Title :
Research on the location and recognition methods for traffic signs
Author :
Bo Zhao ; Feng, Zhang Tie
Author_Institution :
Chinese Acad. of Agric. Mechanization, Beijing, China
Abstract :
In order to insure safety of driving vehicle in the driver assistance system and effective navigation in the automatic driving system, a new location method based on image processing and a new recognition method based on the neural network and the invariant moments for traffic signs were proposed in this paper. Experimental results proved that the location method was fast and accurate. Traffic signs could be segmented from complicated background, and the recognition method can be used for fast and efficient recognition of the traffic signs with high accuracy. This research can provide technological supports to the autonomous vehicles and the vehicle safety driving assistance.
Keywords :
driver information systems; image recognition; image segmentation; neural nets; automatic driving system; autonomous vehicles; driver assistance system; image processing; image segmentation; neural network; traffic sign location; traffic sign recognition; vehicle safety driving assistance; Image processing; Image recognition; Image segmentation; Mobile robots; Navigation; Neural networks; Remotely operated vehicles; Telecommunication traffic; Vehicle driving; Vehicle safety; Invariant moments; Location; Neural network; Recognition; Traffic sign;
Conference_Titel :
Computational Intelligence and Industrial Applications, 2009. PACIIA 2009. Asia-Pacific Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4606-3
DOI :
10.1109/PACIIA.2009.5406397
