CN103116988A - Traffic flow and vehicle type detecting method based on TOF (time of flight) camera - Google Patents
Traffic flow and vehicle type detecting method based on TOF (time of flight) camera Download PDFInfo
- Publication number
- CN103116988A CN103116988A CN2013100277999A CN201310027799A CN103116988A CN 103116988 A CN103116988 A CN 103116988A CN 2013100277999 A CN2013100277999 A CN 2013100277999A CN 201310027799 A CN201310027799 A CN 201310027799A CN 103116988 A CN103116988 A CN 103116988A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detection zone
- virtual detection
- rectangle
- tof camera
- 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)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a traffic flow and vehicle type detecting method based on a TOF (time of flight) camera. A rectangular virtual detecting area is set by utilizing video images, acquired by the TOF camera, of a to-be-detected road surface. When a vehicle passes the virtual detecting area, distance arithmetic mean value in the virtual detecting area changes according to distance information provided by the TOF camera. Features of distance change are utilized to detect traffic flow. In the mean time, height of the vehicle can be obtained by utilizing the distance information provided by the TOF camera, and vehicle type can be detected by judging height contour of the vehicle.
Description
Technical field
The present invention relates to a kind of vehicle flowrate based on the TOF camera and vehicle detection method, belong to the intelligent transportation field of 3D vision.
Background technology
Along with rapid development of economy, urban transportation becomes focus and the difficult point of social common concern gradually, and intelligent transportation system (ITS) is arisen at the historic moment, and wherein vehicle Flow Detection is the key in this field.The transport information of having grasped the bases such as vehicle flowrate is control signal lamp and carry out various control measures on purpose.
The core of transport information is vehicle, vehicle detected and can directly obtain vehicle flowrate, and then obtain vehicle information.Vehicle checking method mainly contains at present: ground induction coil, Ultrasonic Detection, infrared detection, FCD (Floating Car) technology and video detect.The video detection method has than other detection technique the Installation and Debugging of being convenient to, and road pavement can not produce destruction; Small investment, expense are low; High quality traffic roads image when detecting traffic flow parameter is convenient to the characteristics such as monitoring, thereby is widely used.
Vehicle checking method based on video commonly used mainly contains: gray level method, neighbor frame difference method, edge detection method.Gray level method adopts the gray-scale statistical value of road surface and vehicle to detect vehicle, but it is very responsive to the variation of light; The neighbor frame difference method is to subtract each other facing mutually two frames, moving vehicle information is detected, but can not effectively detect the excessively slow vehicle of car speed; Edge detection method can detect the edge of vehicle under different light condition, but road edge obviously, pavement marker exists or the unconspicuous situation of vehicle edge under, may cause undetected, flase drop; The background subtraction method is calculated the difference of current incoming frame and background, but reliable background need to be arranged.
The main method that vehicle detects has: based on the Automotive Style Recognition of feature, based on the vehicle classification of support vector machine, based on the identification of the automotive type of neural network etc.Automotive Style Recognition based on feature is to utilize the feature detection vehicle that detects vehicle, but the precision that detects is lower, identification error easily occurs; Based on the vehicle classification of support vector machine be by complicated training process such as neural networks based on the identification of the automotive type of neural network, recycling neural network, KERNEL FUNCTION METHOD etc. are carried out Classification and Identification, and precision is higher, but expends time in.
Summary of the invention
The present invention is for avoiding the existing deficiency of above-mentioned prior art, a kind of vehicle flowrate based on the TOF camera and vehicle detection method are provided, to overcome the factors such as illumination variation, car speed to the impact that vehicle Flow Detection produces, detect fast and exactly vehicle flowrate; Directly utilize the altitude feature of vehicle different parts, differentiate roughly vehicle, rapidly vehicle is classified.
Technical solution problem of the present invention adopts following technical scheme:
The present invention is based on the vehicle flowrate of TOF camera and the characteristics of vehicle detection method is to utilize the TOF camera that tested road surface is taken, and the video image on Real-time Obtaining tested road surface arranges a rectangle virtual detection zone on the track in video image; When vehicle was arranged through described rectangle virtual detection zone, the range information in described rectangle virtual detection zone changed, and whether surpassed on the threshold decision track of setting whether have vehicle according to the variable quantity of described range information, realized vehicle Flow Detection; When vehicle is arranged through described rectangle virtual detection zone, try to achieve according to the range information in rectangle virtual detection zone the true altitude that vehicle is arranged in rectangle virtual detection zone, utilize vehicle through the continuous multiple frames image in described rectangle virtual detection zone, obtain the height that vehicle comprises the different parts of headstock, compartment and the tailstock, utilize described height profile feature to realize that vehicle detects.
The present invention is based on the vehicle flowrate of TOF camera and the characteristics of vehicle detection method also is to carry out as follows:
Step 1, with the TOF camera be arranged on apart from tested road surface vertical range be d directly over, the TOF camera lens is perpendicular to the road surface down;
Step 2, utilize the TOF camera to take in real time tested road surface, obtain the video image on tested road surface, a rectangle virtual detection is set regional in video image, described rectangle virtual detection zone is positioned at the image medium position, its length direction is perpendicular to vehicle heading, and the length in described rectangle virtual detection zone is the pixel wide of track in video image, and the width in rectangle virtual detection zone is p pixel, based on noise and accuracy factor, the numerical value of choosing described p is 3 ~ 5;
The detection of step 3, vehicle flowrate:
The arithmetic mean of the range information in a, calculating current frame image in rectangle virtual detection zone
Order
Setpoint distance threshold value d
thr
If in the b current frame image, without the vehicle process, Δ d is 0; If Δ d by 0 sudden change to greater than distance threshold d
thr, being judged as vehicle and having entered the virtual detection zone, vehicle count adds 1; If Δ d does not satisfy by 0 sudden change to greater than distance threshold d
thr, being judged as without vehicle and entering virtual detection zone or the vehicle counted does not also leave the virtual detection zone, vehicle count remains unchanged;
Step 4, vehicle detect:
A, in the n two field picture, vehicle X enters rectangle virtual detection zone, is that the rectangle virtual detection of p pixel is regional for width, calculate every row pixel apart from arithmetic mean
Find out the minimum value apart from arithmetic mean
Assert minimum value
Be positioned at the top of vehicle sections in rectangle virtual detection zone for vehicle X to the distance of camera, obtain the true altitude h that vehicle X in the n two field picture is positioned at rectangle virtual detection zone
n=d-d
Min, n
B, in the n+m two field picture, another vehicle Y enters rectangle virtual detection zone, obtains m altitude feature from vehicle X from n two field picture to the n+m-1 two field picture, formation m dimensional vector
Wherein " 0 " characterizes vehicle and leaves the virtual detection zone, cuts out described m dimensional vector
In be 0 afterbody continuously, obtain the altitude feature vector of vehicle X from headstock to the tailstock
C, the vector of the altitude feature with described vehicle X from headstock to the tailstock
Mate with height of car feature dissimilar in the database of having set up, realize the vehicle of vehicle X is detected.
The present invention is based on the vehicle flowrate of TOF camera and the characteristics of vehicle detection method also is:
Choose at random W vehicle X
1, X
2... X
wBe the reference vehicle, utilize the described method of step 4, calculate the altitude feature vector of W vehicle
According to the altitude feature vector, determine the maximum height h of each car
Max1, h
Max1..., h
Maxn, find out the shortest h of height of car in W vehicle
min, setpoint distance threshold value d
thrBe 1/5 ~ 1/3h
minBased on the factor of accuracy, the W that a chooses vehicle comprises various types of vehicles, and the W value should get higher value, sets the W value and is not less than 100.
Compared with prior art, beneficial effect of the present invention is embodied in:
1, the TOF camera that adopts of the present invention is by recording the two-way time of light in the space, obtaining the three-dimensional information of scene.The characteristics such as the computation process that not characteristics of needs extraction, rim detection and renewal background etc. are complicated has speed fast, and calculated amount is little.
2, the present invention adopts the range information that the TOF camera obtains to carry out vehicle Flow Detection, thereby can overcome shade that the ordinary video detection method is subject to vehicle, blocks and car speed etc. causes flase drop, undetected problem, has the high characteristics of precision.
3, the present invention adopts the range information that the TOF camera obtains to carry out the vehicle detection, do not need to obtain as the complicated feature such as vehicle area, vehicle width, straight length, profile, also not needing expends time in carries out sample training, only utilize this feature of height of vehicle to carry out the vehicle detection, have simple, the easy characteristics that realize of algorithm.
4, the TOF camera of the present invention's employing is a kind of active vision sensor, includes an initiatively modulated light source, is not subjected to the restriction of extraneous illumination condition during measurement, and testing environment can be daytime or night.
Description of drawings
The measuring system figure of Fig. 1 the inventive method;
The video image schematic diagram that Fig. 2 TOF camera obtains;
Fig. 3 different automobile types height of car changes schematic diagram.
Number in the figure: 1 camera support; 2 is the TOF camera; 3 is PC; 4 tested vehicles; 5 tracks; 6 rectangle virtual detection are regional; 7 lorries; 8 passenger vehicles; 9 minibuses; 10 cars.
Specific implementation method
Referring to Fig. 1, the system of the present embodiment formation comprises by camera support 1, is fixedly mounted on the TOF camera 2 on camera support 1, PC 3 and the tested vehicle 4 that is used for carrying out the image processing.
Vehicle flowrate and vehicle detection method based on the TOF camera in the present embodiment are to carry out according to the following steps:
Step 1, referring to Fig. 1, utilize camera support 1 that TOF camera 2 is arranged on apart from tested road surface vertical range as directly over d, the TOF camera lens perpendicular to the road surface down, because TOF camera optimum measurement distance range is 0.3m-7m, in the present embodiment, d gets 6m;
Step 2, utilize the TOF camera to take in real time tested road surface, obtain the video image on tested road surface, referring to Fig. 2, a rectangle virtual detection zone 6 is set in video image, and rectangle virtual detection zone is positioned at the image medium position, and its length direction is perpendicular to the travel direction of tested vehicle 4, the length in rectangle virtual detection zone is the pixel wide of track 5 in video image, the width in rectangle virtual detection zone is p pixel, and based on noise and accuracy factor, the numerical value of choosing p is 3 ~ 5; In the present embodiment, p gets 4;
The detection of step 3, vehicle flowrate:
The arithmetic mean of the range information in a, calculating current frame image in rectangle virtual detection zone
Order
Setpoint distance threshold value d
thr
If in the b current frame image, without the vehicle process, Δ d is 0; If Δ d by 0 sudden change to greater than distance threshold d
thr, being judged as vehicle and having entered the virtual detection zone, vehicle count adds 1; If Δ d does not satisfy by 0 sudden change to greater than distance threshold d
thr, being judged as without vehicle and entering virtual detection zone or the vehicle counted does not also leave the virtual detection zone, vehicle count remains unchanged;
Step 4, vehicle detect:
A, in the n two field picture, vehicle X enters rectangle virtual detection zone, is that the rectangle virtual detection of p pixel is regional for width, calculate every row pixel apart from arithmetic mean
Find out the minimum value apart from arithmetic mean
Assert minimum value
Be positioned at the top of vehicle sections in rectangle virtual detection zone for vehicle X to the distance of camera, obtain the true altitude h that vehicle X in the n two field picture is positioned at rectangle virtual detection zone
n=d-d
Min, n
B, in the n+m two field picture, another vehicle Y enters rectangle virtual detection zone, obtains m altitude feature from vehicle X from n two field picture to the n+m-1 two field picture, formation m dimensional vector
Wherein " 0 " characterizes vehicle and leaves the virtual detection zone, cuts out the m dimensional vector
In be 0 afterbody continuously, obtain the altitude feature vector of vehicle X from headstock to the tailstock
C, the vector of the altitude feature with vehicle X from headstock to the tailstock
Mate with vehicle (referring to Fig. 3) altitude feature dissimilar in the database of having set up, realize the vehicle of vehicle X is detected.
D in above-mentioned steps 3
thrEstablishing method: choose at random W vehicle X
1, X
2... X
wBe the reference vehicle, utilize step 4 method, calculate the altitude feature vector of W vehicle
According to the altitude feature vector, determine the maximum height h of each car
Max1, h
Max1..., h
Maxn, find out the shortest h of height of car in W vehicle
minVehicle detected, distance threshold d
thrBe less than h
min, consider that vehicle enters virtual detection and just vehicle can be detected, distance threshold d
thrAs far as possible little, but consider vehicle detection accurately, distance threshold d
thrLarge as far as possible, the precision of the range data of TOF camera is 0.1m, setpoint distance threshold value d
thrBe 1/5 ~ 1/3h
min, in the present embodiment, get d
thr=1/3h
min
Above-mentioned d
thrEstablishing method in the value of W, based on the factor of generality and accuracy, the W that a chooses vehicle should comprise various types of vehicles, such as comprising the lorry 7 shown in Fig. 3, passenger vehicle 8, minibus 9 and car 10 etc., and the W value is large as far as possible, in the present embodiment, gets W=100.
Claims (3)
1. vehicle flowrate and vehicle detection method based on a TOF camera, is characterized in that utilizing the TOF camera that tested road surface is taken, and the video image on Real-time Obtaining tested road surface arranges a rectangle virtual detection zone on the track in video image; When vehicle was arranged through described rectangle virtual detection zone, the range information in described rectangle virtual detection zone changed, and whether surpassed on the threshold decision track of setting whether have vehicle according to the variable quantity of described range information, realized vehicle Flow Detection; When vehicle is arranged through described rectangle virtual detection zone, try to achieve according to the range information in rectangle virtual detection zone the true altitude that vehicle is arranged in rectangle virtual detection zone, utilize vehicle through the continuous multiple frames image in described rectangle virtual detection zone, obtain the height that vehicle comprises the different parts of headstock, compartment and the tailstock, utilize described height profile feature to realize that vehicle detects.
2. vehicle flowrate and vehicle detection method based on the TOF camera according to claim 1 is characterized in that carrying out as follows:
Step 1, with the TOF camera be arranged on apart from tested road surface vertical range be d directly over, the TOF camera lens is perpendicular to the road surface down;
Step 2, utilize the TOF camera to take in real time tested road surface, obtain the video image on tested road surface, a rectangle virtual detection is set regional in video image, described rectangle virtual detection zone is positioned at the image medium position, its length direction is perpendicular to vehicle heading, and the length in described rectangle virtual detection zone is the pixel wide of track in video image, and the width in rectangle virtual detection zone is p pixel, based on noise and accuracy factor, the numerical value of choosing described p is 3 ~ 5;
The detection of step 3, vehicle flowrate:
The arithmetic mean of the range information in a, calculating current frame image in rectangle virtual detection zone
Order
Setpoint distance threshold value d
thr
If in the b current frame image, without the vehicle process, Δ d is 0; If Δ d by 0 sudden change to greater than distance threshold d
thr, being judged as vehicle and having entered the virtual detection zone, vehicle count adds 1; If Δ d does not satisfy by 0 sudden change to greater than distance threshold d
thr, being judged as without vehicle and entering virtual detection zone or the vehicle counted does not also leave the virtual detection zone, vehicle count remains unchanged;
Step 4, vehicle detect:
A, in the n two field picture, vehicle X enters rectangle virtual detection zone, is that the rectangle virtual detection of p pixel is regional for width, calculate every row pixel apart from arithmetic mean
Find out the minimum value apart from arithmetic mean
Assert minimum value
Be positioned at the top of vehicle sections in rectangle virtual detection zone for vehicle X to the distance of camera, obtain the true altitude h that vehicle X in the n two field picture is positioned at rectangle virtual detection zone
n=d-d
Min, n
B, in the n+m two field picture, another vehicle Y enters rectangle virtual detection zone, obtains m altitude feature from vehicle X from n two field picture to the n+m-1 two field picture, formation m dimensional vector
Wherein " 0 " characterizes vehicle and leaves the virtual detection zone, cuts out described m dimensional vector
In be 0 afterbody continuously, obtain the altitude feature vector of vehicle X from headstock to the tailstock
3. vehicle flowrate and vehicle detection method based on the TOF camera according to claim 2 is characterized in that:
Choose at random W vehicle X
1, X
2... X
wBe the reference vehicle, utilize the described method of step 4, calculate the altitude feature vector of W vehicle
According to the altitude feature vector, determine the maximum height h of each car
Max1, h
Max1..., h
Maxn, find out the shortest h of height of car in W vehicle
min, setpoint distance threshold value d
thrBe 1/5 ~ 1/3h
minBased on the factor of accuracy, the W that a chooses vehicle comprises various types of vehicles, and the W value should get higher value, sets the W value and is not less than 100.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310027799.9A CN103116988B (en) | 2013-01-18 | 2013-01-18 | Traffic flow and vehicle type detecting method based on TOF (time of flight) camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310027799.9A CN103116988B (en) | 2013-01-18 | 2013-01-18 | Traffic flow and vehicle type detecting method based on TOF (time of flight) camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103116988A true CN103116988A (en) | 2013-05-22 |
CN103116988B CN103116988B (en) | 2014-10-08 |
Family
ID=48415350
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310027799.9A Expired - Fee Related CN103116988B (en) | 2013-01-18 | 2013-01-18 | Traffic flow and vehicle type detecting method based on TOF (time of flight) camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103116988B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105320710A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Illumination variation resistant vehicle retrieval method and device |
CN105848382A (en) * | 2016-03-29 | 2016-08-10 | 广东恒润光电有限公司 | Lamp control method based on pedestrian volume and system thereof |
CN107767407A (en) * | 2016-08-16 | 2018-03-06 | 北京万集科技股份有限公司 | A kind of road vehicle Objective extraction system and method based on TOF camera |
CN107808525A (en) * | 2017-12-07 | 2018-03-16 | 东莞职业技术学院 | A kind of road monitoring system based on Internet of Things |
CN108399753A (en) * | 2018-03-01 | 2018-08-14 | 山东建筑大学 | Vehicle tracing method and system based on ultrasonic wave wave-record chart |
CN110111582A (en) * | 2019-05-27 | 2019-08-09 | 武汉万集信息技术有限公司 | Multilane free-flow vehicle detection method and system based on TOF camera |
CN110706491A (en) * | 2019-11-05 | 2020-01-17 | 北京深测科技有限公司 | Traffic monitoring and early warning method and system for expressway |
CN110942631A (en) * | 2019-12-02 | 2020-03-31 | 北京深测科技有限公司 | Traffic signal control method based on flight time camera |
US20200391761A1 (en) * | 2019-06-13 | 2020-12-17 | Board Of Supervisors Of Louisiana State University And Agricultural And Mechanical College | Overheight vehicles impact avoidance and incident detection system |
CN113777616A (en) * | 2021-07-27 | 2021-12-10 | 武汉市异方体科技有限公司 | Distance measuring method for moving vehicle |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201051310Y (en) * | 2007-06-21 | 2008-04-23 | 南京理工大学 | Millimeter wave and ultrasonic wave dual frequency traffic parameter detector with car type recognition function |
CN101615342A (en) * | 2008-06-27 | 2009-12-30 | 青岛海信电子产业控股股份有限公司 | A kind of vehicle checking method |
EP2306426A1 (en) * | 2009-10-01 | 2011-04-06 | Kapsch TrafficCom AG | Device for detecting vehicles on a traffic surface |
-
2013
- 2013-01-18 CN CN201310027799.9A patent/CN103116988B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201051310Y (en) * | 2007-06-21 | 2008-04-23 | 南京理工大学 | Millimeter wave and ultrasonic wave dual frequency traffic parameter detector with car type recognition function |
CN101615342A (en) * | 2008-06-27 | 2009-12-30 | 青岛海信电子产业控股股份有限公司 | A kind of vehicle checking method |
EP2306426A1 (en) * | 2009-10-01 | 2011-04-06 | Kapsch TrafficCom AG | Device for detecting vehicles on a traffic surface |
Non-Patent Citations (2)
Title |
---|
丁津津等: "基于TOF技术的3D相机应用研究综述", 《仪器仪表学报》 * |
陈隽: "复杂表面物体3D模型的获取方法", 《微计算机应用》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105320710A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Illumination variation resistant vehicle retrieval method and device |
CN105320710B (en) * | 2014-08-05 | 2018-11-27 | 北京大学 | The vehicle retrieval method and device of resisting illumination variation |
CN105848382B (en) * | 2016-03-29 | 2019-01-25 | 广东恒润光电有限公司 | Lamp prosecutor method and its system based on flow of the people |
CN105848382A (en) * | 2016-03-29 | 2016-08-10 | 广东恒润光电有限公司 | Lamp control method based on pedestrian volume and system thereof |
CN107767407A (en) * | 2016-08-16 | 2018-03-06 | 北京万集科技股份有限公司 | A kind of road vehicle Objective extraction system and method based on TOF camera |
CN107767407B (en) * | 2016-08-16 | 2020-09-22 | 北京万集科技股份有限公司 | Road vehicle target extraction system and method based on TOF camera |
CN107808525A (en) * | 2017-12-07 | 2018-03-16 | 东莞职业技术学院 | A kind of road monitoring system based on Internet of Things |
CN108399753A (en) * | 2018-03-01 | 2018-08-14 | 山东建筑大学 | Vehicle tracing method and system based on ultrasonic wave wave-record chart |
CN110111582A (en) * | 2019-05-27 | 2019-08-09 | 武汉万集信息技术有限公司 | Multilane free-flow vehicle detection method and system based on TOF camera |
US20200391761A1 (en) * | 2019-06-13 | 2020-12-17 | Board Of Supervisors Of Louisiana State University And Agricultural And Mechanical College | Overheight vehicles impact avoidance and incident detection system |
CN110706491A (en) * | 2019-11-05 | 2020-01-17 | 北京深测科技有限公司 | Traffic monitoring and early warning method and system for expressway |
CN110942631A (en) * | 2019-12-02 | 2020-03-31 | 北京深测科技有限公司 | Traffic signal control method based on flight time camera |
CN113777616A (en) * | 2021-07-27 | 2021-12-10 | 武汉市异方体科技有限公司 | Distance measuring method for moving vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN103116988B (en) | 2014-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103116988B (en) | Traffic flow and vehicle type detecting method based on TOF (time of flight) camera | |
US9064418B2 (en) | Vehicle-mounted environment recognition apparatus and vehicle-mounted environment recognition system | |
CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
CN105374212B (en) | The vehicle on highway lane recognition method and system sensed based on intelligent terminal | |
CN103395391B (en) | A kind of vehicle lane-changing alarming device and change state identification method | |
CN104011737B (en) | Method for detecting mist | |
CN103593649A (en) | Lane line detection method for lane departure early warning | |
KR101613667B1 (en) | Apparatus for classifyng vehicle type using -dimensional image camera | |
CN111016903B (en) | System and method for guaranteeing driving safety of automatic driving vehicle in rainy days | |
CN101223416A (en) | Object detection device | |
CN107957259B (en) | Wheelmark cross direction profiles measuring system and measurement method | |
US8718329B2 (en) | Top-down view classification in clear path detection | |
KR20140109990A (en) | Determining a vertical profile of a vehicle environment by means of a 3d camera | |
CN112304633B (en) | Method for identifying automobile braking safety risk in wet and slippery road surface state | |
CN102254161A (en) | Road surface type recognition method and device based on road surface outline and road surface image characteristics | |
CN114572183A (en) | Automobile pavement self-adaptive vehicle control method and equipment | |
CN103577809A (en) | Ground traffic sign real-time detection method based on intelligent driving | |
Díaz et al. | Extended floating car data system: Experimental results and application for a hybrid route level of service | |
CN102927964B (en) | Distance-measuring device, method and vehicle | |
CN107037467B (en) | Positioning system and method and intelligent automobile | |
KR20180075985A (en) | Apparatus for autonomous steering prediction considering driving environment and method thereof | |
RU2722465C1 (en) | Vehicle tire recognition device and method | |
CN106355152A (en) | Method and system for identifying current road vehicles as well as car video recorder | |
Srimongkon et al. | Detection of speed bumps using Gaussian mixture model | |
CN116587978A (en) | Collision early warning method and system based on vehicle-mounted display screen |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141008 Termination date: 20170118 |
|
CF01 | Termination of patent right due to non-payment of annual fee |