CN104463170A - Unlicensed vehicle detecting method based on multiple detection under gate system - Google Patents
Unlicensed vehicle detecting method based on multiple detection under gate system Download PDFInfo
- Publication number
- CN104463170A CN104463170A CN201410735620.XA CN201410735620A CN104463170A CN 104463170 A CN104463170 A CN 104463170A CN 201410735620 A CN201410735620 A CN 201410735620A CN 104463170 A CN104463170 A CN 104463170A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- symmetry
- pixel
- region
- gray level
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides an unlicensed vehicle detecting method based on multiple detection under a gate system. The method comprises the steps that images which are not positioned successfully are acquired from a database of the gate system, and the light and dark conditions of the images are analyzed to judge whether it is in daytime or nighttime; for the daytime images, vehicle coarse detection is conducted on the images by a histogram treatment method, the areas where vehicles possibly exist are obtained, the vehicles are subjected to fine detection by a multiple symmetry method, edge information is analyzed, non-vehicle areas are eliminated, and the vehicle areas are determined; for the nighttime images, vehicle lamps are detected first, namely binaryzation operation is conducted, obtained spots are analyzed, and the positions of the vehicle lamps are positioned; if the vehicle lamps can not be detected, the nighttime images enter in the daytime processing link. According to the unlicensed vehicle detecting method, the problems that background interference can be likely to be caused due to contour symmetry and the detection is sensitive to shooting angles are solved to a certain degree, the calculated amount is small, the rear-time performance is good, the vehicle detection rate is high, and common application requirements can be met.
Description
Technical field
The present invention relates to the unlicensed vehicle checking method based on Multiple detection under a kind of Gate System, belong to the applied technical field of image processing and analysis in intelligent monitoring.
Background technology
What current Gate System detected vehicle is generally by detecting license board information, system by camera to the vehicle photographic pressing through coil, car plate detection is carried out to it, if car plate cannot be detected, be considered to non-vehicle (as motorcycle, tricycle or pedestrian) without exception, but be difficult to the accuracy of detection of accomplishing 100% due to car plate detection technique, add the existence of unlicensed vehicle, wherein must contain some vehicle pictures, and rely on the scheme of License Plate cannot locate these vehicles, cause the imperfection of Gate System vehicle detecting system.The present invention is directed to this phenomenon, the unlicensed vehicle checking method of bayonet socket under research Multiple detection mechanism, the accuracy rate of vehicle detection under raising Gate System.
Summary of the invention
Technical matters to be solved by this invention is to provide the unlicensed vehicle checking method based on Multiple detection under a kind of Gate System, can detect the information of vehicles in the picture of License Plate failure, and consuming time less, can meet reality use in requirement to real-time.
For solving the problems of the technologies described above, the technical solution adopted in the present invention is: unlicensed vehicle checking method under a kind of Gate System, is characterized in that, comprises with lower part:
S01, daytime are detected: the method adopting number D, the intermediate luminance number of pixels M of the inclined dark pixel of statistics, partially bright pixel number L, judges day and night according to the quantitative relation between D, L, M;
S02, based on histogrammic vehicle rough detection: the threshold value T being found vehicle by a kind of method of statistics, if gray level image is f1 (x, y), obtain the image g (x of binaryzation, y), wherein (x, y) is xth row y row pixel in image;
S03, to detect based on the vehicle essence of multiple symmetry: adopt the method for multiple symmetry to carry out vehicle essence and detect, comprising a profile axis of symmetry x1, and at two axis of symmetry x2 and x3 that 8, this axle left and right sides location of pixels increases;
S04, edge treated: analyze marginal information, frame goes out vehicle location;
S05, detection car light: binaryzation is carried out to f1 picture, threshold value is set to 200, obtain speck region and mark, get rid of area and be greater than 260 and the area region that is less than 23, according to the symmetry of car light, find distance rationally, almost symmetric blob in the same horizontal line, judge that it is car light, if cannot find, enter the link of detection on daytime; Suppose that car light is positioned at lower vehicle 1/3 position in vertical direction, just can draw vehicle body position;
As a further improvement on the present invention, described step S01 is specially:
(1) input picture f carried out gray processing and reduce 0.25 times, obtaining gray level image f1;
(2) definition scope that is partially dark, middle, bright pixel partially, wherein partially dark pixel scope be account in 256 gray levels the first six/gray level of, intermediate pixel scope is account for its gray level of 4/2 to six/6ths in 256 gray levels, inclined bright pixel is the gray level of in 256 gray levels rear 1/6th, L, D, M value in statistics f1;
(3) judging situation in daytime according to the relation of L, D, M, if L/D>=27% or M/D>=26% is judged as daytime, otherwise is then evening.
As a further improvement on the present invention, described step S02 is specially:
(1) gray level histogram of gray level image f1 is added up;
(2) analyze vehicle and environment bright-dark degree relation, the gray level that wherein in f1, pixel is maximum represents with A, and next the gray level of sorting represents with B, relation computing formula: C=|A-B|/min (A, B) between them;
(3) compare the relation between A, B, C, find T, T
h, T
l(T
h, T
lbe respectively the high-low threshold value in dual threshold situation):
After obtaining threshold value, following binaryzation operation is carried out to f1:
1) when result is single threshold:
2) when result is dual threshold:
(4) analyze the speckle regions in g, get rid of area too small, rectangular region and sheet and occupy the speckle regions of very large width, obtain the region that may comprise vehicle, or subregion; G is normalized to 100*150 size, calculate the speck area finally obtained, if its area is greater than 2800, the result of histogram coarse positioning is the boundary rectangle frame region of its spot, if be less than 2800, then this phase orientation result is the region between the minimum row of spot and maximum column, if histogram treatment is without result, does not carry out coarse positioning;
As a further improvement on the present invention, described step S03 is specially:
(1) gray level image f1 is normalized to 100*150 pixel, normalized image f2 makes rim detection on the basis of step S02 coarse positioning, and (coarse positioning is set to 0 entirely with exterior domain, the rim detection scope of not carrying out coarse positioning is view picture figure), obtain outline map Y, and following operation is carried out on Y: carry out a line scanning every 6 pixels, carry out a column scan every 4 pixels, adopt the symmetry value of the symmetrical window calculation sweep trace point of crossing of 15*13 size;
(2) calculating symmetry value maximum point is P (x, y), if the symmetry value of P point is less than 18, direct judgement input picture f is non-car picture, otherwise carry out following operation: the vertical direction at P point place is the axis of symmetry x1 calculated, leave out the anisopleural point in left and right on Y along this axle, obtain the profile diagram X1 corresponding to axis of symmetry x1;
(3) leave out the anisopleural pixel in left and right on Y along x2 axis of symmetry, obtain the profile diagram X2 corresponding to axis of symmetry x2; Leave out the anisopleural pixel in left and right on Y along x3 axis of symmetry, obtain the profile diagram X3 corresponding to axis of symmetry x3;
(4) vehicle ' s contour figure X is obtained to X1, X2, X3 work and computing;
As a further improvement on the present invention, described step S04 is specially:
(1) in vehicle ' s contour figure X, the marginal information of vehicle is abundant and concentrated, mainly be divided into highly dense region (vehicle region) and interference region (non-car region), distance close quarters is crossed far away or institute and to be expert at total pixel number too rareness, judge that it is non-car region, and it is deleted;
(2) horizontal vertical projection operation is carried out to X, calculate the positional information of the external frame of profile;
(3) if external frame height is more than 90, external frame is in height divided into two, statistics each several part sum of all pixels, the judgement that pixel count is few is non-car region, deletes, and upgrades external frame positional information; If external frame depth-width ratio is greater than 1.3 when width is less than 30, directly judge that input picture f is non-car picture; If the position of symmetry value maximum point P outside external frame, and be greater than 22 to the vertical range of frame, judge that f is non-car picture;
(4) frame goes out the position of car in normalized image f2;
The invention has the beneficial effects as follows, can reduce the error that shooting angle is just do not caused, and calculated amount is little, real-time is good, have certain adaptability, and discrimination is higher to different light intensity, can meet and generally apply requirement.
Accompanying drawing explanation
Fig. 1 is the unlicensed detection flow for the automobile figure based on Multiple detection under Gate System provided by the present invention.
Embodiment
Below in conjunction with each embodiment shown in the drawings, the present invention is described in detail; but should be noted that; these embodiments are not limitation of the present invention; those of ordinary skill in the art are according to these embodiment institute work energy, method or structural equivalent transformations or substitute, and all belong within protection scope of the present invention.
The process calculating axis of symmetry for profile symmetry is vulnerable to symmetrical background influence, and it is responsive for symmetrical deflection, institute causes the problems such as location is inaccurate, accuracy rate is low, false drop rate is high, the present invention proposes the unlicensed vehicle checking method based on Multiple detection under a kind of Gate System, be described in detail below in conjunction with accompanying drawing:
As shown in Figure 1, under a kind of Gate System provided by the present invention based on the schematic flow sheet in the unlicensed vehicle checking method embodiment of Multiple detection.In the present embodiment, based on the unlicensed vehicle checking method of Multiple detection under a kind of Gate System, it comprises with lower part:
S01, daytime are detected: the method adopting number D, the intermediate luminance number of pixels M of the inclined dark pixel of statistics, partially bright pixel number L, judges day and night according to the quantitative relation between D, L, M;
Described step S01 is specially:
(1) input picture f carried out gray processing and reduce 0.25 times, obtaining gray level image f1;
(2) definition scope that is partially dark, middle, bright pixel partially, wherein partially dark pixel scope be account in 256 gray levels the first six/gray level of, intermediate pixel scope is account for its gray level of 4/2 to six/6ths in 256 gray levels, inclined bright pixel is the gray level of in 256 gray levels rear 1/6th, L, D, M value in statistics f1;
(3) judging situation in daytime according to the relation of L, D, M, if L/D>=27% or M/D>=26% is judged as daytime, otherwise is then evening.
S02, based on histogrammic vehicle rough detection: the threshold value T being found vehicle by a kind of method of statistics, if gray level image is f1 (x, y), obtain the image g (x of binaryzation, y), wherein (x, y) is xth row y row pixel in image;
Described step S02 is specially:
(1) gray level histogram of gray level image f1 is added up;
(2) analyze vehicle and environment bright-dark degree relation, the gray level that wherein in f1, pixel is maximum represents with A, and next the gray level of sorting represents with B, relation computing formula: C=|A-B|/min (A, B) between them;
(3) compare the relation between A, B, C, find T, T
h, T
l(T
h, T
lbe respectively the high-low threshold value in dual threshold situation):
After obtaining threshold value, following binaryzation operation is carried out to f1:
1) when result is single threshold:
2) when result is dual threshold:
(4) analyze the speckle regions in g, get rid of area too small, rectangular region and sheet and occupy the speckle regions of very large width, obtain the region that may comprise vehicle, or subregion; G is normalized to 100*150 size, calculate the speck area finally obtained, if its area is greater than 2800, the result of histogram coarse positioning is the boundary rectangle frame region of its spot, if be less than 2800, then this phase orientation result is the region between the minimum row of spot and maximum column, if histogram treatment is without result, does not carry out coarse positioning;
S03, to detect based on the vehicle essence of multiple symmetry: adopt the method for multiple symmetry to carry out vehicle essence and detect, comprising a profile axis of symmetry x1, and at two axis of symmetry x2 and x3 that 8, this axle left and right sides location of pixels increases;
Described step S03 is specially:
(1) gray level image f1 is normalized to 100*150 pixel, normalized image f2 makes rim detection on the basis of step S02 coarse positioning, and (coarse positioning is set to 0 entirely with exterior domain, the rim detection scope of not carrying out coarse positioning is view picture figure), obtain outline map Y, and following operation is carried out on Y: carry out a line scanning every 6 pixels, carry out a column scan every 4 pixels, adopt the symmetry value of the symmetrical window calculation sweep trace point of crossing of 15*13 size;
(2) calculating symmetry value maximum point is P (x, y), if the symmetry value of P point is less than 18, direct judgement input picture f is non-car picture, otherwise carry out following operation: the vertical direction at P point place is the axis of symmetry x1 calculated, leave out the anisopleural point in left and right on Y along this axle, obtain the profile diagram X1 corresponding to axis of symmetry x1;
(3) leave out the anisopleural pixel in left and right on Y along x2 axis of symmetry, obtain the profile diagram X2 corresponding to axis of symmetry x2; Leave out the anisopleural pixel in left and right on Y along x3 axis of symmetry, obtain the profile diagram X3 corresponding to axis of symmetry x3;
(4) vehicle ' s contour figure X is obtained to X1, X2, X3 work and computing;
S04, edge treated: analyze marginal information, frame goes out vehicle location;
Described step S04 is specially:
(1) in vehicle ' s contour figure X, the marginal information of vehicle is abundant and concentrated, mainly be divided into highly dense region (vehicle region) and interference region (non-car region), distance close quarters is crossed far away or institute and to be expert at total pixel number too rareness, judge that it is non-car region, and it is deleted;
(2) horizontal vertical projection operation is carried out to X, calculate the positional information of the external frame of profile;
(3) if external frame height is more than 90, external frame is in height divided into two, statistics each several part sum of all pixels, the judgement that pixel count is few is non-car region, deletes, and upgrades external frame positional information; If external frame depth-width ratio is greater than 1.3 when width is less than 30, directly judge that input picture f is non-car picture; If the position of symmetry value maximum point P outside external frame, and be greater than 22 to the vertical range of frame, judge that f is non-car picture;
(4) frame goes out the position of car in normalized image f2;
S05, detection car light: binaryzation is carried out to f1 picture, threshold value is set to 200, obtain speck region and mark, get rid of area and be greater than 260 and the area region that is less than 23, according to the symmetry of car light, find distance rationally, almost symmetric blob in the same horizontal line, judge that it is car light, if cannot find, enter the link of detection on daytime; Suppose that car light is positioned at lower vehicle 1/3 position in vertical direction, just can draw vehicle body position;
Below disclose the present invention with preferred embodiment, so it is not intended to limiting the invention, and all employings are equal to replacement or the technical scheme that obtains of equivalent transformation mode, all drop within protection scope of the present invention.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.
In addition, be to be understood that, although this instructions is described according to embodiment, but not each embodiment only comprises an independently technical scheme, this narrating mode of instructions is only for clarity sake, those skilled in the art should by instructions integrally, and the technical scheme in each embodiment also through appropriately combined, can form other embodiments that it will be appreciated by those skilled in the art that.
Claims (5)
1. under Gate System based on a unlicensed vehicle checking method for Multiple detection, be suitable for when Gate System cannot positioning licence plate time detect vehicle, it is characterized in that, comprise the following steps:
S01, daytime are detected: the method adopting number D, the intermediate luminance number of pixels M of the inclined dark pixel of statistics, partially bright pixel number L, judges day and night according to the quantitative relation between D, L, M;
S02, based on histogrammic vehicle rough detection: the threshold value T being found vehicle by a kind of method of statistics, if gray level image is f1 (x, y), obtain the image g (x of binaryzation, y), wherein (x, y) is xth row y row pixel in image;
S03, to detect based on the vehicle essence of multiple symmetry: adopt the method for multiple symmetry to carry out vehicle essence and detect, comprising a profile axis of symmetry x1, and at two axis of symmetry x2 and x3 that 8, this axle left and right sides location of pixels increases;
S04, edge treated: analyze marginal information, frame goes out vehicle location;
S05, detection car light: binaryzation is carried out to f1 picture, threshold value is set to 200, obtain speck region and mark, get rid of area and be greater than 260 and the area region that is less than 23, according to the symmetry of car light, find distance rationally, almost symmetric blob in the same horizontal line, judge that it is car light, if cannot find, enter the link of detection on daytime; Suppose that car light is positioned at lower vehicle 1/3 position in vertical direction, just can draw vehicle body position.
2. the unlicensed vehicle checking method based on Multiple detection according to claim 1, described step S01 is specially:
(1) input picture f carried out gray processing and reduce 0.25 times, obtaining gray level image f1;
(2) definition scope that is partially dark, middle, bright pixel partially, wherein partially dark pixel scope be account in 256 gray levels the first six/gray level of, intermediate pixel scope is account for its gray level of 4/2 to six/6ths in 256 gray levels, inclined bright pixel is the gray level of in 256 gray levels rear 1/6th, L, D, M value in statistics f1;
(3) judging situation in daytime according to the relation of L, D, M, if L/D>=27% or M/D>=26% is judged as daytime, otherwise is then evening.
3. the unlicensed vehicle checking method based on Multiple detection according to claim 1, described step S02 is specially:
(1) gray level histogram of gray level image f1 is added up;
(2) analyze vehicle and environment bright-dark degree relation, the gray level that wherein in f1, pixel is maximum represents with A, and next the gray level of sorting represents with B, relation computing formula: C=|A-B|/min (A, B) between them;
(3) compare the relation between A, B, C, find T, T
h, T
l(T
h, T
lbe respectively the high-low threshold value in dual threshold situation):
After obtaining threshold value, following binaryzation operation is carried out to f1:
1) when result is single threshold:
2) when result is dual threshold:
(4) analyze the speckle regions in g, get rid of area too small, rectangular region and sheet and occupy the speckle regions of very large width, obtain the region that may comprise vehicle, or subregion; G is normalized to 100*150 size, calculate the speck area finally obtained, if its area is greater than 2800, the result of histogram coarse positioning is the boundary rectangle frame region of its spot, if be less than 2800, then this phase orientation result is the region between the minimum row of spot and maximum column, if histogram treatment is without result, does not carry out coarse positioning.
4. the unlicensed vehicle checking method based on Multiple detection according to claim 1, described step S03 is specially:
(1) gray level image f1 is normalized to 100*150 pixel, normalized image f2 makes rim detection on the basis of step S02 coarse positioning, and (coarse positioning is set to 0 entirely with exterior domain, the rim detection scope of not carrying out coarse positioning is view picture figure), obtain outline map Y, and following operation is carried out on Y: carry out a line scanning every 6 pixels, carry out a column scan every 4 pixels, adopt the symmetry value of the symmetrical window calculation sweep trace point of crossing of 15*13 size;
(2) calculating symmetry value maximum point is P (x, y), if the symmetry value of P point is less than 18, direct judgement input picture f is non-car picture, otherwise carry out following operation: the vertical direction at P point place is the axis of symmetry x1 calculated, leave out the anisopleural point in left and right on Y along this axle, obtain the profile diagram X1 corresponding to axis of symmetry x1;
(3) leave out the anisopleural pixel in left and right on Y along x2 axis of symmetry, obtain the profile diagram X2 corresponding to axis of symmetry x2; Leave out the anisopleural pixel in left and right on Y along x3 axis of symmetry, obtain the profile diagram X3 corresponding to axis of symmetry x3;
(4) vehicle ' s contour figure X is obtained to X1, X2, X3 work and computing.
5. the unlicensed vehicle checking method based on Multiple detection according to claim 1, described step S04 is specially:
(1) in vehicle ' s contour figure X, the marginal information of vehicle is abundant and concentrated, mainly be divided into highly dense region (vehicle region) and interference region (non-car region), distance close quarters is crossed far away or institute and to be expert at total pixel number too rareness, judge that it is non-car region, and it is deleted;
(2) horizontal vertical projection operation is carried out to X, calculate the positional information of the external frame of profile;
(3) if external frame height is more than 90, external frame is in height divided into two, statistics each several part sum of all pixels, the judgement that pixel count is few is non-car region, deletes, and upgrades external frame positional information; If external frame depth-width ratio is greater than 1.3 when width is less than 30, directly judge that input picture f is non-car picture; If the position of symmetry value maximum point P outside external frame, and be greater than 22 to the vertical range of frame, judge that f is non-car picture;
(4) frame goes out the position of car in normalized image f2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410735620.XA CN104463170A (en) | 2014-12-04 | 2014-12-04 | Unlicensed vehicle detecting method based on multiple detection under gate system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410735620.XA CN104463170A (en) | 2014-12-04 | 2014-12-04 | Unlicensed vehicle detecting method based on multiple detection under gate system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104463170A true CN104463170A (en) | 2015-03-25 |
Family
ID=52909184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410735620.XA Pending CN104463170A (en) | 2014-12-04 | 2014-12-04 | Unlicensed vehicle detecting method based on multiple detection under gate system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104463170A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512662A (en) * | 2015-06-12 | 2016-04-20 | 北京卓视智通科技有限责任公司 | Detection method and apparatus for unlicensed vehicle |
| CN108388871A (en) * | 2018-02-28 | 2018-08-10 | 中国计量大学 | A kind of vehicle checking method returned based on vehicle body |
| CN110686649A (en) * | 2019-09-20 | 2020-01-14 | 天津普达软件技术有限公司 | Method for detecting stock change of hazardous waste based on machine vision |
| CN112164086A (en) * | 2020-10-12 | 2021-01-01 | 华雁智能科技(集团)股份有限公司 | Refined image edge information determining method and system and electronic equipment |
| CN112526534A (en) * | 2020-11-03 | 2021-03-19 | 上海炬佑智能科技有限公司 | ToF sensing device and distance detection method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509098A (en) * | 2011-10-08 | 2012-06-20 | 天津大学 | Fisheye image vehicle identification method |
| CN103927549A (en) * | 2014-04-14 | 2014-07-16 | 江南大学 | Vehicle detecting distinguishing method based on spot and histogram analysis |
-
2014
- 2014-12-04 CN CN201410735620.XA patent/CN104463170A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509098A (en) * | 2011-10-08 | 2012-06-20 | 天津大学 | Fisheye image vehicle identification method |
| CN103927549A (en) * | 2014-04-14 | 2014-07-16 | 江南大学 | Vehicle detecting distinguishing method based on spot and histogram analysis |
Non-Patent Citations (4)
| Title |
|---|
| A.BENSRHAIR等: "A Cooperative Approach to Vision-based Vehicle Detection", 《2001 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE PROCEEDINGS》 * |
| THOMAS SCHAMM等: "On-Road Vehicle Detection during Dusk and at Night", 《2010 IEEE INTELLIGENT VEHICLES SYMPOSIUM》 * |
| 化春键等: "高精度尺度不变特征点匹配方法及其应用", 《中国机械工程》 * |
| 皮燕妮等: "智能车视觉导航的道路和前车检测系统", 《计算机工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512662A (en) * | 2015-06-12 | 2016-04-20 | 北京卓视智通科技有限责任公司 | Detection method and apparatus for unlicensed vehicle |
| CN108388871A (en) * | 2018-02-28 | 2018-08-10 | 中国计量大学 | A kind of vehicle checking method returned based on vehicle body |
| CN108388871B (en) * | 2018-02-28 | 2021-05-18 | 中国计量大学 | Vehicle detection method based on vehicle body regression |
| CN110686649A (en) * | 2019-09-20 | 2020-01-14 | 天津普达软件技术有限公司 | Method for detecting stock change of hazardous waste based on machine vision |
| CN112164086A (en) * | 2020-10-12 | 2021-01-01 | 华雁智能科技(集团)股份有限公司 | Refined image edge information determining method and system and electronic equipment |
| CN112526534A (en) * | 2020-11-03 | 2021-03-19 | 上海炬佑智能科技有限公司 | ToF sensing device and distance detection method thereof |
| CN112526534B (en) * | 2020-11-03 | 2024-03-08 | 上海炬佑智能科技有限公司 | ToF sensing device and distance detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI409718B (en) | Method of locating license plate of moving vehicle | |
| O'Malley et al. | Vehicle detection at night based on tail-light detection | |
| US8903603B2 (en) | Environment recognizing device for a vehicle and vehicle control system using the same | |
| US9288381B2 (en) | In-vehicle image recognizer | |
| US7566851B2 (en) | Headlight, taillight and streetlight detection | |
| CN108197523B (en) | Night vehicle detection method and system based on image conversion and contour neighborhood difference | |
| CN104463170A (en) | Unlicensed vehicle detecting method based on multiple detection under gate system | |
| JP6723328B2 (en) | Vehicle detection method, night-time vehicle detection method and system based on dynamic light intensity | |
| US10318824B2 (en) | Algorithm to extend detecting range for AVM stop line detection | |
| JP2007234019A (en) | Vehicle image area specifying device and method for it | |
| US20150054955A1 (en) | Image processing method of vehicle camera and image processing apparatus using the same | |
| CN106650730A (en) | Turn signal lamp detection method and system in car lane change process | |
| CN103530640A (en) | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) | |
| Lin et al. | Adaptive IPM-based lane filtering for night forward vehicle detection | |
| CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method | |
| CN108229447B (en) | High beam light detection method based on video stream | |
| CN102610104A (en) | Onboard front vehicle detection method | |
| CN102169583B (en) | Vehicle shielding detection and segmentation method based on vehicle window positioning | |
| CN104992160A (en) | Night preceding vehicle detection method for heavy-duty truck | |
| CN108389177A (en) | A kind of vehicle bumper damage testing method and traffic security early warning method of traffic control | |
| JP7261006B2 (en) | External environment recognition device | |
| US20140301597A1 (en) | Windshield localization for occupancy detection | |
| JP7264428B2 (en) | Road sign recognition device and its program | |
| KR101875786B1 (en) | Method for identifying vehicle using back light region in road image | |
| CN103049742A (en) | License plate positioning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150325 |
|
| WD01 | Invention patent application deemed withdrawn after publication |