CN103065470A - Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces - Google Patents
Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces Download PDFInfo
- Publication number
- CN103065470A CN103065470A CN2012105519078A CN201210551907A CN103065470A CN 103065470 A CN103065470 A CN 103065470A CN 2012105519078 A CN2012105519078 A CN 2012105519078A CN 201210551907 A CN201210551907 A CN 201210551907A CN 103065470 A CN103065470 A CN 103065470A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- track
- image
- signal lamp
- red light
- 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.)
- Granted
Links
Images
Landscapes
- Traffic Control Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
A detection device for behaviors of running the red light of a vehicle based on machine vision with a single eye and multiple detection faces comprises a microprocessor and a monitoring sensor, wherein the monitoring sensor is used for monitoring road conditions. The monitoring sensor is a high definition camera with the single eye and the multiple detection faces. The high definition camera with the single eye and the multiple detection faces is used for shooting signal lamps and an image relative to the signal lamps and of the vehicle running the red light near a stop mark of a road. An image processing technique is used for identification of the states of the traffic signal lamps and the motion states of the vehicle near the stop mark. The behaviors of running the red light of the vehicle are automatically judged according to relevant laws and regulations of the state, and illegal parking recordings and relevant evidence materials are automatically generated. The detection device for the behaviors of running the red light of the vehicle based on the machine vision with the single eye and the multiple detection faces is accurate in detection, convenient to maintain and install, and complete in evidence obtaining of rule and regulation breaking behaviors.
Description
Technical field
The present invention relates to a kind of running red light for vehicle behavior pick-up unit, the effective integrated use such as machine vision technique, image processing techniques, data communication technology, computer networking technology is managed in break in traffic rules and regulations, be particularly useful for special detection and the electronic police of processing the behavior of making a dash across the red light.
Background technology
Develop rapidly along with economy, the rapid increase of vehicle fleet size, day by day serious traffic problems have been produced, such as traffic environment deterioration, frequent accidents, congested in traffic obstruction etc., particularly present degradating trend in medium-and-large-sized urban transportation situations such as Beijing, Shanghai, the death toll of the traffic hazard of annual China is in 100,000 people's left and right horizontal basically, occupies first place in the world for successive years.In China, every dead 3 people of traffic hazard have 2 to be because the traffic violation.China's statistics of traffic accidents data for many years shows, the main inflicter of traffic hazard is automobile driver, and pedestrian, rider and people by bike are three in the traffic hazards colony that is injured greatly, 3rd/4th in the death toll, pedestrian, rider and people by bike.
Many statistical data show that the serious traffic hazard of thumping majority occurs in the crossroad, and thumping majority is wherein broken rules and regulations or made a dash across the red light and cause owing to automobile driver.Generally monitor the violating the regulations of traffic with video camera in the metropolitan traffic administration in present China, owing to lack the support of image processing techniques and artificial intelligence technology, also need a large amount of manpowers to carry out real-time observation, thereby unusual road surface situation is made real-time reflection, this disposal route needs a large amount of human inputs, simultaneously the supervision personnel is required again higher quality and notice.The shortcoming that adopts this working method be take a large amount of police strength, law enfrocement official easily tired, can not all weather operations, strong evidence can't be provided.
A kind of traffic intersection that is used for unattended duty based on the running red light for vehicle behavior pick-up unit of many detection faces of monocular machine vision of the present invention, device can be monitored the situation of traffic intersection automatically, travel conditions to vehicle is traced and monitored, and automatically records the vehicle that violates the traffic regulations; In the invention the crucial problem that will solve be realize can be correctly, the moving vehicle that makes a dash across the red light in fast detecting and the identification video sequence, like this can be with the video information that obtains for the law ruling.
The existing traffic rules of China are that State Council issued on March 9th, 1988, in the rule crossing vehicle, pedestrian current are had clear and definite regulation.Regulation in the tenth of the chapter 2 of rule: (1) permits vehicle, walk when green light is bright, hinders the vehicle of keeping straight on and the walk of being let pass but the vehicle of turning is inaccurate; When (2) amber light is bright, inaccurate vehicles and pedestrians, but the pedestrian who has crossed the vehicle of stop line and entered crossing can continue to pass through; (3) during when red, inaccurate vehicle, walk; When (4) the green arrow lamp is bright, permits vehicle and pass through in a direction indicated by the arrow; (5) amber light when flicker, vehicle, pedestrian must guarantee under the safe principle current.The vehicle of turning right and the right, T shape crossing run into preceding article (2), (3) rules and regulations regularly without the through vehicles of lateral road, in the situation that does not hinder the vehicles and pedestrians of being let pass, and P Passable.
The existing traffic law of China can concluded with table 1 aspect the relation of signal lamp and traveling state of vehicle;
| Red light | Amber light | Green light | Vehicle condition |
| Bright | Go out | Go out | Stop |
| Bright | Bright | Go out | Preparation is advanced |
| Go out | Bright | Go out | Preparation stops |
| Go out | Go out | Bright | Advance |
The relation of table 1 signal lamp and traveling state of vehicle
To make a dash across the red light this traffic violation and brought the phenomenon of threat to people life in order to stop in the past, that can only utilize traffic-police on dutyly plays supervision and managerial role; Now because the attention of traffic department, both at home and abroad with image, camera, sensor high-technology in traffic intersection, the type systematic that these effort cause being called red light video camera (RLC) produces, and it is often worked with traffic lights control circuit and the inductive coil monitor that is embedded under the road surface.
The detection technique of making a dash across the red light starts from late 1980s, and since 1994, the industrially developed country such as the U.S., France succeed in developing the system of making a dash across the red light in succession.The surveillance of making a dash across the red light of France's development adopts the mode of spark photograph, and what the ground such as san francisco, usa used is that geomagnetic induction coil is in conjunction with the CCD acquisition mode.China introduced the surveillance of making a dash across the red light of photographic means in 1996, the units such as Beijing Communication scientific research institution have developed black and white type red light surveillance.Shenzhen Green's prestige transport science and techonologies company limited in 1997 has developed the CCD colour that detects based on the geomagnetic induction coil surveillance of making a dash across the red light, and Northwestern Polytechnical University has then developed the colored CCD that detects based on the video surveillance of making a dash across the red light.The intelligent detecting method that makes a dash across the red light based on image processing techniques mainly contains two kinds at present: (1) inductive coil monitor is in conjunction with the detection method of making a dash across the red light of taking a picture or making a video recording; (2) completely based on the detection method of video technique.
In the use aspect the vehicle peccancy of traffic intersection, although also there are the imagination of this respect in many places and scientific research institution, also do not have so far automatically to detect the practical application that is applied to the crossing with recognition technology, just the method that may use is set forth.Traffic intersection in flourishing city, what usually adopt is the mode of operation of camera-sensing coil, and coil is embedded under the earth's surface, takes picture violating the regulations by the technology such as vibration-sensing, hot sensing control camera.This mode has following several significant shortcoming: the cost of (1) system is high.Because whenever increasing a new monitoring point, just must drop into human and material resources and financial resources and bury sensing coil underground at traffic intersection; (2) crossing to be monitored is dumb.Because can only monitor at the crossing of having buried coil; (3) maintenance of system is inconvenient, if because inductive coil damages, need to again bury, lay; (4) affect the normal operation of traffic, because when burying inductive coil, need the traffic on blocking-up road surface.
The state of signal lamp is the foundation of judging whether vehicle breaks rules and regulations.When monitoring vehicles peccancy, the state of signal lamp can obtain by the Access Control line sometimes.But, can not access easily surveillance at the control line of some local traffic lamp, people also wish and can by the method for image processing, obtain the status information of signal lamp, the intelligent and dirigibility that can improve like this system.
On the other hand, the white thick line on the crossing is reminding driver and pedestrian, if when the state of signal lamp is red light, vehicle or pedestrian cross this white thick line (stop line) and just be considered to make a dash across the red light.In image is processed, whether surmount stop line in order to identify vehicle, just need to determine the position of stop line.And whether the state of marker lamp surmounts stop line and must carry out simultaneously with the identification vehicle.So just can make the running red light for vehicle behavior pick-up unit based on many detection faces of monocular machine vision have real-time, accurate, intelligentized feature.
But, on road from visual angle, the state of signal lamp and the optimal viewing angle of stop line are on the direction of traffic, these state and near present technical some difficulties that exist of the image information the stop line to want simultaneously the picked up signal lamp with a video camera, although can adopt two cameras, state for detection of signal lamp, another is for detection of near the vehicle the stop line and pedestrian's state.Although this mode is feasible, can increase the complexity of cost and system, the real-time that impact detects.
The Ministry of Public Security revises " motor vehicle driving license is applied to get and used and stipulate " of issuing, and comes into effect from 1 day January in 2013, and make a dash across the red light and detained 6 minutes, be take traffic police's on-site law-enforcing as main, it is not yet clear and definite that present electronic police exposes." 6 minutes situation of 200 yuan of punishment buttons is take scene punishment as main; for electric police grasp shoot; temporarily will not score at present; because the current mobility car is as walking-replacing tool; not every motor vehicle is all driven by the car owner; thus be difficult to determine which driver's driving is the phenomenon of making a dash across the red light of electric police grasp shoot be difficult to identify, so temporarily will not deduct points at present to these a part of illegal activities of electric police grasp shoot." but along with the widespread use of high-definition camera, as long as during the driver's that electronic police can significantly be captured facial image, electronic police substitutes on-site law-enforcing and just comes within a measurable distance.
National inventing patent numbers 200610053154.2 discloses a kind of monitoring vehicle breaking regulation method and apparatus based on omnidirectional computer vision, this invention adopts a kind of omnibearing vision sensor to monitor vehicle-state and the signal lamp state at whole crossing, thereby the break in traffic rules and regulations behavior such as has judged whether to make a dash across the red light.Omnibearing vision sensor has a panorama to obtain the advantage of whole 360 ° of physical environment video images, is installed in the middle act of violating regulations that can detect all phase places of crossing in crossing; But also exist obvious defective simultaneously, because the image of process omnibearing vision sensor has carried out the physical compression of image, so that the image of traffic lights is difficult to identification accurately; On the other hand, because the compression of images amount has caused greatly the license plate number identification of vehicles peccancy and the affirmation of driver people's face are produced very large difficulty.Although can adopt speed dome camera and omnibearing vision sensor to merge, capture the image in license plate number and zone, driver's seat with quick, solution will certainly increase the cost of system and the complexity of control like this.Along with the fast development of high-definition camera, identify simultaneously for the behavior of making a dash across the red light and car plate and brought possibility.
National inventing patent numbers 201210239881.3 discloses a kind of motor vehicle red light violation evidence collecting method based on HD video, adopts the high-definition camera capture video, according to the object detecting and tracking technology of video content to vehicle behavior trajectory analysis.Under the red light phase place of traffic lights, the behavior of making a dash across the red light is detected, after confirming as red light violation, obtain high-definition image effectively violating the regulations, formation meets two evidence obtaining pictures that make a dash across the red light of national standard (GA/T832-2009), and will record the synthetic evidence obtaining of the video flowing video of whole red light violation process.Be delivered to the management system of law enforcement agency by the network result that will collect evidence at last.The greatest problem of this invention is: high-definition camera is installed in the back of vehicle, the sight line of stop line is easily by occlusion, cause easily line ball and the more error of line judgement, and can not directly photograph driver's front face image, also need in addition the phase place of access signal lamp from teleseme.National inventing patent number 201010598795.2 Jaywalking snapshot methods and device also exist same problem.
According to " red-lamp running automatic recording system general technical specifications " (GA/T496-2004), finish the video capture process to the red light violation behavior." red-lamp running automatic recording system general technical specifications " be middle requirement (GA/T496-2004), the behavior automatic production record of making a dash across the red light answers the logging machine motor-car to make a dash across the red light the image information of two to three positions in the process with the reflection automobile driver illegal activities process of making a dash across the red light, the information of first position should be able to clearly distinguish that motor vehicle is pressed in or crosses the situation of stop line, and the image information of second and the 3rd position should be able to reflect that whole vehicle body crossed the situation of stop line.
The present invention is devoted to solve following problem: adopt a high-definition camera can photograph near the associated picture of the vehicles running red light of the signal lamp track stop line relevant with signal lamp simultaneously, be the image of first position, second position and the 3rd position, also need to comprise the license plate image information of discernible driver's face image information and steering vehicle in the captured image; Automatically identification and judge the red light violation behavior, automatically identify the car plate of vehicles peccancy, for electronic police automatically law enforcement vaild evidence is provided.
Summary of the invention
The deficiency that is difficult to take into account the aspects such as integrality of the convenience that detects accuracy, maintenance and installation, evidence obtaining violating the regulations in order to overcome existing running red light for vehicle behavior pick-up unit based on machine vision the invention provides a kind of running red light for vehicle behavior pick-up unit based on the machine vision of the many detection faces of monocular that detects precisely, safeguards that evidence obtaining easy for installation and violating the regulations is complete.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular, described running red light for vehicle behavior pick-up unit comprise microprocessor and are used for monitoring the monitoring sensor of crossing situation that described microprocessor comprises:
View data reads and pretreatment module, is used for reading from monitoring sensor passing the video image information of coming, and video image information is carried out pre-service;
Virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track are used for related between track, customization track and the control signal lamp on the virtual stop line, customization traffic lights surveyed area, customization road in customization track;
Network transmission module is used for image, the when and where information exchange of the process violating the regulations of vehicles peccancy are crossed Internet Transmission to traffic police administrative authority;
Described monitoring sensor is the high-definition camera of the many detection faces of monocular, the high-definition camera of the many detection faces of described monocular comprises in order to the catadioptric minute surface of reflected signal lamp regional extent, in order to take the high-definition camera at stop line near zone travel condition of vehicle and signal lamp state, described catadioptric minute surface is positioned at the front upper place of high-definition camera, catadioptric high-definition camera function by the catadioptric minute surface photograph the corresponding signal lamp state in the crossing of monitoring, can also photograph near the stop line of monitoring crossing state by high-definition camera on the other hand; At the high-definition camera imaging surface image information of two detection faces is arranged, its middle and upper part is the image of signal lamp state, and the bottom is the image of the crossing state corresponding with this signal lamp state; All tracks on the image pickup scope covering path of a high-definition camera, the fixedly corner of adjustment catadioptric minute surface is so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state;
Described microprocessor also comprises:
The color space conversion module, the image rgb color space that is used for signal lamp zone that the described traffic lights surveyed area of the video image on each track is set is transformed into the HSV color space;
The signal lamp state detection module is used for the detection to the signal lamp state of the video image on each track;
The moving vehicle detection module is used for the detection to the moving vehicle object of the video image on each track;
Whether the vehicle peccancy judge module exists the red light violation behavior for detection of the vehicle on each track;
The license plate number identification module of vehicles peccancy is for the license plate number of identification vehicles peccancy;
Record generation module violating the regulations is used for the information of the license plate number of the whole process of vehicle peccancy behavior and same time, place, travel direction and vehicles peccancy is generated a record violating the regulations together.
Further, the high-definition camera of the many detection faces of described monocular, adopt high-definition camera and catadioptric minute surface to carry out integrated design, draw a catadioptric mirror support bar at the supporting seat of high-definition camera, one end of support bar is connected with universal auxiliary connection with the catadioptric minute surface, and the lens location of the relative high-definition camera of catadioptric minute surface can be adjusted at any angle; When actual installation is used, by adjusting relative position and the angle of catadioptric minute surface and high-definition camera camera lens, so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state; Adjust and finish the universal auxiliary connection of finger lock obtains signal lamp effectively, accurately with assurance high-definition camera function state.
Further, in described virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track, described virtual detection line is set and is used for setting up the virtual detection line corresponding with the stop line on the real road, and the method for customization is directly by drawing the line that coincides with stop line on the road plane image of high-definition camera shooting; Described traffic lights surveyed area is set the state for detection of signal lamp, because the position of traffic lights is fixed, set the interference that to get rid of some images by the traffic signal light condition surveyed area, improve detecting the accuracy of traffic signal light condition, the method for customization is directly to draw the zone that matches with the traffic lights size on the catadioptric mirror image parts of images by passing through of taking of high-definition camera; The customization of described track is used for being set in the direction that allows vehicle operating on the multilane, in some cities to multilane on clear left lateral, craspedodrome, right lateral track, the current direction setting in track must be consistent with actual road junction roadway situation, the method of customization is to draw the lane line consistent with actual road junction roadway situation on the road plane image of directly taking by high-definition camera, needs to set up related between lane line and the virtual detection line after lane line customizes; The customization related with signal lamp of described track is used for setting up related between track and the signal lamp, be that the left lateral track is carried out related with the left lateral signal lamp, Through Lane carries out related with the craspedodrome signal lamp, the right lateral track is carried out related with the right lateral signal lamp, because related between lane line and the virtual detection line set up in the front, therefore just set up the related of virtual detection line and signal lamp here; Just can judge according to such association and traffic law whether vehicle exists the behavior of making a dash across the red light and get over the act of violating regulations that line travels.
Further again, in the described signal lamp state detection module, at first, by the color normalized, 3 component values of HSV are all between 0～l; Then use the number of pixels Number of statistical color histogram tone H in the green 3 kinds of color gamuts of reddish yellow
{ R, Y, G}, the total number of pixels of the pixel in the traffic lights surveyed area is designated as Total, calculates both ratio with formula (1),
NumRadio
{i}＝Number
{i}/Total i∈{R,Y,G} （1）
In the formula, Number
{ i}For a certain color is in the number of pixels of traffic lights surveyed area in the green 3 kinds of colors of reddish yellow, Total is the total number of pixels of the pixel of traffic lights surveyed area, NumRadio
{ i}Be the ratio of a certain color in the green 3 kinds of colors of reddish yellow in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone;
Carry out at last the state of traffic lights and judge that determination methods is provided by formula (2),
In the formula, NumRadio
{ R}Be the ratio of redness in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone, NumRadio
{ Y}Be the ratio of yellow in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone, NumRadio
{ G}Be the ratio of green in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone.
In the described moving vehicle detection module, extract foreground moving object on this track with the motion history image algorithm, judge on the virtual detection line on this track, whether to have existed the moving vehicle object;
Described motion history image algorithm, it is the MHI algorithm, the motion history image that obtains among the MHI is that the adjacent image frame in a period of time interval carries out obtaining after inter-frame difference and the gray processing processing, this algorithm that obtains motion history image can obtain well the motion outline template for the target that is kept in motion all the time and calculated amount smaller, the MHI algorithm can be used for a movement gradient image of establishment and calculate direction and the size of movement gradient by the SOBEL operator, utilize simultaneously this result can be further used for estimating the direction of motion of object, because not needing background modeling only to carry out the inter-frame difference processing, the MHI algorithm just can not obtain foreground moving object, thereby this algorithm has very high real-time for extracting foreground moving object, computing method as shown in Equation (3)
In the formula, the binary picture sequence of D (x, y, t) moving region, τ is the duration, H
τ(x, y, t-1) was the motion history binary picture sequence in a upper moment;
After having obtained the foreground moving object on the track by the MHI algorithm, owing to may exist pedestrian or other Moving Objects on the track, therefore need to judge whether vehicle of these foreground moving object; Distinguish foreground moving object with area threshold, shape and direction of motion in the present invention, because the area of vehicle is larger than pedestrian or cyclist's area, pedestrian or cyclist's direction of motion is perpendicular to the track direction simultaneously, and shape has than big difference, judge that computing method represent with formula (4)
In the formula, ∑ H τ (x, y, t) is the sum of all pixels of the binary image of foreground object, T
1Be area threshold, Shape is the shape attribute of foreground object, then finds shape attribute to obtain T by binary image being searched the border
2Be the rectangular shape threshold value, Direction is the direction of motion of foreground object, obtains T during by calculating MHI algorithm
3Be the direction threshold value;
Judgement by formula (4) can extract the vehicle that moves on the track effectively, judges then whether this moving vehicle is pressed in or crosses virtual detection line.
In the described vehicle peccancy judge module, be divided into two kinds of basic conditions; The first situation is that the road that the track traffic lights is clearly arranged is arranged, and the second situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights is arranged;
The first situation is for the road that the clear driveway travel directions is arranged, at first can whether there be the vehicle lane change to travel according to detecting on the virtual track, if there is the vehicle on the craspedodrome road to occur to turn right or turn left all to be judged to be and drive against traffic regulations, the situation of this situation and signal lamp is irrelevant; Next is drives against traffic regulations relevant with signal lamp, this situation is will be according to the situation of signal lamp, virtual track and the detection case that stops on the dummy line make a decision, for each track of each travel direction corresponding signal lamp is arranged generally speaking, and each travel direction also has corresponding stop line, therefore can judge according to the existing traffic law of China, when being taken in the when red of certain direction running in certain track, if find that having vehicle entering stops dummy line or be in stopping just to think on the dummy line position to make a dash across the red light, as violating the regulations; When the amber light of fooled certain direction running in certain track is bright, if find that having vehicle entering stops dummy line as act of violating regulations;
The second situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights is arranged, the judgement of this situation is more more complex than the first situation, even this is because be to allow to turn right according to the existing traffic law of China vehicle near the right, road in the situation of red light, that is to say, be not that all surmount the vehicle that stops the dummy line position and all break rules and regulations in the situation of red light, distinguish whether the result that also will see the back vehicle tracking violating the regulations is arranged; Specific practice is to find to have vehicle entering and stop dummy line or be in to stop just to set on the dummy line position this vehicle and get over line states, then continue to follow the tracks of, the vehicle of line states does not bend to right if tracking has been found to have set more, so just as act of violating regulations.
In described vehicle peccancy judge module, judge to begin to record motor vehicle violation evidence obtaining video image when having existed the running red light for vehicle situation, begin to capture the image of first position; Along with passage of time, detect vehicle still under signal lamp disabled orientation ruuning situation, continue to capture the image of second and the 3rd position, the form of candid photograph image is JPEG.
In the license plate number identification module of described vehicles peccancy, according to the vehicles peccancy image information of first position that high-definition camera is captured, the number on the front part of vehicle car plate is identified; If can not identify the license plate number of vehicles peccancy, continue to carry out license plate number identification with the vehicles peccancy image information of second position, carry out the license plate number recognition result still in the situation of None-identified in the vehicles peccancy image information of the 3rd position, allow break in traffic rules and regulations process the manual confirmation of department.
In the described record generation module violating the regulations, with the specific requirement and the Index Content that have comprised " red-lamp running automatic recording system general technical specifications " defined of stipulating in " the traffic safety illegal activities image forensics technical manual " stipulated in the GA/T832-2009 national standard and the GA/T496-2004 international standard in the record; Capture the video image of first position, second position and the image of the 3rd position and the process of making a dash across the red light and all record violating the regulations with the attachment version apposition, the annex name is named in the mode in time+place; Record violating the regulations and annex are kept in the red light violation database of record.
The pulsed light that when capturing the red light violation behavior image of primary importance, the second place and the 3rd position, adopts a kind of narrow-pulse generator the to send floor light that glistens, the flash of light floor light has microprocessor control, when capturing action, start simultaneously the flash of light floor light, the pulsed light flash duration is 1/tens of general flash duration, the flash of light floor light is installed near many detection faces of monocular video camera, and flash illumination light throws towards crossing stop line direction.
Beneficial effect of the present invention is mainly manifested in: 1, adopt a high-definition camera can photograph near the associated picture of the vehicles running red light of the signal lamp track stop line relevant with signal lamp simultaneously, detect precisely, safeguard that evidence obtaining easy for installation and violating the regulations is complete; 2, automatically identify and judge the red light violation behavior, automatically identify the car plate of vehicles peccancy, the peccancy detection algorithm is simple, and the ratio of performance to price is high; 3, coming into operation of this device can have very large deterrent effect to the driver of custom running red light for vehicle behavior, also greatly reduced traffic police's Spot Enforcing amount simultaneously, improved traffic administration efficient.
Description of drawings
Fig. 1 is many detection faces of monocular high definition camera device; The 1-high-definition camera, 2-catadioptric minute surface;
Fig. 2 is based on the fundamental diagram of running red light for vehicle behavior pick-up unit of the machine vision of the many detection faces of monocular; The 1-high-definition camera, 2-catadioptric minute surface, 3-traffic lights, 4-stop line, 5-track, 6-vehicle, 9-microprocessor;
Fig. 3 is based on the image synoptic diagram of running red light for vehicle behavior pick-up unit of the machine vision of the many detection faces of monocular; The 3-traffic lights, 4-stop line, 5-track, 6-vehicle, the car plate of 7-vehicle, the driver face of 8-vehicle;
Fig. 4 is the image that stop line-right lane control signal lamp is corresponding that is divided into right lane-right lane after the imaging synoptic diagram of Fig. 3 customizes by the track;
Fig. 5 is the image that stop line-Through Lane control signal lamp is corresponding that is divided into Through Lane-Through Lane after the imaging synoptic diagram of Fig. 3 customizes by the track;
Fig. 6 is the image that stop line-left-lane control signal lamp is corresponding that is divided into left-lane-left-lane after the imaging synoptic diagram of Fig. 3 customizes by the track;
Fig. 7 is based on the process flow diagram that some threads in the running red light for vehicle behavior pick-up unit of machine vision of the many detection faces of monocular detect red light violation.
Embodiment
The invention will be further described below in conjunction with accompanying drawing.
With reference to Fig. 1 ~ Fig. 7, a kind of running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular, based on the fundamental diagram of the running red light for vehicle behavior pick-up unit of the machine vision of the many detection faces of monocular as shown in Figure 2; Described running red light for vehicle behavior pick-up unit comprises microprocessor, is used for monitoring the monitoring sensor of road cross situation, described microprocessor comprises: view data reads and pretreatment module, be used for reading the video image information of coming from the monitoring sensor biography, video image information is carried out pre-service; Virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track are used for related between track, customization track and the control signal lamp on the virtual stop line, customization traffic lights surveyed area, customization road in customization track; Network transmission module is used for image, the when and where information exchange of the process violating the regulations of vehicles peccancy are crossed Internet Transmission to traffic police administrative authority; Described monitoring sensor is the high-definition camera of the many detection faces of monocular, the high-definition camera of the many detection faces of described monocular comprises in order to the catadioptric minute surface of reflected signal lamp regional extent, in order to take the high-definition camera at stop line near zone travel condition of vehicle and signal lamp state, described catadioptric minute surface is positioned at the front upper place of high-definition camera, catadioptric high-definition camera function by the catadioptric minute surface photograph the corresponding signal lamp state in the crossing of monitoring, can also photograph near the stop line of monitoring crossing state by high-definition camera on the other hand; At the high-definition camera imaging surface image information of two detection faces is arranged, its middle and upper part is the image of signal lamp state, and the bottom is the image of the crossing state corresponding with this signal lamp state; Adopt the high definition imager chip of 3200 * 1200 pixels more than 5,000,000 in the high-definition camera, all tracks on the image pickup scope covering path of a high-definition camera, high-definition camera is installed in the place close with signal lamp, for the place that signal lamp bracket is arranged high-definition camera is placed on the same support, adjust the fixedly corner of catadioptric minute surface, so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state;
High-definition camera and catadioptric minute surface carry out integrated design, as shown in Figure 1, draw a catadioptric mirror support bar at the supporting seat of high-definition camera, one end of support bar is connected with universal auxiliary connection with the catadioptric minute surface, and the lens location of the relative high-definition camera of catadioptric minute surface can be adjusted at any angle; When actual installation is used, by adjusting relative position and the angle of catadioptric minute surface and high-definition camera camera lens, so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state; Adjust and finish the universal auxiliary connection of finger lock obtains signal lamp effectively, accurately with assurance high-definition camera function state; The image information that two detection faces are arranged at the high-definition camera imaging surface like this, its middle and upper part are the image of signal lamp state, and the bottom is the image of the crossing state corresponding with this signal lamp state, as shown in Figure 3;
Described virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track, described virtual detection line is set and is used for setting up the virtual detection line corresponding with the stop line on the real road, and the method for customization is directly by drawing the line that coincides with stop line on the road plane image of high-definition camera shooting; Described traffic lights surveyed area is set the state for detection of signal lamp, because the position of traffic lights is fixed, set the interference that to get rid of some images by the traffic signal light condition surveyed area, improve detecting the accuracy of traffic signal light condition, the method for customization is directly to draw the zone that matches with the traffic lights size on the catadioptric mirror image parts of images by passing through of taking of high-definition camera; The customization of described track is used for being set in the direction that allows vehicle operating on the multilane, in some cities to multilane on clear left lateral, craspedodrome, right lateral track, the current direction setting in track must be consistent with actual road junction roadway situation, the method of customization is to draw the lane line consistent with actual road junction roadway situation on the road plane image of directly taking by high-definition camera, needs to set up related between lane line and the virtual detection line after lane line customizes; The customization related with signal lamp of described track is used for setting up related between track and the signal lamp, be that the left lateral track is carried out related with the left lateral signal lamp, Through Lane carries out related with the craspedodrome signal lamp, the right lateral track is carried out related with the right lateral signal lamp, because related between lane line and the virtual detection line set up in the front, therefore just set up the related of virtual detection line and signal lamp here; Just can judge according to such association and traffic law whether vehicle exists the behavior of making a dash across the red light and get over the act of violating regulations that line travels; In order to improve detection efficiency, the present invention makes a dash across the red light to detect to road vehicle and resolves into track running red light for vehicle detection, each track running red light for vehicle detects and uses a thread, namely has how many bar track correspondences what threads on the road and detects respectively the track behavior of making a dash across the red light of getting on the bus; By such customization with the captured image of high-definition camera shown in the accompanying drawing 3, be divided into image, the image on the Through Lane and the image on the right lateral track on the left lateral track shown in accompanying drawing 4, accompanying drawing 5 and accompanying drawing 6, comprised each autocorrelative virtual detection line and signal lamp in this three width of cloth image;
For the efficient that improves detection and the convenience of calculating, on software system design, among the present invention the running red light for vehicle detection in each track is calculated with a thread respectively, utilize the multithreading treatment technology in the Java language, namely had how many bar tracks just what threads to come the corresponding running red light for vehicle of computing to detect with; Accompanying drawing 7 is the running red light for vehicle detection procedure of some threads, shown in the dotted portion in the accompanying drawing 7, has what threads to move at the same time detection with regard to the dotted portion shown in the drawings attached 7 arranged side by side so;
Described microprocessor also comprises:
The color space conversion module, the image rgb color space that is used for signal lamp zone that the described traffic lights surveyed area of the video image on each track is set is transformed into the HSV color space, for pre-service is carried out in the state recognition of signal lamp; Colouring information is mainly distinguished by tone H, with color histogram tone H is added up, and is used for distinguishing the color of signal lamp;
The signal lamp state detection module is used for the detection to the signal lamp state of the video image on each track; At first, by the color normalized, 3 component values of HSV are all between 0～l; The scope of the tone H of the green 3 kinds of color traffic lights of reddish yellow is as follows: red traffic lights zone: [0,0.0667] ∪ [0.9058,1]; Amber signal lamp zone: [0.0705,0.2353]; Green traffic lamp zone: [0.2549,0.5882]; Then use the number of pixels Number of statistical color histogram tone H in the green 3 kinds of color gamuts of reddish yellow
{ R, Y, G}, the total number of pixels of the pixel in the traffic lights surveyed area is designated as Total, calculates both ratio with formula (1),
NumRadio
{i}=Number
{i}/Total i∈{R,Y,G} （1）
In the formula, Number
{ i}For a certain color is in the number of pixels of traffic lights surveyed area in the green 3 kinds of colors of reddish yellow, Total is the total number of pixels of the pixel of traffic lights surveyed area, NumRadio
{ i}Be the ratio of a certain color in the green 3 kinds of colors of reddish yellow in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone;
Carry out at last the state of traffic lights and judge that determination methods is provided by formula (2),
In the formula, NumRadio
{ R}Be the ratio of redness in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone, NumRadio
{ Y}Be the ratio of yellow in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone, NumRadio
{ G}Be the ratio of green in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone;
The moving vehicle detection module is used for the detection to the moving vehicle object of the video image on each track; Extract foreground moving object on this track with the motion history image algorithm, judge on the virtual detection line on this track, whether to have existed the moving vehicle object;
The motion history image algorithm, it is the MHI algorithm, the motion history image that obtains among the MHI is that the adjacent image frame in a period of time interval carries out obtaining after inter-frame difference and the gray processing processing, this algorithm that obtains motion history image can obtain well the motion outline template for the target that is kept in motion all the time and calculated amount smaller, the MHI algorithm can be used for a movement gradient image of establishment and calculate direction and the size of movement gradient by the SOBEL operator, utilize simultaneously this result can be further used for estimating the direction of motion of object, because not needing background modeling only to carry out the inter-frame difference processing, the MHI algorithm just can not obtain foreground moving object, thereby this algorithm has very high real-time for extracting foreground moving object, computing method as shown in Equation (3)
In the formula, the binary picture sequence of D (x, y, t) moving region, τ is the duration, H
τ(x, y, t-1) was the motion history binary picture sequence in a upper moment;
After having obtained the foreground moving object on the track by the MHI algorithm, owing to may exist pedestrian or other Moving Objects on the track, therefore need to judge whether vehicle of these foreground moving object; Distinguish foreground moving object with area threshold, shape and direction of motion in the present invention, because the area of vehicle is larger than pedestrian or cyclist's area, pedestrian or cyclist's direction of motion is perpendicular to the track direction simultaneously, and shape has than big difference, judge that computing method represent with formula (4)
In the formula, ∑ H
τ(x, y, t) is the sum of all pixels of the binary image of foreground object, T
1Be area threshold, Shape is the shape attribute of foreground object, then finds shape attribute to obtain T by binary image being searched the border
2Be the rectangular shape threshold value, Direction is the direction of motion of foreground object, obtains T during by calculating MHI algorithm
3Be the direction threshold value;
Judgement by formula (4) can extract the vehicle that moves on the track effectively, judges then whether this moving vehicle is pressed in or crosses virtual detection line;
Whether the vehicle peccancy judge module has violating the regulationsly for detection of vehicle, basically can be divided into two kinds of basic conditions here; A kind of situation is that the road that the track traffic lights is clearly arranged is arranged, and another kind of situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights (reddish yellow is green) is arranged.
The first situation is for the road that the clear driveway travel directions is arranged, at first can whether there be the vehicle lane change to travel according to detecting on the virtual track, if there is the vehicle on the craspedodrome road to occur to turn right or turn left all to be judged to be and drive against traffic regulations, the situation of this situation and signal lamp is irrelevant; Next is drives against traffic regulations relevant with signal lamp, this situation is will be according to the situation of signal lamp, virtual track and the detection case that stops on the dummy line make a decision, for each track of each travel direction corresponding signal lamp is arranged generally speaking, and each travel direction also has corresponding stop line, therefore can judge according to the existing traffic law of China, when being taken in the when red of certain direction running in certain track, if find that having vehicle entering stops dummy line or be in stopping just to think on the dummy line position to make a dash across the red light, as violating the regulations; When the amber light of fooled certain direction running in certain track is bright, stop dummy line as violating the regulations if find have vehicle entering;
The second situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights (reddish yellow is green) is arranged, the judgement of this situation is more more complex than the first situation, even this is because be to allow to turn right according to the existing traffic law of China vehicle near the right, road in the situation of red light, that is to say, be not that all surmount the vehicle that stops the dummy line position and all break rules and regulations in the situation of red light, distinguish whether the result that also will see the back vehicle tracking violating the regulations is arranged; Specific practice is to find to have vehicle entering and stop dummy line or be in to stop just to set on the dummy line position this vehicle and get over line states, then continues to follow the tracks of, and has found to have set more that the vehicle of line states does not bend to right if follow the tracks of, so just as violating the regulations;
Accurately reflect the automobile driver illegal activities process of making a dash across the red light with the image information of three or three above positions among the present invention, require the information of first position should be able to clearly distinguish that motor vehicle is pressed in or crosses the situation of stop line, the image information of second and the 3rd position should be able to reflect that whole vehicle body crossed the situation of stop line;
In described vehicle peccancy judge module, judge to begin to record motor vehicle violation evidence obtaining video image when having existed the running red light for vehicle situation, begin to capture the image of first position; Along with passage of time, detect vehicle still under signal lamp disabled orientation ruuning situation, continue to capture the image of second and the 3rd position, the form of candid photograph image is JPEG;
The license plate number identification module of vehicles peccancy is used for the license plate number of identification vehicles peccancy, processes in order to automatically break rules and regulations; According to the vehicles peccancy image information of first position that high-definition camera is captured, the number on the front part of vehicle car plate is identified; If can not identify the license plate number of vehicles peccancy, continue to carry out license plate number identification with the vehicles peccancy image information of second position, carry out the license plate number recognition result still in the situation of None-identified in the vehicles peccancy image information of the 3rd position, license plate number temporarily is set to * * * * * * *, and relief break in traffic rules and regulations is processed the manual confirmation of department;
Record generation module violating the regulations, be used for the information of the license plate number of the whole process of vehicle peccancy behavior and same time, place, travel direction and vehicles peccancy is generated a record violating the regulations together, comprised specific requirement and the Index Content of " red-lamp running automatic recording system general technical specifications " defined of stipulating in " the traffic safety illegal activities image forensics technical manual " stipulated in the GA/T832-2009 national standard and the GA/T496-2004 international standard in the record; Capture image and the video image of first position, second position and the 3rd position and all record violating the regulations with the attachment version apposition, the annex name is named in the mode in time+place; Record violating the regulations and annex are kept in the red light violation database of record;
Network transmission module, the record violating the regulations that is used for being kept at the red light violation database of record are confirmed to process with the personnel that treat traffic police administrative authority by the management system of Internet Transmission to law enforcement agency.
With reference to Fig. 1 ~ Fig. 7, all the other are identical with embodiment 1, institute is not both the filler lighting mode that adopts, in the situation of crossing illuminating ray deficiency, in order to capture the facial image on high-quality license plate image and the driver's seat, the present invention is capturing primary importance, the pulsed light that adopts a kind of narrow-pulse generator to send during the image of the second place and the 3rd position floor light that glistens, the flash of light floor light has microprocessor control, when capturing action, start simultaneously the flash of light floor light, the pulsed light flash duration is 1/tens of general flash duration, the flash of light floor light is installed near many detection faces of monocular video camera, and flash illumination light throws towards crossing stop line direction.Flash illumination light can be ignored driver's eye irritation, but can photograph clearly the car plate of vehicle and people's face of driver.
Claims (10)
1. running red light for vehicle behavior pick-up unit based on the machine vision of the many detection faces of monocular, described running red light for vehicle behavior pick-up unit comprise microprocessor and are used for monitoring the monitoring sensor of crossing situation that described microprocessor comprises:
View data reads and pretreatment module, is used for reading from monitoring sensor passing the video image information of coming, and video image information is carried out pre-service;
Virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track are used for related between track, customization track and the control signal lamp on the virtual stop line, customization traffic lights surveyed area, customization road in customization track;
Network transmission module is used for image, the when and where information exchange of the process violating the regulations of vehicles peccancy are crossed Internet Transmission to traffic police administrative authority;
It is characterized in that: described monitoring sensor is the high-definition camera of the many detection faces of monocular, the high-definition camera of the many detection faces of described monocular comprises the catadioptric minute surface in order to reflected signal lamp regional extent, in order to take the high-definition camera at stop line near zone travel condition of vehicle and signal lamp state, described catadioptric minute surface is positioned at the front upper place of high-definition camera, catadioptric high-definition camera function by the catadioptric minute surface photograph the corresponding signal lamp state in the crossing of monitoring, can also photograph near the stop line of monitoring crossing state by high-definition camera on the other hand; At the high-definition camera imaging surface image information of two detection faces is arranged, its middle and upper part is the image of signal lamp state, and the bottom is the image of the crossing state corresponding with this signal lamp state; All tracks on the image pickup scope covering path of a high-definition camera, the fixedly corner of adjustment catadioptric minute surface is so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state;
Described microprocessor also comprises:
The color space conversion module, the image rgb color space that is used for signal lamp zone that the described traffic lights surveyed area of the video image on each track is set is transformed into the HSV color space;
The signal lamp state detection module is used for the detection to the signal lamp state of the video image on each track;
The moving vehicle detection module is used for the detection to the moving vehicle object of the video image on each track;
Whether the vehicle peccancy judge module exists the red light violation behavior for detection of the vehicle on each track;
The license plate number identification module of vehicles peccancy is for the license plate number of identification vehicles peccancy;
Record generation module violating the regulations is used for the information of the license plate number of the whole process of vehicle peccancy behavior and same time, place, travel direction and vehicles peccancy is generated a record violating the regulations together.
2. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1, it is characterized in that: the high-definition camera of the many detection faces of described monocular, adopt high-definition camera and catadioptric minute surface to carry out integrated design, draw a catadioptric mirror support bar at the supporting seat of high-definition camera, one end of support bar is connected with universal auxiliary connection with the catadioptric minute surface, and the lens location of the relative high-definition camera of catadioptric minute surface can be adjusted at any angle; When actual installation is used, by adjusting relative position and the angle of catadioptric minute surface and high-definition camera camera lens, so that the top in the image of high-definition camera imaging can photograph the image of signal lamp state; Adjust and finish the universal auxiliary connection of finger lock obtains signal lamp effectively, accurately with assurance high-definition camera function state.
3. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in described virtual detection line setting, the setting of traffic lights surveyed area, track customization, the related customized module with signal lamp in track, described virtual detection line is set and is used for setting up the virtual detection line corresponding with the stop line on the real road, and the method for customization is directly by drawing the line that coincides with stop line on the road plane image of high-definition camera shooting; Described traffic lights surveyed area is set the state for detection of signal lamp, because the position of traffic lights is fixed, set the interference that to get rid of some images by the traffic signal light condition surveyed area, improve detecting the accuracy of traffic signal light condition, the method for customization is directly to draw the zone that matches with the traffic lights size on the catadioptric mirror image parts of images by passing through of taking of high-definition camera; The customization of described track is used for being set in the direction that allows vehicle operating on the multilane, in some cities to multilane on clear left lateral, craspedodrome, right lateral track, the current direction setting in track must be consistent with actual road junction roadway situation, the method of customization is to draw the lane line consistent with actual road junction roadway situation on the road plane image of directly taking by high-definition camera, needs to set up related between lane line and the virtual detection line after lane line customizes; The customization related with signal lamp of described track is used for setting up related between track and the signal lamp, be that the left lateral track is carried out related with the left lateral signal lamp, Through Lane carries out related with the craspedodrome signal lamp, the right lateral track is carried out related with the right lateral signal lamp, because related between lane line and the virtual detection line set up in the front, therefore just set up the related of virtual detection line and signal lamp here; Just can judge according to such association and traffic law whether vehicle exists the behavior of making a dash across the red light and get over the act of violating regulations that line travels.
4. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in the described signal lamp state detection module, at first, by the color normalized, 3 component values of HSV are all between 0～l; Then use the number of pixels Number of statistical color histogram tone H in the green 3 kinds of color gamuts of reddish yellow
{ R, Y, G}, the total number of pixels of the pixel in the traffic lights surveyed area is designated as Total, calculates both ratio with formula (1),
NumRadio
{i}＝Number
{i}/Total
i∈{R,Y,G} （1）
In the formula, Number
{ i}For a certain color is in the number of pixels of traffic lights surveyed area in the green 3 kinds of colors of reddish yellow, Total is the total number of pixels of the pixel of traffic lights surveyed area, NumRadio
{ i}Be the ratio of a certain color in the green 3 kinds of colors of reddish yellow in the total number of pixels of the number of pixels value of traffic lights surveyed area and the pixel in this zone;
Carry out at last the state of traffic lights and judge that determination methods is provided by formula (2),
5. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in the described moving vehicle detection module, extract foreground moving object on this track with the motion history image algorithm, judge on the virtual detection line on this track, whether to have existed the moving vehicle object;
Described motion history image algorithm, it is the MHI algorithm, the motion history image that obtains among the MHI is that the adjacent image frame in a period of time interval carries out obtaining after inter-frame difference and the gray processing processing, this algorithm that obtains motion history image can obtain well the motion outline template for the target that is kept in motion all the time and calculated amount smaller, the MHI algorithm can be used for a movement gradient image of establishment and calculate direction and the size of movement gradient by the SOBEL operator, utilize simultaneously this result can be further used for estimating the direction of motion of object, because not needing background modeling only to carry out the inter-frame difference processing, the MHI algorithm just can not obtain foreground moving object, thereby this algorithm has very high real-time for extracting foreground moving object, computing method as shown in Equation (3)
In the formula, the binary picture sequence of D (x, y, t) moving region, τ is the duration, H
τ(x, y, t-1) was the motion history binary picture sequence in a upper moment;
After having obtained the foreground moving object on the track by the MHI algorithm, owing to may exist pedestrian or other Moving Objects on the track, therefore need to judge whether vehicle of these foreground moving object; Distinguish foreground moving object with area threshold, shape and direction of motion in the present invention, because the area of vehicle is larger than pedestrian or cyclist's area, pedestrian or cyclist's direction of motion is perpendicular to the track direction simultaneously, and shape has than big difference, judge that computing method represent with formula (4)
Judgement by formula (4) can extract the vehicle that moves on the track effectively, judges then whether this moving vehicle is pressed in or crosses virtual detection line.
6. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2 is characterized in that: in the described vehicle peccancy judge module, be divided into two kinds of basic conditions; The first situation is that the road that the track traffic lights is clearly arranged is arranged, and the second situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights is arranged;
The first situation is for the road that the clear driveway travel directions is arranged, at first can whether there be the vehicle lane change to travel according to detecting on the virtual track, if there is the vehicle on the craspedodrome road to occur to turn right or turn left all to be judged to be and drive against traffic regulations, the situation of this situation and signal lamp is irrelevant; Next is drives against traffic regulations relevant with signal lamp, this situation is will be according to the situation of signal lamp, virtual track and the detection case that stops on the dummy line make a decision, for each track of each travel direction corresponding signal lamp is arranged generally speaking, and each travel direction also has corresponding stop line, therefore can judge according to the existing traffic law of China, when being taken in the when red of certain direction running in certain track, if find that having vehicle entering stops dummy line or be in stopping just to think on the dummy line position to make a dash across the red light, as violating the regulations; When the amber light of fooled certain direction running in certain track is bright, if find that having vehicle entering stops dummy line as act of violating regulations;
The second situation is that the road that does not have clear and definite track traffic lights and only have a traffic lights is arranged, the judgement of this situation is more more complex than the first situation, even this is because be to allow to turn right according to the existing traffic law of China vehicle near the right, road in the situation of red light, that is to say, be not that all surmount the vehicle that stops the dummy line position and all break rules and regulations in the situation of red light, distinguish whether the result that also will see the back vehicle tracking violating the regulations is arranged; Specific practice is to find to have vehicle entering and stop dummy line or be in to stop just to set on the dummy line position this vehicle and get over line states, then continue to follow the tracks of, the vehicle of line states does not bend to right if tracking has been found to have set more, so just as act of violating regulations.
7. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in described vehicle peccancy judge module, judge to begin to record motor vehicle violation evidence obtaining video image when having existed the running red light for vehicle situation, begin to capture the image of first position; Along with passage of time, detect vehicle still under signal lamp disabled orientation ruuning situation, continue to capture the image of second and the 3rd position, the form of candid photograph image is JPEG.
8. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in the license plate number identification module of described vehicles peccancy, according to the vehicles peccancy image information of first position that high-definition camera is captured, the number on the front part of vehicle car plate is identified; If can not identify the license plate number of vehicles peccancy, continue to carry out license plate number identification with the vehicles peccancy image information of second position, carry out the license plate number recognition result still in the situation of None-identified in the vehicles peccancy image information of the 3rd position, allow break in traffic rules and regulations process the manual confirmation of department.
9. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 1 or 2, it is characterized in that: in the described record generation module violating the regulations, with the specific requirement and the Index Content that have comprised " red-lamp running automatic recording system general technical specifications " defined of stipulating in " the traffic safety illegal activities image forensics technical manual " stipulated in the GA/T832-2009 national standard and the GA/T496-2004 international standard in the record; Capture the video image of first position, second position and the image of the 3rd position and the process of making a dash across the red light and all record violating the regulations with the attachment version apposition, the annex name is named in the mode in time+place; Record violating the regulations and annex are kept in the red light violation database of record.
10. the running red light for vehicle behavior pick-up unit of the machine vision based on the many detection faces of monocular as claimed in claim 8, it is characterized in that: capturing primary importance, the pulsed light that adopts a kind of narrow-pulse generator to send during the red light violation behavior image of the second place and the 3rd position floor light that glistens, the flash of light floor light has microprocessor control, when capturing action, start simultaneously the flash of light floor light, the pulsed light flash duration is 1/tens of general flash duration, the flash of light floor light is installed near many detection faces of monocular video camera, and flash illumination light throws towards crossing stop line direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210551907.8A CN103065470B (en) | 2012-12-18 | 2012-12-18 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210551907.8A CN103065470B (en) | 2012-12-18 | 2012-12-18 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103065470A true CN103065470A (en) | 2013-04-24 |
| CN103065470B CN103065470B (en) | 2014-12-17 |
Family
ID=48108082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210551907.8A Active CN103065470B (en) | 2012-12-18 | 2012-12-18 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065470B (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325258A (en) * | 2013-06-24 | 2013-09-25 | 武汉烽火众智数字技术有限责任公司 | Red light running detecting device and method based on video processing |
| CN104134350A (en) * | 2014-08-11 | 2014-11-05 | 浙江力石科技股份有限公司 | Intelligent dome camera system for traffic violation behavior recognition |
| CN104702907A (en) * | 2014-03-20 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and system for stitching video |
| CN105070061A (en) * | 2015-08-19 | 2015-11-18 | 成都正广科技有限公司 | Evidence-obtaining inspection method and system for vehicle peccancy |
| CN105812674A (en) * | 2014-12-29 | 2016-07-27 | 浙江大华技术股份有限公司 | Signal lamp color correction method, monitoring method, and device thereof |
| CN106560861A (en) * | 2015-09-30 | 2017-04-12 | 徐贵力 | Intelligent supervision method based on computer vision |
| CN107038869A (en) * | 2017-05-08 | 2017-08-11 | 钟辉 | A kind of judgement system violating the regulations of traffic circulation |
| CN107067745A (en) * | 2017-06-15 | 2017-08-18 | 河南中安占海控股集团有限公司 | Intelligent traffic management systems |
| CN107221160A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | Smart electronicses police's system for detecting regulation violation |
| CN107221159A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107221164A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107230359A (en) * | 2016-03-24 | 2017-10-03 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107230360A (en) * | 2016-03-24 | 2017-10-03 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107463170A (en) * | 2016-06-06 | 2017-12-12 | 通用汽车环球科技运作有限责任公司 | Traffic control equipment and the sensor-based relevance of traffic lane for autonomous vehicle navigation |
| CN107533798A (en) * | 2015-07-08 | 2018-01-02 | 欧姆龙株式会社 | Image processing apparatus and with the traffic control system of the device, image processing method |
| CN107786788A (en) * | 2016-08-31 | 2018-03-09 | 百度在线网络技术（北京）有限公司 | Intelligent traffic lamp system and its image processing method |
| CN108280438A (en) * | 2018-02-02 | 2018-07-13 | 刘洁 | Entry region driver identity identifying system |
| CN109643375A (en) * | 2016-08-02 | 2019-04-16 | 宝马股份公司 | For learn the vehicle behavior of monitored automobile method and corresponding automobile |
| CN110766949A (en) * | 2018-07-27 | 2020-02-07 | 浙江宇视科技有限公司 | Violation snapshot method and device |
| CN110930715A (en) * | 2019-11-21 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and system for identifying red light running of non-motor vehicle and violation processing platform |
| CN110929676A (en) * | 2019-12-04 | 2020-03-27 | 浙江工业大学 | Deep learning-based real-time detection method for illegal turning around |
| CN111107305A (en) * | 2018-10-26 | 2020-05-05 | 杭州海康威视数字技术股份有限公司 | Monitoring interface configuration method, device and system and camera |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111710189A (en) * | 2014-12-01 | 2020-09-25 | 星克跃尔株式会社 | Control method for electronic device, and recording medium |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
| CN112200148A (en) * | 2020-11-06 | 2021-01-08 | 中国计量大学 | Decentralized traffic integrity evaluation system |
| WO2021028751A1 (en) * | 2019-08-13 | 2021-02-18 | International Business Machines Corporation | Determining the state of infrastructure in a region of interest |
| CN112638712A (en) * | 2018-08-06 | 2021-04-09 | 克诺尔商用车制动系统有限公司 | Camera monitoring system |
| CN113870558A (en) * | 2021-09-26 | 2021-12-31 | 中国联合网络通信集团有限公司 | Vehicle detection method, vehicle detection device, vehicle, and traffic control device |
| CN114761310A (en) * | 2019-12-05 | 2022-07-15 | 塞夫霍兰德有限公司 | System for checking operating state of component on vehicle and operating state checking method |
| CN115762173A (en) * | 2022-11-03 | 2023-03-07 | 湖北九州数字科技有限公司 | Traffic violation monitoring method and device based on three-dimensional road map |
| CN117392621A (en) * | 2023-11-07 | 2024-01-12 | 西南交通大学 | Method and system for identifying behavior of motor vehicle in case of turning right without giving away pedestrians |
| CN117392621B (en) * | 2023-11-07 | 2024-06-07 | 西南交通大学 | Method and system for identifying behavior of motor vehicle in case of turning right without giving away pedestrians |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000031707A1 (en) * | 1998-11-23 | 2000-06-02 | Nestor, Inc. | Non-violation event filtering for a traffic light violation detection system |
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN1987345A (en) * | 2006-12-20 | 2007-06-27 | 东华大学 | Single eye stereo vision sensor |
| CN101710448A (en) * | 2009-12-29 | 2010-05-19 | 浙江工业大学 | Road traffic state detecting device based on omnibearing computer vision |
| CN101930628A (en) * | 2010-09-21 | 2010-12-29 | 北京大学 | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method |
| CN102110369A (en) * | 2010-12-21 | 2011-06-29 | 汉王科技股份有限公司 | Jaywalking snapshot method and device |
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
-
2012
- 2012-12-18 CN CN201210551907.8A patent/CN103065470B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000031707A1 (en) * | 1998-11-23 | 2000-06-02 | Nestor, Inc. | Non-violation event filtering for a traffic light violation detection system |
| CN1912950A (en) * | 2006-08-25 | 2007-02-14 | 浙江工业大学 | Device for monitoring vehicle breaking regulation based on all-position visual sensor |
| CN1987345A (en) * | 2006-12-20 | 2007-06-27 | 东华大学 | Single eye stereo vision sensor |
| CN101710448A (en) * | 2009-12-29 | 2010-05-19 | 浙江工业大学 | Road traffic state detecting device based on omnibearing computer vision |
| CN101930628A (en) * | 2010-09-21 | 2010-12-29 | 北京大学 | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method |
| CN102110369A (en) * | 2010-12-21 | 2011-06-29 | 汉王科技股份有限公司 | Jaywalking snapshot method and device |
| CN102768800A (en) * | 2012-07-12 | 2012-11-07 | 复旦大学 | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos |
Non-Patent Citations (1)
| Title |
|---|
| 江昆: "基于视频检测的闯红灯自动抓拍系统研究与设计", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325258A (en) * | 2013-06-24 | 2013-09-25 | 武汉烽火众智数字技术有限责任公司 | Red light running detecting device and method based on video processing |
| CN104702907A (en) * | 2014-03-20 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Method and system for stitching video |
| US9961305B2 (en) | 2014-03-20 | 2018-05-01 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and system for video stitching |
| CN104702907B (en) * | 2014-03-20 | 2019-05-10 | 杭州海康威视数字技术股份有限公司 | A kind of method and system of video-splicing |
| CN104134350A (en) * | 2014-08-11 | 2014-11-05 | 浙江力石科技股份有限公司 | Intelligent dome camera system for traffic violation behavior recognition |
| CN111710189B (en) * | 2014-12-01 | 2023-09-08 | 现代自动车株式会社 | Control method for electronic device, and recording medium |
| CN111710189A (en) * | 2014-12-01 | 2020-09-25 | 星克跃尔株式会社 | Control method for electronic device, and recording medium |
| CN105812674B (en) * | 2014-12-29 | 2019-05-21 | 浙江大华技术股份有限公司 | A kind of color correct method, monitoring method and the device of signal lamp |
| CN105812674A (en) * | 2014-12-29 | 2016-07-27 | 浙江大华技术股份有限公司 | Signal lamp color correction method, monitoring method, and device thereof |
| CN107533798B (en) * | 2015-07-08 | 2020-08-14 | 欧姆龙株式会社 | Image processing device, traffic management system having the same, and image processing method |
| CN107533798A (en) * | 2015-07-08 | 2018-01-02 | 欧姆龙株式会社 | Image processing apparatus and with the traffic control system of the device, image processing method |
| CN105070061A (en) * | 2015-08-19 | 2015-11-18 | 成都正广科技有限公司 | Evidence-obtaining inspection method and system for vehicle peccancy |
| CN106560861A (en) * | 2015-09-30 | 2017-04-12 | 徐贵力 | Intelligent supervision method based on computer vision |
| CN107221160A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | Smart electronicses police's system for detecting regulation violation |
| CN107221164A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107221159A (en) * | 2016-03-22 | 2017-09-29 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107230360A (en) * | 2016-03-24 | 2017-10-03 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107230359A (en) * | 2016-03-24 | 2017-10-03 | 深圳市以捷创新科技有限公司 | The peccancy detection method of smart electronicses police's system for detecting regulation violation |
| CN107463170A (en) * | 2016-06-06 | 2017-12-12 | 通用汽车环球科技运作有限责任公司 | Traffic control equipment and the sensor-based relevance of traffic lane for autonomous vehicle navigation |
| CN109643375A (en) * | 2016-08-02 | 2019-04-16 | 宝马股份公司 | For learn the vehicle behavior of monitored automobile method and corresponding automobile |
| CN109643375B (en) * | 2016-08-02 | 2023-10-31 | 宝马股份公司 | Method for learning the behavior of a vehicle of a monitored vehicle and corresponding vehicle |
| CN107786788A (en) * | 2016-08-31 | 2018-03-09 | 百度在线网络技术（北京）有限公司 | Intelligent traffic lamp system and its image processing method |
| CN107038869A (en) * | 2017-05-08 | 2017-08-11 | 钟辉 | A kind of judgement system violating the regulations of traffic circulation |
| CN107067745A (en) * | 2017-06-15 | 2017-08-18 | 河南中安占海控股集团有限公司 | Intelligent traffic management systems |
| CN108280438A (en) * | 2018-02-02 | 2018-07-13 | 刘洁 | Entry region driver identity identifying system |
| CN110766949B (en) * | 2018-07-27 | 2021-09-28 | 浙江宇视科技有限公司 | Violation snapshot method and device |
| CN110766949A (en) * | 2018-07-27 | 2020-02-07 | 浙江宇视科技有限公司 | Violation snapshot method and device |
| CN112638712A (en) * | 2018-08-06 | 2021-04-09 | 克诺尔商用车制动系统有限公司 | Camera monitoring system |
| CN112638712B (en) * | 2018-08-06 | 2024-04-16 | 克诺尔商用车制动系统有限公司 | Video camera monitoring system |
| CN111107305A (en) * | 2018-10-26 | 2020-05-05 | 杭州海康威视数字技术股份有限公司 | Monitoring interface configuration method, device and system and camera |
| GB2601689A (en) * | 2019-08-13 | 2022-06-08 | Ibm | Determining the state of infrastructure in a region of interest |
| US11157741B2 (en) | 2019-08-13 | 2021-10-26 | International Business Machines Corporation | Determining the state of infrastructure in a region of interest |
| WO2021028751A1 (en) * | 2019-08-13 | 2021-02-18 | International Business Machines Corporation | Determining the state of infrastructure in a region of interest |
| GB2601689B (en) * | 2019-08-13 | 2023-03-15 | Ibm | Determining the state of infrastructure in a region of interest |
| CN110930715B (en) * | 2019-11-21 | 2021-07-20 | 浙江大华技术股份有限公司 | Method and system for identifying red light running of non-motor vehicle and violation processing platform |
| CN110930715A (en) * | 2019-11-21 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and system for identifying red light running of non-motor vehicle and violation processing platform |
| CN110929676A (en) * | 2019-12-04 | 2020-03-27 | 浙江工业大学 | Deep learning-based real-time detection method for illegal turning around |
| CN114761310A (en) * | 2019-12-05 | 2022-07-15 | 塞夫霍兰德有限公司 | System for checking operating state of component on vehicle and operating state checking method |
| CN111325988A (en) * | 2020-03-10 | 2020-06-23 | 北京以萨技术股份有限公司 | Real-time red light running detection method, device and system based on video and storage medium |
| CN111968378A (en) * | 2020-07-07 | 2020-11-20 | 浙江大华技术股份有限公司 | Motor vehicle red light running snapshot method and device, computer equipment and storage medium |
| CN112200148A (en) * | 2020-11-06 | 2021-01-08 | 中国计量大学 | Decentralized traffic integrity evaluation system |
| CN112200148B (en) * | 2020-11-06 | 2024-01-26 | 中国计量大学 | Decentralizing traffic integrity evaluation system |
| CN113870558A (en) * | 2021-09-26 | 2021-12-31 | 中国联合网络通信集团有限公司 | Vehicle detection method, vehicle detection device, vehicle, and traffic control device |
| CN115762173B (en) * | 2022-11-03 | 2023-08-22 | 湖北九州数字科技有限公司 | Traffic illegal behavior monitoring method and device based on three-dimensional road map |
| CN115762173A (en) * | 2022-11-03 | 2023-03-07 | 湖北九州数字科技有限公司 | Traffic violation monitoring method and device based on three-dimensional road map |
| CN117392621A (en) * | 2023-11-07 | 2024-01-12 | 西南交通大学 | Method and system for identifying behavior of motor vehicle in case of turning right without giving away pedestrians |
| CN117392621B (en) * | 2023-11-07 | 2024-06-07 | 西南交通大学 | Method and system for identifying behavior of motor vehicle in case of turning right without giving away pedestrians |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103065470B (en) | 2014-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103065470B (en) | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces | |
| CN102768801B (en) | Method for detecting motor vehicle green light follow-up traffic violation based on video | |
| CN110197589B (en) | Deep learning-based red light violation detection method | |
| CN101799987B (en) | Self-adaptive intelligent traffic light and control method thereof | |
| CN102496285B (en) | Method for determining red-light running of vehicles at intersection based on video detection and signal control system | |
| CN202584422U (en) | Apparatus for snapshotting vehicles violating traffic rules based on intelligent analysis and video monitoring | |
| CN100578562C (en) | Method for monitoring vehicle offences by video | |
| CN102129779B (en) | Monitoring system of safety and efficiency of traffic signal of intersection | |
| KR101671428B1 (en) | Intelligent Monitoring System For Violation Vehicles in crossroads | |
| CN104504896B (en) | A kind of traffic offence automatic production record and method | |
| CN202422425U (en) | Video-detection-based intelligent signal control system for crossing | |
| CN106327863A (en) | Method, device and system for detection and early warning of vehicle congestion | |
| CN201397576Y (en) | Device for automatically shooting picture of the illegal turning of vehicles at crossings | |
| CN102201165A (en) | Monitoring system of vehicle traffic violation at crossing and method thereof | |
| CN104157143B (en) | Parking offense detection system and detection method thereof | |
| CN104361753B (en) | Method and device for obtaining evidences of rule and regulation breaking of vehicles not running in alternating mode | |
| CN107240299A (en) | Autonomous land vehicle is to mobile object identification and the method for vehicle obstacle-avoidance | |
| CN204155450U (en) | High definition bayonet apparatus on a kind of road | |
| CN102768800A (en) | Motor vehicle red light running rule violation evidence obtaining method based on high-definition videos | |
| CN107123270A (en) | A kind of intelligent managing and control system in building site for slag-soil truck | |
| CN102298844A (en) | Automatic rule breaking vehicle detection system and method | |
| CN104134350A (en) | Intelligent dome camera system for traffic violation behavior recognition | |
| CN105046966A (en) | System and method for automatically detecting illegal parking behaviors in drop-off areas | |
| CN107393311B (en) | A kind of license plate tamper Detection device and method | |
| KR20160141226A (en) | System for inspecting vehicle in violation by intervention and the 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |