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

Volume

1

fYear

2012

Firstpage

261

Lastpage

263

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation & Measurement, Sensor Network and Automation (IMSNA), 2012 International Symposium on

Conference_Location

Sanya

Print_ISBN

978-1-4673-2465-6

Type

conf

DOI

10.1109/MSNA.2012.6324563

Filename

6324563