Real-time nighttime vehicle detection and recognition system based on computer vision

• US 20070263901A1
• Filed: 08/07/2006
• Published: 11/15/2007
• Est. Priority Date: 05/12/2006
• Status: Active Grant

• Current Assignee: CSSP Incorporated
• Original Assignee: National Chiao Tung University (Government of The Republic of China)
• Inventors: Chen, Yen-Lin, Chen, Chao-Jung, Wu, Bing-Fei, Chen, Yuan-Hsin
• Granted Patent: US 7,949,190 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights

Abstract

The present invention relates to a real time night time vehicle detection and identification system comprising of an illuminant object image segmentation device 1, an illuminant object classifying device 2, a vehicle lighting object identification device 3, a vehicle position determining device 4 and a vehicle tracking device 5. Under various circumstances of road lighting during nighttime, the system can efficiently and accurately demarcate and identify the lamps of incoming and preceding vehicles and accurately provides the driver with auxiliary information needed to analyze the traffic conditions in front of the vehicle during the conditions met on the road at that time.

Claims

1. A system for real time night time vehicle detection and identification, which includes:

An illuminant object image segmentation device, for carrying out illuminant object segmentation on the retrieved image of illuminant object;

An illuminant object classification device, relying on a connected object demarcation unit, classification procedure is carried out on the illuminant object which is to be segmented, so as to carry out a generalization on the characteristics correlation amongst each illuminant object and thus becomes each illuminant object groups;

A vehicle lighting object identification device, for gaining characteristic information of each vehicle from the illuminant object groups, which is to be generalized, relying on a pattern analyzing unit;

A vehicle position determining device, for gaining position information between each vehicle that appears ahead on the road and the vehicle in concern from the characteristic information, utilizing a distance estimation unit; and

A vehicle tracking device, after gaining the demarcated illuminant object groups from the position information, targeting at the vehicle lighting groups demarcated at each continued image frame, to detect the direction it is heading, so as to decide the movement information of each vehicle that enters the area under surveillance, and correspondingly operates the relative device and equipment.

2. According to the system of claim 1 wherein the position information includes detection of distance of target vehicle from the lane and its relative positions et cetera.

3. According to the system of claim 1 wherein the movement information includes corresponding direction of motion and relative velocity of each vehicles et cetera.

4. According to the system of claim 1 wherein it further includes an automatic control mechanism, using the position information and the movement information, to adopt a correct corresponding operation on vehicle cruise velocity and drive route.

5. According to the system of claim 1 wherein the connected object demarcation unit is used in the demarcation of each illuminant object and analyzing and comparing the characteristics of projection analysis, object size, ratio, and distance.

6. According to the system of claim 1 wherein the pattern analyzing unit is targeted at the demarcated illuminant object group, to identify whether it has characteristics of vehicle and vehicle lighting, in the process as well identit˜

y it out as vehicle head light or vehicle tail lamp.

7. According to the system of claim 1 wherein the distance estimation unit is based on perspective image modeling, using estimated detection of corresponding distance of depth of field of target vehicle on the imaginary and real coordinate axes system at a particular timeline, and using the corresponding relation between coordinate position of image element and distance of depth of field of the target vehicle in the image, to derive the relative space position between it and the vehicle in concern on the lane.

8. According to the real time night time vehicle detection and identification system of claim number 7 wherein the relative space position includes distance of depth of field, position of left-hand edge and position of right-hand edge et cetera.

9. According to the real time night time vehicle detection and identification system of claim number 1 wherein the related device and equipment is the switch controller of high beam and low beam of the vehicle'"'"'s head light.

10. A method of real time detection and identification of night time vehicle includes:

Step of illuminant object image segmentation, carrying out illuminant object segmentation on the retrieved image of illuminant object;

Step of Illuminant object classification, relying on a connected object demarcation unit, classification procedure is carried out on the illuminant object which is to be segmented, so as to carry out a generalization on the characteristics correlation amongst each illuminant object and thus becomes each illuminant object groups;

Step of vehicle lighting object identification, gaining characteristic information of each vehicle from the illuminant object groups to be generalized, relying on a pattern analyzing unit;

Step of vehicle position determination, gaining position information between each vehicle that appears ahead on the road and the vehicle in concern from the characteristic information, utilizing a distance estimation unit; and

Step of vehicle tracking, after gaining the demarcated illuminant object groups from the position information, targeting at the vehicle lighting groups demarcated at each continued image frame, to detect the direction it is heading, so as to decide the movement information of every one vehicle that enters the area under surveillance, and correspondingly operates the relative device and equipment.

11. According to the method of claim 10 wherein the position information includes detection of distance of target vehicle from the lane and its corresponding positions et cetera.

12. According to the method of claim 10 wherein the movement information includes corresponding direction of motion and corresponding velocity of various vehicles et cetera.

13. According to the method of claim 10 wherein it further includes an automatic control mechanism, permitting the use of the position information and the movement information, to adopt a correct corresponding operation on vehicle cruise velocity and drive route.

14. According to the method of real time detection and identification of night time vehicle of claim number 10 wherein the connected object demarcation unit is used in the demarcation of each illuminant object projection and analyzing and comparing the characteristics of projection analysis, object size, ratio, and distance.

15. According to the method of claim 10 wherein the related device and equipment is the switch controller of high beam and low beam of the vehicle'"'"'s head light.

16. According to the method of claim 10 wherein the distance estimation unit is based on perspective image modeling, using estimated detection of corresponding distance of depth of field of target vehicle on the imaginary and real coordinate axes system at a particular timeline, and using the corresponding relation between coordinate position of image element and distance of depth of field of the target vehicle in the image, to derive the relative space position between it and the vehicle in concern on the lane.

17. According to the method of claim 10 wherein the relative space position includes distance of depth of field, position of left-hand edge and position of right-hand edge et cetera.

18. According to the method of claim 10 wherein the pattern analyzing unit is targeted at the demarcated illuminant object group, to identify whether it has characteristics of vehicle and vehicle lighting, in the process as well identify it out as vehicle head light or vehicle tail lamp.