Title :
Vision-Based Vehicle Detection System With Consideration of the Detecting Location
Author :
Minkyu Cheon ; Wonju Lee ; Changyong Yoon ; Mignon Park
Author_Institution :
Sch. of Electr. & Electron. Eng., Yonsei Univ., Seoul, South Korea
Abstract :
In this paper, we propose a vision-based vehicle detection system. We use a method composed of a hypothesis generation (HG) step and a hypothesis verification (HV) step, following the general approach to vision-based vehicle detection systems. In the HG step, the system extracts hypotheses using shadow regions that appear under vehicles. In the HV step, the system classifies feature vectors extracted from hypotheses to determine whether those hypotheses are vehicles. Along with the histogram of oriented gradients (HOG), we propose and implement a new type of feature vector, i.e., HOG symmetry vectors, in this paper. We also propose a new classification method that uses data importance in the HV step. The data importance value is based on the locations of hypotheses to prioritize hypotheses that have greater risks of accident. Experimental results show the strong performance of our proposed system.
Keywords :
computer vision; feature extraction; gradient methods; image classification; object detection; statistical analysis; traffic engineering computing; vectors; HG step; HOG; HOG symmetry vector; HV step; accident risk; data importance; detecting location consideration; feature vector classification; histogram-of-oriented gradient; hypothesis extraction; hypothesis generation step; hypothesis verification step; vision-based vehicle detection system; Feature extraction; Histograms; Real-time systems; Vectors; Vehicle detection; HOG symmetry; Histogram of oriented gradients (HOG); total error rate minimization with importance value; vehicle detection;
Journal_Title :
Intelligent Transportation Systems, IEEE Transactions on
DOI :
10.1109/TITS.2012.2188630