Title :
Traffic indication symbols recognition with shape context
Author :
Kai Li ; Weiyao Lan
Author_Institution :
Dept. of Autom., Xiamen Univ., Xiamen, China
Abstract :
A novel traffic indication symbol detection and recognition method is introduced in this paper. We firstly apply color detection and shape detection on the real-time image to locate and extract the symbol region. Then the traffic indication sign is matched and recognized by using shape context. Experimental result demonstrates the proposed algorithm has good performance on recognition and more robustness to the disturbances.
Keywords :
edge detection; feature extraction; image colour analysis; image matching; shape recognition; traffic engineering computing; color detection; real-time image; shape detection; symbol region extraction; traffic indication sign matching; traffic indication symbol detection; traffic indication symbol recognition; Context; Educational institutions; Histograms; Image color analysis; Image edge detection; Shape; Transforms; HIS (Hue; Saturation and Intensity) color model; detection and recognition; shape context; traffic indication symbols;
Conference_Titel :
Computer Science & Education (ICCSE), 2011 6th International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-9717-1
DOI :
10.1109/ICCSE.2011.6028771