CN101770571B - Method and device for detecting vehicle at night - Google Patents
Method and device for detecting vehicle at night Download PDFInfo
- Publication number
- CN101770571B CN101770571B CN2009102441065A CN200910244106A CN101770571B CN 101770571 B CN101770571 B CN 101770571B CN 2009102441065 A CN2009102441065 A CN 2009102441065A CN 200910244106 A CN200910244106 A CN 200910244106A CN 101770571 B CN101770571 B CN 101770571B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- interest
- area
- virtual coil
- night
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/174—Segmentation; Edge detection involving the use of two or more images
-
- 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
-
- 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
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
-
- 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
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30261—Obstacle
Abstract
The invention discloses a method and a device for detecting a vehicle at night, which relate to the field of intelligent traffic systems and aim to solve the problem that the influence of illumination and halo of vehicle lamps causes the reduction of accuracy in detecting the vehicle at night. The technical scheme provided by the invention comprises: acquiring adjacent video frames; extracting an interested area according to a difference between two adjacent video frames; and detecting the vehicle at night according to the interested area. The technical scheme provided by the embodiment of the invention is suitable for the intelligent traffic systems.
Description
Technical field
The present invention relates to the intelligent transportation system field, relate in particular to the method and apparatus that a kind of vehicle at night detects.
Background technology
Vehicle detection is the important component part of intelligent transportation system.The low variation with light intensity of illumination at night is greatly the biggest problem of vehicle being carried out round-the-clock detection.
In the prior art, mostly adopt the background subtraction method to extract area-of-interest, according to the area-of-interest that extracts vehicle is detected.Described background subtraction method is to obtain sport foreground by the difference between current frame image and the background frames image, and the extraction of background and real-time renewal are the committed steps of described background subtraction method.
In realizing process of the present invention, the inventor finds, because night, intensity variation was large, especially the impact of car light photograph and halation, so that the renewal difficult of background, the area-of-interest that causes the background subtraction method to be extracted comprises the bulk redundancy light information, has reduced the accuracy of the detection of vehicle at night.
Summary of the invention
The method and apparatus that embodiments of the invention provide a kind of vehicle at night to detect has solved because the problem that car light shines and the accuracy that causes vehicle at night to detect of the impact of halation reduces.
For achieving the above object, embodiments of the invention adopt following technical scheme:
The method that a kind of vehicle at night detects comprises: obtain adjacent frame of video; Extract area-of-interest according to the difference between the two adjacent frame of video; According to described area-of-interest vehicle at night is detected.
The device that a kind of vehicle at night detects comprises:
Acquiring unit is used for obtaining adjacent frame of video;
Extraction unit, the difference between the two adjacent frame of video that are used for obtaining according to described acquiring unit is extracted area-of-interest;
The first detecting unit is used for according to the area-of-interest that described extraction unit extracts vehicle at night being detected.
The method and apparatus that the vehicle at night that the embodiment of the invention provides detects, utilize the difference between the two adjacent frame of video, so that the target of motion is retained in error image, thereby obtain area-of-interest, described area-of-interest has gradient effect to a certain degree, thereby so that changing slowly shade and halation, part cut when two adjacent video difference values are processed carrying out, thereby reach the effect of eliminating part shade and halation impact, solved in the prior art because the problem that the impact of shade and halation causes the vehicle at night detection accuracy to reduce.
Description of drawings
The method flow diagram that the vehicle at night that Fig. 1 provides for the embodiment of the invention detects;
The method flow diagram that the vehicle at night that Fig. 2 provides for further embodiment of this invention detects;
The process flow diagram of step 205 in the method flow diagram that the vehicle at night that Fig. 3 provides for inventive embodiments shown in Figure 2 detects;
The structural representation one of the device that the vehicle at night that Fig. 4 provides for the embodiment of the invention detects;
The structural representation of the first detecting unit in the device that the vehicle at night that Fig. 5 provides for inventive embodiments shown in Figure 4 detects;
The structural representation two of the device that the vehicle at night that Fig. 6 provides for the embodiment of the invention detects;
The structural representation of judging unit in the device that the vehicle at night that Fig. 7 provides for inventive embodiments shown in Figure 6 detects.
Embodiment
In order to solve because the problem that the vehicle at night detection accuracy that shade and halation cause reduces, the method and apparatus that the embodiment of the invention provides a kind of vehicle at night to detect.
As shown in Figure 1, the method that the vehicle at night that the embodiment of the invention provides detects comprises:
The method that the vehicle at night that the embodiment of the invention provides detects, utilize the difference between the two adjacent frame of video, so that the target of motion is retained in error image, thereby obtain area-of-interest, described area-of-interest has gradient effect to a certain degree, thereby so that changing slowly shade and halation, part cut when two adjacent video difference values are processed carrying out, thereby reach the effect of eliminating part shade and halation impact, solved in the prior art because the problem that the impact of shade and halation causes the vehicle at night detection accuracy to reduce.
In order to make those skilled in the art can more clearly understand the technical scheme that the embodiment of the invention provides, below by specific embodiment, the method that the vehicle at night that the embodiment of the invention is provided detects is elaborated.
As shown in Figure 2, the method that the vehicle at night that further embodiment of this invention provides detects comprises:
In the present embodiment, the difference between the described two adjacent videos is by Δ f=f
2(x, y)-f
1(x, y) obtains, in the formula, and f
1(x, y) is t
1Frame of video constantly, f
2(x, y) is t
2Frame of video constantly.Realize by frame difference method when being the difference between the described two adjacent videos.Frame difference method is that front and back two two field pictures are subtracted each other, and the target of motion is retained to become area-of-interest in error image.
What deserves to be explained is, under the night scene, high capacity waggon increase so that the road surface produce easily resonance cause flashing suddenly all of DE Camera Shake and car light can bring a large amount of noises, car light part or high reflector segment and other regional luminances are widely different simultaneously, cause the light distribution of sport foreground extremely inhomogeneous, obvious fault-layer-phenomenon can appear in the area-of-interest of corresponding extraction, and random noise and fault-layer-phenomenon all can bring the error detection to vehicle at night.In order to prevent the generation of random noise and fault-layer-phenomenon, before described step 203, also comprise:
In the present embodiment, on the basis of analyzing described random noise and described fault-layer-phenomenon generation reason, 2 hypothesis are proposed, suppose one, miss owing to tomography between a plurality of area-of-interests of cutting apart between air line distance to be less than air line distance between the two cars, show as on the time domain, a plurality of area-of-interests that tomography mistake is cut apart the successively frame period number by default virtual coil are less than frame period number between two cars.Set the minimum frame period number between two cars.Suppose two, the occupation number of the frame when the frame occupation number of the area-of-interest that forms owing to random noise will be less than actual vehicle through virtual coil is set the minimum occupation number of vehicle.On the basis of above-mentioned two hypothesis, described step 205 as shown in Figure 3, comprising:
Step 2051 judges that whether frame period between the area-of-interest of the area-of-interest enter first described virtual coil and last vehicle that enters virtual coil is less than minimum frame period number between two cars of presetting;
Step 2052, if the frame period between the area-of-interest of the described area-of-interest that enters first described virtual coil and last vehicle that enters virtual coil is not less than minimum frame period number between the two default cars, judge described area-of-interest through the shared frame number of described virtual coil whether less than default frame number;
What deserves to be explained is, when minimum frame period is counted between the frame period between the area-of-interest of the described area-of-interest that enters first described virtual coil and last vehicle that enters virtual coil is less than two default cars, illustrate that this area-of-interest is to be cut apart by the mistake that fault-layer-phenomenon causes.
Step 2053 when described frame number during greater than default frame number, is exported in the described virtual coil result through vehicle, otherwise is exported the result who does not pass through vehicle in the described virtual coil.
What deserves to be explained is, when described frame number is less than or equal to default frame number, illustrate that this area-of-interest is because the mistake that random noise causes is cut apart.
Further, for the vehicle of judging vehicle convenient and simple when carrying out vehicle detection, describedly according to described area-of-interest vehicle at night is detected, comprising:
Obtain the vehicle of vehicle at night according to the distribution dispersion of described area-of-interest in described default virtual coil.
In the present embodiment, the virtual coil in current track is divided into left, center, right three parts, the distribution situation of statistics sport foreground information point during through this virtual coil is also analyzed the dispersion of this distribution situation.Described dispersion is weighed by standard deviation.The dispersion degree that the different automobile types information point distributes is different, and large car almost takes whole track, and it is basic identical to distribute in the Three regions of dividing in advance accordingly, and dispersion is low; And compact car mainly occupies 2/3 zone in track, and the distribution dispersion is high.Height by described distribution dispersion is judged the vehicle of vehicle.
The method that the vehicle at night that the embodiment of the invention provides detects, utilize the difference between the two adjacent frame of video, so that the target of motion is retained in error image, thereby obtain area-of-interest, described area-of-interest has gradient effect to a certain degree, thereby so that changing slowly shade and halation, part cut when two adjacent video difference values are processed carrying out, thereby reach the effect of eliminating part shade and halation impact, solved in the prior art because the problem that the impact of shade and halation causes the vehicle at night detection accuracy to reduce.
As shown in Figure 4, the vehicle at night pick-up unit that the embodiment of the invention provides comprises:
The first detecting unit 303 is used for according to the area-of-interest that described extraction unit extracts vehicle at night being detected.In the present embodiment, described the first detecting unit as shown in Figure 5, comprises that vehicle obtains subelement 3031, is used for the vehicle that the area-of-interest that extracts according to the described extraction unit distribution dispersion in described default virtual coil obtains vehicle at night.Concrete implementation method can be described referring to step 203 as shown in Figure 2, repeats no more herein.
For the error detection that prevents that fault-layer-phenomenon and random noise from bringing, as shown in Figure 6, described device also comprises:
The second detecting unit 304, the area-of-interest that extracts for detection of reaching extraction unit accounts for the ratio of default virtual coil, and described virtual coil is the quadrilateral in the video image respective regions; Concrete implementation method can be described referring to step 204 as shown in Figure 2, repeats no more herein.
In the present embodiment, described judging unit as shown in Figure 7, comprising:
The first judgment sub-unit 3051 be used for to judge that whether frame period between the area-of-interest of the area-of-interest that enters first described virtual coil and last vehicle that enters virtual coil is less than minimum frame period number between two cars of presetting; Concrete implementation method can be described referring to step 2051 as shown in Figure 2, repeats no more herein.
The second judgment sub-unit 3052, be used for when described the first judgment sub-unit judges that frame period between the area-of-interest of the area-of-interest that entered first described virtual coil and last vehicle that enters virtual coil is not less than that minimum frame period is counted between the two default cars, judge described area-of-interest through the shared frame number of described virtual coil whether less than the frame number of presetting; Concrete implementation method can be described referring to step 2052 as shown in Figure 2, repeats no more herein.
Allow unit 306, be used in described judgment unit judges obtains described virtual coil by have vehicle by change into without vehicle by the time, allow described the first detecting unit is detected vehicle at night.Concrete implementation method can be described referring to step 206 as shown in Figure 2, repeats no more herein.
The device that the vehicle at night that the embodiment of the invention provides detects, utilize the difference between the two adjacent frame of video, so that the target of motion is retained in error image, thereby obtain area-of-interest, described area-of-interest has gradient effect to a certain degree, thereby so that changing slowly shade and halation, part cut when two adjacent video difference values are processed carrying out, thereby reach the effect of eliminating part shade and halation impact, solved in the prior art because the problem that the impact of shade and halation causes the vehicle at night detection accuracy to reduce
The method and apparatus that the vehicle at night that the embodiment of the invention provides detects is applicable to intelligent transportation system.
One of ordinary skill in the art will appreciate that all or part of step that realizes in above-described embodiment method is to come the relevant hardware of instruction to finish by program, described program can be stored in the computer-readable recording medium, such as ROM/RAM, magnetic disc or CD etc.
The above; be the specific embodiment of the present invention only, but protection scope of the present invention is not limited to this, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (7)
1. the method that vehicle at night detects is characterized in that, comprising:
Obtain adjacent frame of video;
Extract area-of-interest according to the difference between the two adjacent frame of video;
According to described area-of-interest vehicle at night is detected;
Wherein, describedly according to described area-of-interest vehicle at night is detected, comprising:
Obtain the vehicle of vehicle at night according to the distribution dispersion of described area-of-interest in default virtual coil.
2. method according to claim 1 is characterized in that, described according to described area-of-interest vehicle at night is detected before, also comprise:
Detect the ratio that described area-of-interest accounts for default virtual coil, described virtual coil is the quadrilateral in the video image respective regions;
Judge whether have vehicle to pass through in the described virtual coil according to described ratio;
When in the described virtual coil by have vehicle by change into without vehicle by the time, allow vehicle at night is detected.
3. method according to claim 2 is characterized in that, describedly judges whether have vehicle to pass through in the described virtual coil, to comprise according to described ratio:
Judge that whether frame period between the area-of-interest of the area-of-interest enter first described virtual coil and last vehicle that enters virtual coil is less than minimum frame period number between two cars of presetting;
If the frame period between the area-of-interest of the described area-of-interest that enters first described virtual coil and last vehicle that enters virtual coil is not less than minimum frame period number between the two default cars, judge described area-of-interest through the shared frame number of described virtual coil whether less than default frame number;
When described frame number during greater than default frame number, export in the described virtual coil result through vehicle, otherwise export the result who does not pass through vehicle in the described virtual coil.
4. method according to claim 1 is characterized in that, described dispersion is weighed by standard deviation.
5. the device that vehicle at night detects is characterized in that, comprising:
Acquiring unit is used for obtaining adjacent frame of video;
Extraction unit, the difference between the two adjacent frame of video that are used for obtaining according to described acquiring unit is extracted area-of-interest;
The first detecting unit is used for according to the area-of-interest that described extraction unit extracts vehicle at night being detected;
Wherein, described the first detecting unit comprises:
Vehicle is obtained subelement, and the distribution dispersion of area-of-interest in default virtual coil that is used for extracting according to described extraction unit obtains the vehicle of vehicle at night.
6. device according to claim 5 is characterized in that, also comprises:
The second detecting unit, the area-of-interest that extracts for detection of described extraction unit accounts for the ratio of default virtual coil, and described virtual coil is the quadrilateral in the video image respective regions;
Judging unit is used for judging whether have vehicle to pass through in the described virtual coil according to the ratio that described detecting unit obtains;
Allow the unit, be used in described judgment unit judges obtains described virtual coil by have vehicle by change into without vehicle by the time, allow described the first detecting unit is detected vehicle at night.
7. device according to claim 6 is characterized in that, described judging unit comprises:
The first judgment sub-unit be used for to judge that whether frame period between the area-of-interest of the area-of-interest that enters first described virtual coil and last vehicle that enters virtual coil is less than minimum frame period number between two cars of presetting;
The second judgment sub-unit, be used for when described the first judgment sub-unit judges that frame period between the area-of-interest of the area-of-interest that entered first described virtual coil and last vehicle that enters virtual coil is not less than that minimum frame period is counted between the two default cars, judge described area-of-interest through the shared frame number of described virtual coil whether less than the frame number of presetting;
The output subelement is used for judging when obtaining described frame number greater than default frame number in described the second judgment sub-unit, exports in the described virtual coil result through vehicle, otherwise exports the result who does not pass through vehicle in the described virtual coil.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102441065A CN101770571B (en) | 2009-12-29 | 2009-12-29 | Method and device for detecting vehicle at night |
| PCT/CN2010/079525 WO2011079691A1 (en) | 2009-12-29 | 2010-12-07 | Method and device for detecting nighttime vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102441065A CN101770571B (en) | 2009-12-29 | 2009-12-29 | Method and device for detecting vehicle at night |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101770571A CN101770571A (en) | 2010-07-07 |
| CN101770571B true CN101770571B (en) | 2013-02-13 |
Family
ID=42503423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102441065A Active CN101770571B (en) | 2009-12-29 | 2009-12-29 | Method and device for detecting vehicle at night |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN101770571B (en) |
| WO (1) | WO2011079691A1 (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770571B (en) * | 2009-12-29 | 2013-02-13 | 北京世纪高通科技有限公司 | Method and device for detecting vehicle at night |
| CN102044152B (en) * | 2010-11-19 | 2013-10-30 | 杭州海康威视系统技术有限公司 | Day and night video detecting method and device |
| CN102142194B (en) * | 2010-12-30 | 2013-12-11 | 杭州海康威视数字技术股份有限公司 | Video detection method and system |
| CN102637362B (en) * | 2012-04-01 | 2014-06-18 | 长安大学 | Tunnel vehicle type identification method based on video |
| CN103489317A (en) * | 2013-10-10 | 2014-01-01 | 扬州瑞控汽车电子有限公司 | Method for detecting vehicle in different scenes |
| CN103984917A (en) * | 2014-04-10 | 2014-08-13 | 杭州电子科技大学 | Multi-feature nighttime vehicle detection method based on machine vision |
| CN105740788B (en) * | 2016-01-25 | 2018-11-16 | 大连楼兰科技股份有限公司 | A kind of abnormal theft preventing method of car based on interframe histogram Disturbance Detection |
| CN105946718B (en) * | 2016-06-08 | 2019-04-05 | 深圳芯智汇科技有限公司 | The method of car-mounted terminal and its switching display reverse image |
| CN106355140B (en) * | 2016-08-22 | 2018-03-02 | 平安科技（深圳）有限公司 | The method and device of vehicle detection |
| TWI700017B (en) * | 2018-10-17 | 2020-07-21 | 財團法人車輛研究測試中心 | Vehicle detecting method, nighttime vehicle detecting method based on dynamic light intensity and system thereof |
| CN112508002B (en) * | 2020-12-11 | 2023-08-29 | 杭州海康威视数字技术股份有限公司 | Car light red halo suppression method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1320063A2 (en) * | 2001-12-11 | 2003-06-18 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method and device for recognition and repeated recognition of objects |
| CN101383094A (en) * | 2008-10-21 | 2009-03-11 | 上海高德威智能交通系统有限公司 | Video triggering method and device |
| CN101436253A (en) * | 2007-11-14 | 2009-05-20 | 东软集团股份有限公司 | Method and device for verifying interested area of vehicle |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101295405A (en) * | 2008-06-13 | 2008-10-29 | 西北工业大学 | Portrait and vehicle recognition alarming and tracing method |
| CN101382997B (en) * | 2008-06-13 | 2011-06-22 | 青岛海信电子产业控股股份有限公司 | Vehicle detecting and tracking method and device at night |
| CN101770571B (en) * | 2009-12-29 | 2013-02-13 | 北京世纪高通科技有限公司 | Method and device for detecting vehicle at night |
-
2009
- 2009-12-29 CN CN2009102441065A patent/CN101770571B/en active Active
-
2010
- 2010-12-07 WO PCT/CN2010/079525 patent/WO2011079691A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1320063A2 (en) * | 2001-12-11 | 2003-06-18 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method and device for recognition and repeated recognition of objects |
| CN101436253A (en) * | 2007-11-14 | 2009-05-20 | 东软集团股份有限公司 | Method and device for verifying interested area of vehicle |
| CN101383094A (en) * | 2008-10-21 | 2009-03-11 | 上海高德威智能交通系统有限公司 | Video triggering method and device |
Non-Patent Citations (1)
| Title |
|---|
| 宋晨炜.基于ARM的电子警察车辆检测系统设计.《中国优秀硕士学位论文全文数据库,中国学术期刊(光盘版)电子期刊》.2009, * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2011079691A1 (en) | 2011-07-07 |
| CN101770571A (en) | 2010-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101770571B (en) | Method and device for detecting vehicle at night | |
| CN101382997B (en) | Vehicle detecting and tracking method and device at night | |
| US8441535B2 (en) | System and method for independent image sensor parameter control in regions of interest | |
| CN102556021B (en) | Control device for preventing cars from running red light | |
| CN102016876A (en) | Method and device for processing recorded image information from a vehicle | |
| EP1837803A3 (en) | Headlight, taillight and streetlight detection | |
| CN103400499B (en) | Ultra-high definition intelligent video electronic police system and vehicle violation judging method of ultra-high definition intelligent video electronic police system | |
| AU2013316125C1 (en) | Backward movement indicator apparatus for a vehicle | |
| CN204681510U (en) | A kind of vehicle-mounted traffic violation video apparatus for obtaining evidence | |
| EP2718869A2 (en) | Method and device for detecting objects in the area surrounding a vehicle | |
| US20150085118A1 (en) | Method and camera assembly for detecting raindrops on a windscreen of a vehicle | |
| CN103646546A (en) | An intelligent traffic system with a large-scale vehicle passing-forbidding function | |
| CN102496281A (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| CN105718923A (en) | Method for vehicle detection and counting at night based on inverse projection drawings | |
| CN104890567A (en) | Method and device for automatically turning on double-flash light | |
| CN102768799B (en) | Method for detecting red light running of vehicle at night | |
| CN106557754A (en) | A kind of vehicle detection at night and state judging method | |
| CN101398932B (en) | video vehicle detection method and device | |
| JP4025007B2 (en) | Railroad crossing obstacle detection device | |
| CN107067734A (en) | A kind of urban signal controlling intersection vehicles are detained peccancy detection method | |
| CN204155453U (en) | A kind of high-definition electronic police capturing retrograde vehicle | |
| CN203020184U (en) | Electric vehicle lane marking line detecting device based on double charge coupled devices (CCD) | |
| KR20130070210A (en) | Method for removing noise of image | |
| CN108154687B (en) | Night traffic flow detection method, device and system based on car lamp | |
| CN101430830B (en) | Imaging control method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |