System and method of detection, tracking and identification of evolutionary adaptation of vehicle lamp

• US 9,898,672 B2
• Filed: 03/29/2016
• Issued: 02/20/2018
• Est. Priority Date: 02/02/2016
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Jen, Cheng-Lung, Chen, Yen-Lin, Yu, Chao-Wei, Li, Meng-Tsan, Tsai, Augustine
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US15/084,465
• Publication Number:
  US 20170220880A1
• Time in Patent Office: 693 Days
• CPC Class Codes: B60Q 9/00 Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00 , e.g. haptic signalling
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/251 involving models
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/422 for representing the structure of the pattern or shape of an object therefor
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 20/584 of vehicle lights or traffic lights
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

A system of detection, tracking and identification of an evolutionary adaptation of a vehicle lamp includes an image capture device and a processor. The image capture device captures an image of a vehicle. The processor processes the image of the vehicle to generate a detection result of the vehicle lamp, analyzes and integrates vehicle lamp dynamic motion information and vehicle lamp multiple scale variation information based on the detection result, and then tracks the position of the vehicle lamp by applying a multiple scale vehicle lamp measurement model.

Claims

1. A system of detection, tracking and identification of an evolutionary adaptation of a vehicle lamp, comprising:

an image capture device configured to capture an image of a vehicle; and

a processor programmed to;

process the image of the vehicle, so as to generate a detection result of the vehicle lamp; and

based on the detection result of the vehicle lamp, analyze and integrate vehicle lamp dynamic motion information and vehicle lamp multiple scale variation information, to track the position of the vehicle lamp of the vehicle by applying the multiple scale vehicle lamp measurement model.

2. The system of claim 1, wherein the vehicle lamp dynamic motion information comprises a center of the vehicle lamp, a moving speed of the vehicle lamp and a moving angle of the vehicle lamp, and the processor calculates a prediction mobility center of the vehicle lamp based on the center of the vehicle lamp, the moving speed of the vehicle lamp and the moving angle of the vehicle lamp.

3. The system of claim 2, wherein the vehicle lamp multiple scale variation information comprises a variance matrix of a previous sample of the vehicle lamp, the processor calculates an adaptive sampling range of an evolution sample according to the variance matrix and the moving speed of the vehicle lamp, so as to perform a sampling in the adaptive sampling range.

4. The system of claim 3, wherein the processor simulates and compares characteristics of the previous sample of the vehicle lamp in multi-scale spaces with characteristics of a current sample of the vehicle lamp in the multi-scale spaces to calculate the weighted characteristic differences and a similar weighting through a kernel function, and calculates the position of the vehicle lamp of the vehicle according to the similar weighting and the current sample of the vehicle lamp.

5. The system of claim 4, wherein the processor updates the variance matrix of an evolution sample after calculating the position of the vehicle lamp of the vehicle.

6. The system of claim 4, wherein a difference between the characteristics of the previous sample of the vehicle lamp in the multi-scale spaces with the characteristics of the current sample of the vehicle lamp in the multi-scale spaces comprises at least one of a center position difference, an average luminance difference, an average color difference, a lamp area difference and a three-dimensional color histogram difference.

7. The system of claim 1, further comprising:

a warning device electrically coupled with the processor, wherein when determining that the position of the vehicle lamp of the vehicle in a predetermined range, the processor commends the warning device to perform a warning action.

8. The system of claim 1, wherein the processor calculates a total difference of weighted characteristics according to a longitudinal vehicle distance of the vehicle and a relative angle between the image capture device and the vehicle so as to calculate a similarity through a kernel function calculate, and multiples the similarity and a original lamp color threshold together to get a updated lamp color threshold.

9. The system of claim 8, wherein the processor defines a longitudinal vehicle distance based on a distance between a vehicle center and a skyline in the image.

10. The system of claim 8, further comprising:

a warning device electrically coupled with the processor, wherein when determines that a color parameter of a third brake light of the vehicle exceeds an updated lamp color threshold by using the image of the vehicle, the processor commends the warning device to perform a warning action.

11. A method of detection, tracking and identification of an evolutionary adaptation of a vehicle lamp, comprising steps of:

(a) using an image capture device to capture an image of a vehicle;

(b) using a processor to process the image of the vehicle, so as to generate a detection result of the vehicle lamp; and

(c) using the processor to analyze and integrate vehicle lamp dynamic motion information and vehicle lamp multiple scale variation information based on the detection result of the vehicle lamp, so as to track the position of the vehicle lamp of the vehicle by applying the multiple scale vehicle lamp measurement model.

12. The method of claim 11, wherein the vehicle lamp dynamic motion information comprises a center of the vehicle lamp, a moving speed of the vehicle lamp and a moving angle of the vehicle lamp, and the step (c) comprises:

calculating a prediction mobility center of the vehicle lamp based on the center of the vehicle lamp, the moving speed of the vehicle lamp and the moving angle of the vehicle lamp.

13. The method of claim 12, wherein the vehicle lamp multiple scale variation information comprises a variance matrix of a previous sample the vehicle lamp, and the step (c) further comprises:

calculating an adaptive sampling range of an evolution sample according to the variance matrix and the moving speed of the vehicle lamp, so as to perform a sampling in the adaptive sampling range.

14. The method of claim 13, wherein the step (c) further comprises:

simulating and comparing characteristics of the previous sample of the vehicle lamp in multi-scale spaces with characteristics of a current sample of the vehicle lamp in the multi-scale spaces to calculate the weighted characteristic differences and a similar weighting through a kernel function, and calculating the position of the vehicle lamp of the vehicle according to the similar weighting and the current sample of the vehicle lamp.

15. The method of claim 14, wherein the step (c) further comprises:

updating the variance matrix of an evolution sample after calculating the position of the vehicle lamp of the vehicle.

16. The method of claim 14, wherein a difference between the characteristics of the previous sample of the vehicle lamp in the multi-scale spaces with the characteristics of the current sample of the vehicle lamp in the multi-scale spaces comprises at least one of a center position difference, an average luminance difference, an average color difference, a lamp area difference and a three-dimensional color histogram difference.

17. The method of claim 11, further comprising:

when determining that the position of the vehicle lamp of the vehicle in a predetermined range, commending a warning device to perform a warning action.

18. The method of claim 11, further comprising:

using the processor to calculate a total difference of weighted characteristics according to a longitudinal vehicle distance of the vehicle and a relative angle between the image capture device and the vehicle so as to calculate a similarity through a kernel function calculate, and to multiple the similarity and a original lamp color threshold together to get a updated lamp color threshold.

19. The method of claim 18, wherein the processor defines a longitudinal vehicle distance based on a distance between a vehicle center and a skyline in the image.

20. The method of claim 18, further comprising:

when determining that a color parameter of a third brake light of the vehicle exceeds an updated lamp color threshold by using the image of the vehicle, commending the warning device to perform a warning action.