CN105469604A - An in-tunnel vehicle detection method based on monitored images - Google Patents
An in-tunnel vehicle detection method based on monitored images Download PDFInfo
- Publication number
- CN105469604A CN105469604A CN201510915392.9A CN201510915392A CN105469604A CN 105469604 A CN105469604 A CN 105469604A CN 201510915392 A CN201510915392 A CN 201510915392A CN 105469604 A CN105469604 A CN 105469604A
- Authority
- CN
- China
- Prior art keywords
- image
- tunnel
- vehicle
- road surface
- brightness
- 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
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an in-tunnel vehicle detection method based on monitored images. The method comprises the following steps: a processor receives in-tunnel road surface area images at a present tunnel illuminating lamp brightness level acquired by a monitor camera in real time; processing is carried out according to characteristic areas of the road surface area images and characteristic areas of background images which are the same with the road surface area images in terms of illuminating lamp brightness; the background images are images acquired when no vehicle exists in a tunnel; and the processor determines whether a vehicle exists in a tunnel according to the processed result. The invention realizes detection of vehicles in the tunnel, and raises the accuracy of detection results.
Description
Technical field
The embodiment of the present invention relates to image data analysis techniques field, particularly relates to a kind of based on vehicle checking method in the tunnel of monitoring image.
Background technology
The method that in current tunnel, vehicle testing techniques is conventional utilizes the equipment Inspection vehicles such as ground sensing coil vehicle detector, infrared eye or radar meter with or without information.When practical application, the installation expense of ground induction coil is large, road pavement destroys that serious, cabling is complicated is unfavorable for lightning protection and the cost of maintenance is too large, has very large limitation; Be subject to the impact of highway roadside guardrail when infrared eye is installed and can detection leakage phenomenon be produced for the vehicle that the speed of a motor vehicle is too fast; Radar meter also may produce detection leakage phenomenon for the vehicle that the speed of a motor vehicle is too high.Therefore carry out vehicle detection according to the image of the CCTV camera collection in tunnel and become a trend.
Video vehicle detection method comparatively conventional at present mainly contains: frame differential method, optical flow method and background subtraction.Frame differential method has stronger adaptivity for the change of scene, but easily produces detection leakage phenomenon for static vehicle and slow vehicle; Optical flow method can detect the target of self-movement, and does not need any information knowing scene in advance, and also can detect when video camera moves and can not be affected, but its operational formula is complicated, and calculated amount is large and noise immunity is poor.Background subtraction is a kind of method conventional in fixed background situation, generally can provide characteristic the most completely, and simply, computing velocity is fast for its principle and algorithm, but comparatively large by the impact of the external condition such as illumination, weather, causes testing result accuracy rate low.
Summary of the invention
The embodiment of the present invention provides a kind of based on vehicle checking method in the tunnel of monitoring image, realizes complexity, the problem that testing result accuracy rate is low to overcome in prior art for vehicle testing techniques in tunnel.
Of the present invention based on vehicle checking method in the tunnel of monitoring image, comprising:
Processor receives road surface area image in the tunnel under the current tunnel lighting brightness grade of CCTV camera Real-time Collection;
Described processor processes according to the characteristic area of the background image of the characteristic area of described road surface area image and the area image equal illumination lamp brightness of described road surface, and described background image is without vehicle image in described tunnel;
Described processor judges whether have vehicle in tunnel according to the result after process;
Adopt the background image replaced without vehicle image under described equal illumination lamp brightness degree under the current tunnel lighting brightness grade of Real-time Collection.
Further, in the tunnel of described processor reception CCTV camera Real-time Collection before the area image of road surface, also comprise:
Processor stores in the tunnel under the different brightness degree of tunnel illuminating lamp of described CCTV camera collection without vehicle image.
Further, in the tunnel under the current tunnel lighting brightness grade of described processor reception CCTV camera Real-time Collection after the area image of road surface, also comprise:
Described processor judges whether the brightness variable signal receiving tunnel intraoral illumination lamp, if, the average image of multiple image corresponding after then asking the intraoral illumination lamp brightness change of described tunnel, and the background image after adopting described the average image to replace the change of corresponding lighting brightness.
Further, described processor processes without vehicle image according in the characteristic area of described image and described tunnel, comprising:
Intercept the characteristic area of described road surface area image;
Difference processing is carried out according to described characteristic area and the described characteristic area without vehicle image;
Rim detection is carried out to the image after described difference processing;
Piecemeal process is carried out to the image after described rim detection;
Add up the non-zero points number in specific block of image;
Vehicle has been judged whether according to described non-zero points number.
Further, describedly judge whether vehicle according to described non-zero points number, having comprised:
If described non-zero points number is in threshold range, then determine have vehicle to occur in described tunnel;
If described non-zero points number exceeds described threshold range, then determine to occur without vehicle in described tunnel.
Vehicle checking method in the tunnel that the present invention is based on monitoring image, carries out rim detection and piecemeal process by the characteristic area of road pavement image, and under the different brightness of illumination in tunnel background extraction image again.The method realizes simple, and application is convenient, and reliability is high, the situation that there will not be tunnel internal to have vehicle undetected, improves the accuracy rate of vehicle detection in tunnel.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 be the present invention is based on monitoring image tunnel in vehicle checking method process flow diagram;
Fig. 2 be the present invention is based on monitoring image tunnel in another process flow diagram of vehicle checking method;
Fig. 3 is that the present invention gathers image procossing schematic diagram.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 be the present invention is based on monitoring image tunnel in vehicle checking method process flow diagram, as shown in Figure 1, the present embodiment method, comprising:
Step 101, processor receive road surface area image in the tunnel under the current tunnel lighting brightness grade of CCTV camera Real-time Collection;
Step 102, described processor process for the characteristic area of the characteristic area of described road surface area image and the background image of described road surface area image equal illumination lamp brightness, and described background image is without vehicle image in described tunnel;
Step 103, described processor judge whether have vehicle in tunnel according to the result after process;
The background image replaced without vehicle image under described equal illumination lamp brightness degree under the current tunnel lighting brightness grade of step 104, employing Real-time Collection.
Further, in the tunnel of described processor reception CCTV camera Real-time Collection before the area image of road surface, also comprise:
Processor stores in the tunnel under the different brightness degree of tunnel illuminating lamp of described CCTV camera collection without vehicle image.
Specifically, regulate the brightness of tunnel illuminating lamp, step-length is adopted to be 10%, regulate from 10% ~ 100% brightness degree, often regulate a CCTV camera just gather under present lighting intensity without vehicle road area image, it can be used as the background image under corresponding bright to be saved in context vault.Road surface area image in usage monitoring video camera Real-time Collection tunnel, the parameter such as aperture type, time shutter, gain gathering CCTV camera during image should be set to MANUAL CONTROL mode; CCTV camera is the video camera for supervisory function bit in tunnel.Processor extracts the characteristic area of the road surface area image of this CCTV camera Real-time Collection, and by this characteristic area and background image with the characteristic area comparison of the background image of current lighting brightness same levels, judge whether have vehicle in tunnel according to comparison result.Illustrate, current lighting brightness grade is 30%, in the road surface area image of CCTV camera Real-time Collection and the background image of multiple lighting brightness grade lighting brightness grade be 30% background image process, and judge whether have vehicle in tunnel according to the result after process.
Further, described processor processes without vehicle image according in the characteristic area of described image and described tunnel, comprising:
Intercept the characteristic area of described road surface area image;
Difference processing is carried out according to described characteristic area and the described characteristic area without vehicle image;
Rim detection is carried out to the image after described difference processing;
Piecemeal process is carried out to the image after described rim detection;
Add up the non-zero points number in specific block of image;
Vehicle has been judged whether according to described non-zero points number.
Further, describedly judge whether vehicle according to described non-zero points number, having comprised:
If described non-zero points number is in threshold range, then determine have vehicle to occur in described tunnel;
If described non-zero points number exceeds described threshold range, then determine to occur without vehicle in described tunnel.
Further, described determine in described tunnel without vehicle occur after, also comprise:
Adopt the background image replaced without vehicle image under described equal illumination lamp brightness degree under the current tunnel lighting brightness grade of Real-time Collection.
Specifically, according to the image of Real-time Collection in the present embodiment, as shown in Figure 3 a, with background image, as shown in Figure 3 b, the method carrying out processing is intercepted by the characteristic area of real-time road surface area image as in Fig. 3 a 301, and this characteristic area 301 is carried out difference processing with the characteristic area 302 of background image, again the image after difference processing is carried out rim detection for shown in Fig. 3 c, the image after detection is carried out piecemeal and is treated to as shown in Figure 3 d.Adopt C++ in this example in conjunction with the method for OpenCV to realize image procossing, other programming language or other programmed methods also can be used to realize this function, this is not limited.
The method intercepting characteristic area use is:
cvSetImageROI(image,cvRect(x,y,width,height))；
Wherein, image represent Real-time Collection image 3a or without car background image 3b; (x, y) is coordinate points position in real-time image acquisition 3a of the point in feature regional images 301 upper left corner or the point in feature regional images 302 upper left corner without the coordinate points position in car background image 3b; Width is the picture traverse of feature regional images 301 or feature regional images 302; Height be feature regional images 301 or feature regional images 302 picture altitude.
The feature regional images 301 of real-time image acquisition 3a carries out phase reducing with the feature regional images 302 without car background image 3b, obtains difference image 3c.Adopt C++ in this example in conjunction with the method for OpenCV to realize image procossing, other programming language or other programmed methods also can be used to realize this function.
Wherein, the method that image subtraction uses is:
cvAbsDiff(constCvArr*image,constCvArr*B_image,CvArr*S_image)；
Wherein, image is the image of the characteristic area 301 intercepted under Real-time Collection tunnel internal pavement image 3a; B_image is the image of the characteristic area 302 without car background image 3b under the corresponding brightness of illumination in the context vault intercepted; S_image is the difference image 3c of two feature regional images exported.
S5., after obtaining difference image 3c, rim detection is carried out to difference image 3c and obtains edge-detected image 3d.Adopt C++ in this example in conjunction with the method for OpenCV to realize image procossing, other programming language or other programmed methods also can be used to realize this function.
The method that rim detection uses is:
cvCanny(S_image,BY_image,50,200,3)；
Wherein, BY_image is edge-detected image 3d.
S6. edge detected image 3d carries out piecemeal process.Be divided into by edge-detected image 3d 3 row 5 to arrange in the present embodiment, be namely altogether divided into 15 blocks of images.The non-zero points number of statistics view picture edge-detected image 3d, and the non-zero points number of most upper right hornblock image 303, the rule being appeared at tunnel road surface by vehicle is added up and can be obtained, and the decision condition having car to occur in tunnel is:
sum_all≥a(1.1)
Or
sum_all<a&sum_right>b(1.2)
Wherein, sum_all refers to the non-zero points number in edge-detected image 3d; Sum_right represents the non-zero points number in most upper right hornblock image 303; Wherein the numerical value deterministic process of a is: the statistical property of the position occurred in the picture from vehicle, and when the non-zero points number in edge-detected image 3d is less than a, vehicle only may appear in most upper right hornblock image 303; If vehicle appears in other block images, then the non-zero points number in edge-detected image 3d is necessarily greater than a.Wherein the numerical value deterministic process of b is: even if due to when in tunnel, real-time image acquisition 3a is without car, also there are some non-zero points with the edge-detected image 3d after the difference without car background image 3b, but these non-zero points are caused by noise, be scattered in entire image, can not all concentrate in the upper right hornblock image 303 in edge-detected image 3d, so when only having the non-zero points number in upper right hornblock image 303 to be greater than b, just think and have vehicle to occur in tunnel.Wherein, a, b are constant, and this is mainly determined by camera resolution and point block size.
If according to the decision condition in S6, when judging to occur without car in tunnel, then the tunnel internal image 3a of Real-time Collection is replaced the former background image 3b in context vault under corresponding brightness of illumination.
Further, in the tunnel under the current tunnel lighting brightness grade of described processor reception CCTV camera Real-time Collection after the area image of road surface, also comprise:
Described processor judges whether the brightness variable signal receiving tunnel intraoral illumination lamp transmission, if, the average image of multiple image corresponding after then asking the intraoral illumination lamp brightness change of described tunnel, and the background image after adopting described the average image to replace the change of corresponding lighting brightness.
Specifically, due to the change of external environment brightness moment, so for the camera in tunnel portal place and exit, the background image that can gather in advance is limited, even if when tunnel illuminating lamp brightness of illumination is consistent, the brightness that different time sections gathers image is different, and vehicle false drop rate can be caused to increase considerably; When there is rainy weather, in tunnel, road surface has large area ponding, in this case gather actual without car image with have car image be difficult to distinguish, vehicle false drop rate can be caused to increase.Tunnel intraoral illumination lamp brightness environmentally brightness and changing, and this change by have influence on CCTV camera Real-time Collection current tunnel in the brightness of image on road surface, therefore, after processor receives the brightness variable signal of tunnel intraoral illumination lamp transmission, the average image of multiple image corresponding after then asking tunnel intraoral illumination lamp brightness change, illustrate, when lighting brightness is 20% grade from 30% change of rank, the average image of multiple image corresponding when brightness is 20% grade by processor replaces 20% grade background image in stored data base.Achieve present intensity real-time update in background image in database and tunnel, improve the accuracy rate of testing result.
In sum, the program flow diagram that the present embodiment is corresponding as shown in Figure 2.
The present invention's advantage is compared with prior art:
1, the present invention adopts the image of the existing CCTV camera Real-time Collection of tunnel internal to carry out the detection of vehicle, without the need to burying ground induction coil underground, installation infrared detector, radar meter is not needed yet, decrease equipment mounting complexity and equipment purchase expense, when not affecting tunnel and normally monitoring, there is provided a road vision signal for the detection of the vehicle based on monitoring image, in tunnel, vehicle detection provides great convenience by video shunt;
2, the present invention clips only having the parts of images of light fixture information according to characteristics of image in tunnel, the partial image region of process only containing information of road surface.The partial image region containing road surface of Real-time Collection and the respective regions preserved in advance carried out subtracting each other obtaining difference image without car background image, rim detection is carried out to difference image and edge detect image carry out piecemeal process, add up the number of non-zero points in specific block of image, appear at the pixel count that may occupy in each small images in conjunction with vehicle, determine the threshold range judging whether vehicle exists.This algorithm utilizes vehicle on road surface, occur the statistical law of position, and detection speed is fast;
3, the present invention takes when tunnel intraoral illumination brightness changes, and 100 ~ 300 two field pictures under Resurvey present lighting intensity, ask its average image as the new background image under present lighting intensity, be saved in context vault.This algorithm eliminates illumination, weather to the impact of testing result, reduces outdoor environment to the impact detected, and reduces loss, false drop rate.
Last it is noted that above each embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (5)
1., based on a vehicle checking method in the tunnel of monitoring image, it is characterized in that, comprising:
Processor receives road surface area image in the tunnel under the current tunnel lighting brightness grade of CCTV camera Real-time Collection;
Described processor processes for the characteristic area of the characteristic area of described road surface area image and the background image of described road surface area image equal illumination lamp brightness, and described background image is without vehicle image in described tunnel;
Described processor judges whether have vehicle in tunnel according to the result after process;
Adopt the background image replaced without vehicle image under described equal illumination lamp brightness degree under the current tunnel lighting brightness grade of Real-time Collection.
2. method according to claim 1, is characterized in that, in the tunnel of described processor reception CCTV camera Real-time Collection before the area image of road surface, also comprises:
Processor stores in the tunnel under the different brightness degree of tunnel illuminating lamp of described CCTV camera collection without vehicle image.
3. method according to claim 2, is characterized in that, in the tunnel under the current tunnel lighting brightness grade of described processor reception CCTV camera Real-time Collection after the area image of road surface, also comprises:
Described processor judges whether the brightness variable signal receiving tunnel intraoral illumination lamp, if, the average image of multiple image corresponding after then asking the intraoral illumination lamp brightness change of described tunnel, and the background image after adopting described the average image to replace the change of corresponding lighting brightness.
4. the method according to any one of claims 1 to 3, is characterized in that, described processor processes without vehicle image according in the characteristic area of described image and described tunnel, comprising:
Intercept the characteristic area of described road surface area image;
Difference processing is carried out according to described characteristic area and the described characteristic area without vehicle image;
Rim detection is carried out to the image after described difference processing;
Piecemeal process is carried out to the image after described rim detection;
Add up the non-zero points number in specific block of image;
Vehicle has been judged whether according to described non-zero points number.
5. method according to claim 4, is characterized in that, has describedly judged whether vehicle according to described non-zero points number, comprising:
If described non-zero points number is in threshold range, then determine have vehicle to occur in described tunnel;
If described non-zero points number exceeds described threshold range, then determine to occur without vehicle in described tunnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510915392.9A CN105469604A (en) | 2015-12-09 | 2015-12-09 | An in-tunnel vehicle detection method based on monitored images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510915392.9A CN105469604A (en) | 2015-12-09 | 2015-12-09 | An in-tunnel vehicle detection method based on monitored images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105469604A true CN105469604A (en) | 2016-04-06 |
Family
ID=55607249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510915392.9A Pending CN105469604A (en) | 2015-12-09 | 2015-12-09 | An in-tunnel vehicle detection method based on monitored images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105469604A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147877A (en) * | 2017-06-01 | 2017-09-08 | 大连海事大学 | FX night fog day condition all-weather colorful video imaging system and its construction method |
| CN108288361A (en) * | 2018-01-25 | 2018-07-17 | 深圳前海大观信息技术有限公司 | A kind of passageway for fire apparatus door state detection method |
| EP3506621A1 (en) * | 2017-12-28 | 2019-07-03 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and computer program |
| CN110648540A (en) * | 2019-09-09 | 2020-01-03 | 安徽师范大学 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0986036A2 (en) * | 1998-09-10 | 2000-03-15 | Hitachi Denshi Kabushiki Kaisha | Method of updating reference background image, method of detecting entering objects and system for detecting entering objects using the methods |
| CN101004860A (en) * | 2006-11-30 | 2007-07-25 | 复旦大学 | Video method for collecting information of vehicle flowrate on road in real time |
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| JP2009169718A (en) * | 2008-01-17 | 2009-07-30 | Meidensha Corp | Environmentally-adaptable intruder detection apparatus by image processing |
| CN101968924A (en) * | 2010-10-19 | 2011-02-09 | 北方工业大学 | High-resolution image-based real-time traffic flow detection method |
| JP2012104872A (en) * | 2010-11-05 | 2012-05-31 | Omron Corp | Image processing unit, and image processing program |
| CN103366569A (en) * | 2013-06-26 | 2013-10-23 | 东南大学 | Method and system for snapshotting traffic violation vehicle in real time |
| CN103810703A (en) * | 2014-01-22 | 2014-05-21 | 安徽科力信息产业有限责任公司 | Picture processing based tunnel video moving object detection method |
| CN104778725A (en) * | 2015-04-14 | 2015-07-15 | 长兴泛亚照明电器有限公司 | Underground garage for adaptive background update and tunnel moving target detection method |
| CN105096603A (en) * | 2014-12-12 | 2015-11-25 | 天津艾思科尔科技有限公司 | All-weather detection device |
-
2015
- 2015-12-09 CN CN201510915392.9A patent/CN105469604A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0986036A2 (en) * | 1998-09-10 | 2000-03-15 | Hitachi Denshi Kabushiki Kaisha | Method of updating reference background image, method of detecting entering objects and system for detecting entering objects using the methods |
| CN101004860A (en) * | 2006-11-30 | 2007-07-25 | 复旦大学 | Video method for collecting information of vehicle flowrate on road in real time |
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| JP2009169718A (en) * | 2008-01-17 | 2009-07-30 | Meidensha Corp | Environmentally-adaptable intruder detection apparatus by image processing |
| CN101968924A (en) * | 2010-10-19 | 2011-02-09 | 北方工业大学 | High-resolution image-based real-time traffic flow detection method |
| JP2012104872A (en) * | 2010-11-05 | 2012-05-31 | Omron Corp | Image processing unit, and image processing program |
| CN103366569A (en) * | 2013-06-26 | 2013-10-23 | 东南大学 | Method and system for snapshotting traffic violation vehicle in real time |
| CN103810703A (en) * | 2014-01-22 | 2014-05-21 | 安徽科力信息产业有限责任公司 | Picture processing based tunnel video moving object detection method |
| CN105096603A (en) * | 2014-12-12 | 2015-11-25 | 天津艾思科尔科技有限公司 | All-weather detection device |
| CN104778725A (en) * | 2015-04-14 | 2015-07-15 | 长兴泛亚照明电器有限公司 | Underground garage for adaptive background update and tunnel moving target detection method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147877A (en) * | 2017-06-01 | 2017-09-08 | 大连海事大学 | FX night fog day condition all-weather colorful video imaging system and its construction method |
| EP3506621A1 (en) * | 2017-12-28 | 2019-07-03 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and computer program |
| US11144762B2 (en) | 2017-12-28 | 2021-10-12 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and medium |
| CN108288361A (en) * | 2018-01-25 | 2018-07-17 | 深圳前海大观信息技术有限公司 | A kind of passageway for fire apparatus door state detection method |
| CN110648540A (en) * | 2019-09-09 | 2020-01-03 | 安徽师范大学 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
| CN110648540B (en) * | 2019-09-09 | 2021-07-02 | 安徽师范大学 | Expressway emergency lane occupation tracking system and method based on unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105260713B (en) | A kind of method for detecting lane lines and device | |
| JP5551595B2 (en) | Runway monitoring system and method | |
| JP5518359B2 (en) | Smoke detector | |
| KR101810727B1 (en) | Vehicle and method for operating a camera arrangement for a vehicle | |
| US20130342692A1 (en) | Ptz video visibility detection method based on luminance characteristic | |
| CN106778534B (en) | Method for identifying ambient light during vehicle running | |
| CN105469604A (en) | An in-tunnel vehicle detection method based on monitored images | |
| Gallen et al. | Towards night fog detection through use of in-vehicle multipurpose cameras | |
| CN107845264A (en) | A kind of volume of traffic acquisition system and method based on video monitoring | |
| JP4729610B2 (en) | Smoke detector | |
| CN105812618B (en) | A kind of method for testing motion and motion detection apparatus | |
| US8462211B2 (en) | Method of detecting objects | |
| US20180260964A1 (en) | System and method for detecting moving object in an image | |
| CN103793921B (en) | Moving object extraction method and moving object extraction device | |
| JP2019154027A (en) | Method and device for setting parameter for video monitoring system, and video monitoring system | |
| CN110020642A (en) | A kind of visibility recognition methods based on vehicle detection | |
| CN104778723A (en) | Method for performing motion detection on infrared image with three-frame difference method | |
| CN107169969B (en) | Highway dangerous rock collapse deposit size measurement and alarm system based on FPGA | |
| CN108230288B (en) | Method and device for determining fog state | |
| KR101795652B1 (en) | Device for Measuring Visibility for Fog Guardian Device | |
| CN111524121A (en) | Road and bridge fault automatic detection method based on machine vision technology | |
| Dehghani et al. | Single camera vehicles speed measurement | |
| Sezgin et al. | Safe autonomous driving in adverse weather: Sensor evaluation and performance monitoring | |
| CN109635782A (en) | A method of obtaining unmanned required static traffic information | |
| CN105046223A (en) | Device for detecting severity of ''black-hole effect'' at tunnel entrance and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160406 |
|
| RJ01 | Rejection of invention patent application after publication |