging whether hand region presents identical or close pixel value in digital picture with the hand peripheral region; If then control reference voltage VREF1 and VREF2 that the reference voltage adjustment module is regulated A/D converter in the CMOS optical sensing chip; If not, then through the direct output digital image of output unit.
Said infrared illumination module is made up of 4 infrared LED fluorescent tubes, and said 4 infrared LED fluorescent tubes are evenly distributed on around the camera lens of lens assembly, is less than or equal to 3cm with the distance of optical center, and angle is 90 ° between the line of each LED fluorescent tube and optical center.
The diameter parameters of said LED fluorescent tube is 8mm, and emission angle is greater than 45 °.
The place ahead of said camera lens is equipped with filter plate, and the transmission region of said filter plate is corresponding with the luminous wave band of infrared LED fluorescent tube.
The gesture identification method of above-mentioned gesture identification system based on infrared image may further comprise the steps:
(1) infrared illumination module illuminates the gesture operation zone;
(2) the infrared video collecting unit is gathered infrared image, specifically may further comprise the steps:
(2-1) CMOS optical sensing chip obtains the aanalogvoltage V of pixel
0
(2-2) according to the reference voltage VREF1 and the VREF2 of CMOS optical sensing chip, handle each pixel aanalogvoltage V of digital picture that CMOS optical sensing chip is obtained through A/D converter and dsp chip
0Quantize, the voltage of each two field picture pixel is turned to 8bit data: VREF1≤V
0≤VREF2 obtains digital picture;
(2-3) can the image quality measure module be judged and gesture be identified: whether hand region presents identical or close pixel value with the hand peripheral region in digital picture; If; Then control the reference voltage adjustment module and regulate the reference voltage VREF1 and the VREF2 of A/D converter, repeating step (2-2)～(2-3); If not, then through the direct output digital image of output unit;
(3) digital picture being carried out gesture cuts apart and follows the tracks of.
Step (3) is said carries out gesture to digital picture and cuts apart and follow the tracks of, and specifically may further comprise the steps:
The infrared image I that (3-1) the infrared video collecting unit is collected
0, extract among its RGB arbitrary chromatograph or its gray processing obtained image I
1
(3-2) use the good sorter of training in advance to I
1Image is handled, and finds in the image staff zone, and definite staff the position P and the scope S that in image, occur;
(3-3) according to DID in the scope S, the highest gray-scale value of probability of occurrence in the statistical regions, with this gray-scale value as threshold value T;
(3-4) estimate the gray-scale value scope that staff is regional, confirm overall binary-state threshold, obtain binary image I with threshold value T
B
(3-5) to I
1Gray level image uses frame difference method, confirms human hand movement frame difference image I
F
(3-6) at I
BImage can normally be partitioned under the situation of staff, confirms staff centroid position coordinate, upgrades P and confirms scope S position again, and staff is followed the tracks of; At I
BImage can not normally be partitioned under the situation of staff, uses frame difference image I
F, confirm the staff center-of-mass coordinate, upgrade P and confirm scope S position again, staff is followed the tracks of.
Compared with prior art, the present invention has the following advantages and beneficial effect: the present invention guarantees the uniqueness and the stability of scene lighting through utilizing infrared illumination, can effectively solve recognizer problem of unstable under low-light (level) or the illumination variation environment.Simultaneously; Through getting involved obtaining of front end video data, adaptive video data is quantized, make that the details of area-of-interest (people's hand position) is more clear and outstanding in the infrared image; Further improve the quality of infrared digital of digital video data, guaranteed the discrimination of rear end recognizer.On the other hand,, existing gesture identification method is improved, make algorithm can follow total system cooperative cooperating better, guarantee the stability of system to the characteristics of the existing infrared imaging of the present invention.
Description of drawings
Fig. 1 is the formation synoptic diagram that the present invention is based on the gesture identification system of infrared image.
Fig. 2 is the synoptic diagram of infrared illumination module, and wherein 1 is infrared LED, and 2 for containing the optical filter camera lens.
Fig. 3 judges the process flow diagram that can gesture be identified for the image quality measure module.
Fig. 4 is for to carry out the process flow diagram that gesture is cut apart and followed the tracks of to digital picture.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is done to specify further, but embodiment of the present invention is not limited thereto.
Embodiment
As shown in Figure 1; Gesture identification system based on infrared image; Comprise that infrared illumination module, front end image processing module, digital picture gesture cut apart and tracking module, said front end image processing module comprises interconnective infrared video collecting unit and FPGA control and output unit.
Said infrared video collecting unit comprises the CMOS optical sensing chip and the lens assembly of adjustable reference voltage, and said CMOS optical sensing chip is integrated with dsp chip; Said lens assembly is installed in the place ahead of CMOS optical sensing chip.
As shown in Figure 2; Said infrared illumination module is made up of 4 infrared LED fluorescent tubes 1; Said 4 infrared LED fluorescent tubes are evenly distributed on around the camera lens 2 of lens assembly, are less than or equal to 3cm with the distance of optical center, and angle is 90 ° between the line of each LED fluorescent tube and optical center; The diameter parameters of LED fluorescent tube is for being 8mm, and emission angle is greater than 45 °.
Said FPGA control and output unit comprise image quality measure module, reference voltage adjustment module and the output module that connects successively; Said image quality measure module is used for judging whether hand region presents identical or close pixel value in digital picture with the hand peripheral region; If then control reference voltage VREF1 and VREF2 that the reference voltage adjustment module is regulated A/D converter in the CMOS optical sensing chip; If not, then through the direct output digital image of output unit.
The gesture identification method of above-mentioned gesture identification system based on infrared image may further comprise the steps:
(1) infrared illumination module illuminates the gesture operation zone;
(2) the infrared video collecting unit is gathered infrared image, specifically may further comprise the steps:
(2-1) CMOS optical sensing chip obtains the aanalogvoltage V of pixel
0, according to cmos semiconductor device photoelectric effect, in theory, the photon energy that pixel obtains is high more, aanalogvoltage V
0Be worth big more;
(2-2) according to the reference voltage VREF1 and the VREF2 of CMOS optical sensing chip, handle each pixel aanalogvoltage V of digital picture that CMOS optical sensing chip is obtained through A/D converter and dsp chip
0Quantize, the voltage of each two field picture pixel is turned to 8bit data: VREF1≤V
0≤VREF2 obtains digital picture;
(2-3) the image quality measure module judges that can gesture be identified; As shown in Figure 3, be specially: whether hand region presents identical or close pixel value with the hand peripheral region in digital picture, if; Then think and to be identified; Control reference voltage adjustment module is regulated the reference voltage VREF1 and the VREF2 of A/D converter: analyze reason, if staff area pixel gray-scale value is higher, can think that its corresponding analog voltage is higher; Then heighten reference voltage VREF1 and VREF2, make staff regional simulation voltage in VREF1～VREF2 numerical range; In like manner,, can think that its corresponding analog voltage is lower, then turn down reference voltage VREF1 and VREF2, make staff regional simulation voltage in VREF1～VREF2 numerical range if staff area pixel gray-scale value is lower; Behind the reference voltage VREF1 and VREF2 that obtains proofreading and correct, repeating step (2-2)～(2-3); If inequality, then think and to be identified, through the direct output digital image of output unit;
For example; Suppose that CMOS works under default reference voltage VREF1=0V and VREF2=5V situation; Though hand and the brightness under the irradiation of infrared lamp of its peripheral region object are had any different, be 5V like the aanalogvoltage of hand respective pixel, the aanalogvoltage of staff neighboring area object respective pixel is 4.99V; Then their pixel values decimal system numerical value after the A/D conversion is 255, both indifferences behind the digital quantization.Through the image quality measure module analysis; Hardware dynamic adjustment reference voltage VREF1 and VREF2 are respectively 4V and 5V under above-mentioned situation; Retroactive effect is in CMOS; This moment is because A/D transformation result decimal system numerical value is respectively 255 and 252, so the pixel that equates of clothes that obtained last time and hand has obtained the pixels with different value through the feedback regulation reference voltage.Same reason; When hand in the image and neighboring area identical and actual both brightness of object digital pixel value are had any different,, dynamically adjust CMOS reference voltage VREF1 and VREF2 through the feedback of FPGA; Can the nuance of hand and surrounding environment brightness be displayed in digital picture; Thereby make back-end algorithm to extract staff like a cork and realize gesture identification, the digital picture of output remains the 8bit data, and the image that requires of non-conformity of quality hop algorithm will abandon simultaneously.
(3) digital picture is carried out gesture and cut apart and follow the tracks of, as shown in Figure 4, specifically may further comprise the steps:
The infrared image I that (3-1) the infrared video collecting unit is collected
0, extract among its RGB arbitrary chromatograph or its gray processing obtained image I
1
(3-2) use the good sorter of training in advance to I
1Image is handled, and finds in the image staff zone, and definite staff the position P and the scope S that in image, occur;
(3-3) according to DID in the scope S, the highest gray-scale value of probability of occurrence in the statistical regions, with this gray-scale value as threshold value T;
(3-4) estimate the gray-scale value scope that staff is regional, confirm overall binary-state threshold, obtain binary image I with threshold value T
B
(3-5) to I
1Gray level image uses frame difference method, confirms human hand movement frame difference image I
F
(3-6) at I
BImage can normally be partitioned under the situation of staff, confirms staff centroid position coordinate, upgrades P and confirms scope S position again, and staff is followed the tracks of; At I
BImage can not normally be partitioned under the situation of staff, uses frame difference image I
F, confirm the staff center-of-mass coordinate, upgrade P and confirm scope S position again, staff is followed the tracks of.
The foregoing description is a preferred implementation of the present invention; But embodiment of the present invention is not limited by the examples; Other any do not deviate from change, the modification done under spirit of the present invention and the principle, substitutes, combination, simplify; All should be the substitute mode of equivalence, be included within protection scope of the present invention.
Claims (6)
1. gesture identification system based on infrared image; Comprise that infrared illumination module, front end image processing module and digital picture gesture cut apart and tracking module; It is characterized in that said front end image processing module comprises interconnective infrared video collecting unit, FPGA control and output unit
Said infrared video collecting unit comprises the CMOS optical sensing chip and the lens assembly of adjustable reference voltage, and said CMOS optical sensing chip is integrated with dsp chip; Said lens assembly is installed in the place ahead of CMOS optical sensing chip;
Said FPGA control and output unit comprise image quality measure module, reference voltage adjustment module and the output module that connects successively; Said image quality measure module is used for judging whether hand region presents identical or close pixel value in digital picture with the hand peripheral region; If then control reference voltage VREF1 and VREF2 that the reference voltage adjustment module is regulated A/D converter in the CMOS optical sensing chip; If not, then through the direct output digital image of output unit.
2. the gesture identification system based on infrared image according to claim 1; It is characterized in that; Said infrared illumination module is made up of 4 infrared LED fluorescent tubes; Said 4 infrared LED fluorescent tubes are evenly distributed on around the camera lens of lens assembly, are less than or equal to 3cm with the distance of optical center, and angle is 90 ° between the line of each LED fluorescent tube and optical center.
3. the gesture identification system based on infrared image according to claim 2 is characterized in that the diameter parameters of said LED fluorescent tube is 8mm, and emission angle is greater than 45 °.
4. the gesture identification system based on infrared image according to claim 2 is characterized in that the place ahead of said camera lens is equipped with filter plate, and the transmission region of said filter plate is corresponding with the luminous wave band of infrared LED fluorescent tube.
5. like the gesture identification method of each described gesture identification system based on infrared image of claim 1～4, it is characterized in that, may further comprise the steps:
(1) infrared illumination module illuminates the gesture operation zone;
(2) the infrared video collecting unit is gathered infrared image, specifically may further comprise the steps:
(2-1) CMOS optical sensing chip obtains the aanalogvoltage V of pixel
0
(2-2) according to the reference voltage VREF1 and the VREF2 of CMOS optical sensing chip, handle each pixel aanalogvoltage V of digital picture that CMOS optical sensing chip is obtained through A/D converter and dsp chip
0Quantize, the voltage of each two field picture pixel is turned to 8bit data: VREF1≤V
0≤VREF2 obtains digital picture;
(2-3) can the image quality measure module be judged and gesture be identified: whether hand region presents identical or close pixel value with the hand peripheral region in digital picture; If; Then control the reference voltage adjustment module and regulate the reference voltage VREF1 and the VREF2 of A/D converter, repeating step (2-2)～(2-3); If not, then through the direct output digital image of output unit;
(3) digital picture being carried out gesture cuts apart and follows the tracks of.
6. the gesture identification method of the gesture identification system based on infrared image according to claim 5 is characterized in that, step (3) is said carries out gesture to digital picture and cut apart and follow the tracks of, and specifically may further comprise the steps:
The infrared image I that (3-1) the infrared video collecting unit is collected
0, extract among its RGB arbitrary chromatograph or its gray processing obtained image I
1
(3-2) use the good sorter of training in advance to I
1Image is handled, and finds in the image staff zone, and definite staff the position P and the scope S that in image, occur;
(3-3) according to DID in the scope S, the highest gray-scale value of probability of occurrence in the statistical regions, with this gray-scale value as threshold value T;
(3-4) estimate the gray-scale value scope that staff is regional, confirm overall binary-state threshold, obtain binary image I with threshold value T
B
(3-5) to I
1Gray level image uses frame difference method, confirms human hand movement frame difference image I
F
(3-6) at I
BImage can normally be partitioned under the situation of staff, confirms staff centroid position coordinate, upgrades P and confirms scope S position again, and staff is followed the tracks of; At I
BImage can not normally be partitioned under the situation of staff, uses frame difference image I
F, confirm the staff center-of-mass coordinate, upgrade P and confirm scope S position again, staff is followed the tracks of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100368461A CN102629314A (en) | 2012-02-17 | 2012-02-17 | Gesture recognition system based on infrared image and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100368461A CN102629314A (en) | 2012-02-17 | 2012-02-17 | Gesture recognition system based on infrared image and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102629314A true CN102629314A (en) | 2012-08-08 |
Family
ID=46587572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100368461A Pending CN102629314A (en) | 2012-02-17 | 2012-02-17 | Gesture recognition system based on infrared image and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102629314A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104363494A (en) * | 2013-12-21 | 2015-02-18 | 滁州惠智科技服务有限公司 | Gesture recognition system for smart television |
| CN105426817A (en) * | 2015-10-30 | 2016-03-23 | 上海集成电路研发中心有限公司 | Gesture position recognition device and recognition method based on infrared imaging |
| CN109086747A (en) * | 2013-03-13 | 2018-12-25 | 英特尔公司 | It is pre-processed using the posture of the video flowing of Face Detection |
| CN109710071A (en) * | 2018-12-26 | 2019-05-03 | 青岛小鸟看看科技有限公司 | A kind of screen control method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1218917A (en) * | 1997-11-29 | 1999-06-09 | 三星电子株式会社 | Image processing device and method |
| US6075895A (en) * | 1997-06-20 | 2000-06-13 | Holoplex | Methods and apparatus for gesture recognition based on templates |
| CN101800853A (en) * | 2009-02-06 | 2010-08-11 | （株）赛丽康 | Image sensor capable of judging proximity of a subject |
| CN102043945A (en) * | 2010-11-23 | 2011-05-04 | 聊城大学 | License plate character recognition method based on real-time vehicle tracking and binary index classification |
| US20110162004A1 (en) * | 2009-12-30 | 2011-06-30 | Cevat Yerli | Sensor device for a computer-controlled video entertainment system |
| CN102324019A (en) * | 2011-08-12 | 2012-01-18 | 浙江大学 | Method and system for automatically extracting gesture candidate region in video sequence |
-
2012
- 2012-02-17 CN CN2012100368461A patent/CN102629314A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6075895A (en) * | 1997-06-20 | 2000-06-13 | Holoplex | Methods and apparatus for gesture recognition based on templates |
| CN1218917A (en) * | 1997-11-29 | 1999-06-09 | 三星电子株式会社 | Image processing device and method |
| CN101800853A (en) * | 2009-02-06 | 2010-08-11 | （株）赛丽康 | Image sensor capable of judging proximity of a subject |
| US20110162004A1 (en) * | 2009-12-30 | 2011-06-30 | Cevat Yerli | Sensor device for a computer-controlled video entertainment system |
| CN102043945A (en) * | 2010-11-23 | 2011-05-04 | 聊城大学 | License plate character recognition method based on real-time vehicle tracking and binary index classification |
| CN102324019A (en) * | 2011-08-12 | 2012-01-18 | 浙江大学 | Method and system for automatically extracting gesture candidate region in video sequence |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086747A (en) * | 2013-03-13 | 2018-12-25 | 英特尔公司 | It is pre-processed using the posture of the video flowing of Face Detection |
| CN104363494A (en) * | 2013-12-21 | 2015-02-18 | 滁州惠智科技服务有限公司 | Gesture recognition system for smart television |
| CN105426817A (en) * | 2015-10-30 | 2016-03-23 | 上海集成电路研发中心有限公司 | Gesture position recognition device and recognition method based on infrared imaging |
| CN105426817B (en) * | 2015-10-30 | 2019-08-20 | 上海集成电路研发中心有限公司 | Hand gesture location identification device and recognition methods based on infrared imaging |
| CN109710071A (en) * | 2018-12-26 | 2019-05-03 | 青岛小鸟看看科技有限公司 | A kind of screen control method and device |
| CN109710071B (en) * | 2018-12-26 | 2022-05-17 | 青岛小鸟看看科技有限公司 | Screen control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102629314A (en) | Gesture recognition system based on infrared image and method thereof | |
| CN104133548A (en) | Method and device for determining viewpoint area and controlling screen luminance | |
| CN108600649B (en) | Intelligent household illumination brightness acquisition and control method | |
| CN102769757A (en) | Active light source-based image acquisition method and system | |
| CN102789635A (en) | Image enhancement method and image enhancement device | |
| CN104092987B (en) | A kind of bimodulus bi-feedback adaptive Target Tracking System, control circuit and method | |
| CN110913102A (en) | Image processing device for alum blossom acquisition and recognition | |
| CN109086823B (en) | Automatic statistical method for wheat scab ear disease rate | |
| Ribeiro et al. | Face detection on infrared thermal image | |
| CN103839245B (en) | The Retinex colour-image reinforcing method at night of Corpus--based Method rule | |
| CN113449730A (en) | Image processing method, system, automatic walking device and readable storage medium | |
| WO2022206156A1 (en) | Image generation method and apparatus, device and storage medium | |
| WO2020130799A1 (en) | A system and method for licence plate detection | |
| CN102622594A (en) | Short-distance objective extraction method based on infrared rays and frame difference | |
| CN102788806A (en) | Fruit peel defect detection method based on spheroidic brightness transformation | |
| KR102171384B1 (en) | Object recognition system and method using image correction filter | |
| CN107833223B (en) | Fruit hyperspectral image segmentation method based on spectral information | |
| CN111881924B (en) | Dark-light vehicle illumination identification method combining illumination invariance and short-exposure illumination enhancement | |
| CN100484203C (en) | Same vision field multi-spectral video stream acquiring device and method | |
| CN110533027B (en) | Text detection and identification method and system based on mobile equipment | |
| CN105678744B (en) | The autonomous imaging self-adaptive MCP gain adjusting method therefores of range gating | |
| JP2016122905A (en) | Image processing apparatus, image processing method, and program | |
| CN117058182A (en) | Target detection frame optimization method for visual ranging | |
| CN201440274U (en) | Target detection equipment and image acquisition device used by same | |
| CN110889321A (en) | Intelligent face anti-overexposure algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120808 |