An improved wavelet feature extraction approach for vehicle detection

Feature extraction is a key point of pattern recognition. Wavelet features are attractive for vehicle detection because they form a compact representation, encode edges, capture information from multi-resolution, and can be computed efficiently. This paper concerns the improvement of wavelet features. Currently, the wavelet features directly based on signed coefficients are easily affected by the surroundings and illumination conditions and cause high intra-class variability. In order to deal with this problem, an improved wavelet feature extraction approach based on unsigned coefficients is proposed. Compare the proposed approach to current popular feature extraction methods using Support Vector Machine (SVM) for vehicle detection. The proposed approach shows super performance under various illuminations and different roads (different day time, different scenes: highway, urban common road, urban narrow road).