A vehicle detection method in tunnel video based on ViBe algorithm
Qiming Zhu, Ma Chengqian · 2017
A vehicle detection method in tunnel video is proposed based on ViBe (Visual Background Extractor) algorithm. The proposed method consists of three steps: firstly, histogram equalization is used to preprocessing the video aiming at improving the quality of the video images; secondly, the classic ViBe algorithm is adopted to model the background and detect the moving vehicles; finally, morphological filtering is applied to remove the noise pixels in the detection results. Experimental results on real tunnel video demonstrated that the proposed method can achieve better detection performance for moving vehicles than the classic ViBe algorithm.