A vehicle detection approach based on multi-features fusion in the fisheye images

In a visual driver-assistance system, vehicle detection is one of the major tasks. This paper presents a vehicle detection method based on multi-features fusion in the images acquired by a fisheye camera. The vehicle detection algorithm can be divided into three main steps: fisheye image calibration, generation of candidates with respect to a vehicle and verification of the candidates. In the fist step, a fisheye image calibration algorithm based on cylinder model is proposed for reproducing virtual scene. The second step determines vehicle candidates using features such as the shadow, symmetry and vertical edge. A precise symmetry axis location approach is introduced by combining edge symmetry axis, grey-level symmetry axis and S-channel symmetry axis in HSV color space. Furthermore, a nighttime vehicle detection algorithm is designed by detecting the headlights. And the last step determines whether the candidate is a vehicle or not by using wavelet decomposition for feature extraction and the Support Vector Machines (SVMS) for classification. Experimental results in different conditions, including sunny, rainy, and nighttime demonstrates that most vehicles can be detected and recognized with a high accuracy and a frame rate of approximately 16 frames per second on a standard PC.