Abstract | ||
---|---|---|
Many traffic accidents occurred at intersections are caused by drivers who miss or ignore the traffic signals. In this paper, we present a method dealing with automatic detection of traffic lights that integrates both image processing and support vector machine techniques. Firstly, based on the color characteristics of traffic lights, the paper proposes a method of traffic light segmentation in RGB and HSV color space. And then, according to the geometric features and backplane color information of traffic lights, we design an algorithm to remove false targets in images. Moreover, in order to solve traffic lights diffusion problem, we apply a strategy that we first map the candidate regions onto the original image, then using Otsu algorithm re-extract the target region. Finally, HOG features are extracted from the target regions, and recognized by the trained SVM classifier. Experimental results show that the proposed method has relatively high detection rate and recognition accuracy in different natural scenarios, and is able to meet real-time requirements. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/s11042-016-4051-5 | Multimedia Tools Appl. |
Keywords | Field | DocType |
Traffic lights,Color segmentation,Noise removal,Support vector machine | Computer vision,HSL and HSV,Feature fusion,Traffic signal,Pattern recognition,Backplane,Computer science,Segmentation,Support vector machine,Image processing,RGB color model,Artificial intelligence | Journal |
Volume | Issue | ISSN |
76 | 13 | 1380-7501 |
Citations | PageRank | References |
1 | 0.35 | 9 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenhao Wang | 1 | 60 | 10.80 |
Shanlin Sun | 2 | 1 | 0.35 |
Mingxin Jiang | 3 | 6 | 2.84 |
Yunyang Yan | 4 | 17 | 4.99 |
Xiaobing Chen | 5 | 1 | 1.03 |