Title :
Image analysis of crosswalk
Author :
Shioyama, Tadayoshi ; Wu, Haiyuan ; Nishibe, Yuna ; Nakamura, Naoki ; Kitawaki, Suguru
Author_Institution :
Dept. of Mech. & Syst. Eng., Kyoto Inst. of Technol., Japan
Abstract :
This paper proposes a method for image analysis of a crosswalk and a traffic light. The method provides information not only about the length of a crosswalk, but also about the colour of the traffic light. The length of a crosswalk is estimated by projective geometry using white lines painted on the road at a crosswalk. Furthermore, the state of the traffic light, that is, the colour of green (walk signal) or red (stop signal), is detected by searching the green (or red) traffic light using affine moment invariants. In order to evaluate the performance, experimental results estimating the length and detecting the traffic light are presented
Keywords :
computational geometry; edge detection; image colour analysis; traffic engineering computing; affine moment invariants; crosswalk estimation; edge detection; image analysis; performance; projective geometry; traffic light colour; white lines; Bicycles; Cameras; Image analysis; Image color analysis; Image edge detection; Intelligent robots; Intelligent sensors; Roads; Signal detection; Time of arrival estimation;
Conference_Titel :
Image Analysis and Processing, 2001. Proceedings. 11th International Conference on
Conference_Location :
Palermo
Print_ISBN :
0-7695-1183-X
DOI :
10.1109/ICIAP.2001.957003
