Back to Search Start Over

Vehicle window detection based on line features

Authors :
Hao Xiaoli
Yang Xing
Hou Dianfu
Source :
2012 International Symposium on Instrumentation & Measurement, Sensor Network and Automation (IMSNA).
Publication Year :
2012
Publisher :
IEEE, 2012.

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.

Details

Database :
OpenAIRE
Journal :
2012 International Symposium on Instrumentation & Measurement, Sensor Network and Automation (IMSNA)
Accession number :
edsair.doi...........1c2cd97ae9bd7aaf32ea0da01d77111f
Full Text :
https://doi.org/10.1109/msna.2012.6324563