Title :
Vehicle window detection based on line features
Author :
Xiaoli, Hao ; Dianfu, Hou ; Xing, Yang
Author_Institution :
Sch. of Electron. & Inf. Eng., Beijing Jiaotong Univ., Beijing, China
Abstract :
Quickly and accurately locating vehicle windows will greatly improve efficiency of occupant detection in High-occupancy vehicle (HOV) system. Based on the fact that vehicle´s windscreen has the geometric characteristics of line borders, a method involving frame difference, optimized edge detection and Hough transform to perform vehicle window detection is proposed. Experimental results have indicated that the proposed is effective for various vehicle type and color under different lighting conditions and backgrounds; and that its average executive time for each vehicle and success rate is 10~20ms and 95.4% respectively.
Keywords :
Hough transforms; edge detection; vehicles; Hough transform; frame difference; geometric characteristics; high-occupancy vehicle system; line borders; occupant detection; on line features; optimized edge detection; vehicle window detection; Computational efficiency; Feature extraction; Image color analysis; Image edge detection; Signal to noise ratio; Transforms; Vehicles; Hough transform; optimized edge detection; template filtering; vehicle window detection;
Conference_Titel :
Instrumentation & Measurement, Sensor Network and Automation (IMSNA), 2012 International Symposium on
Conference_Location :
Sanya
Print_ISBN :
978-1-4673-2465-6
DOI :
10.1109/MSNA.2012.6324563