Vehicles detection in complex urban traffic scenes using Gaussian mixture model with confidence measurement

• Published in: IET intelligent transport systems Vol. 10; no. 6; pp. 445 - 452
• Main Authors: Zhang, Yunsheng, Zhao, Chihang, He, Jie, Chen, Aiwei
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.08.2016
• Subjects: complex urban traffic scenes; Confidence; confidence measurement; Gaussian; Gaussian mixture model with confidence measurement; Gaussian processes; GMMCM; image processing; Intelligent transport systems; Learning; mixture models; Pixels; road traffic; road vehicles; subtraction background model; Traffic engineering; traffic engineering computing; Traffic flow; Vehicles; vehicles detection; visual background extractor; image processing; road traffic; complex urban traffic scenes; subtraction background model; traffic engineering computing; road vehicles; visual background extractor; Gaussian processes; vehicles detection; mixture models; Gaussian mixture model with confidence measurement; GMMCM; confidence measurement
• ISSN: 1751-956X; 1751-9578; 1751-9578
• DOI: 10.1049/iet-its.2015.0141

Aiming to efficiently resolve the problem that the subtraction background model is easily contaminated by slow-moving or temporarily stopped vehicles, the Gaussian mixture model with confidence measurement (GMMCM) is proposed for vehicle detection in complex urban traffic scenes. According to the current traffic state, each pixel of background model is set a CM. Whether to update the background model and the corresponding adaptive learning rate depends on if the current pixel point is in confidence period. Using the real-world urban traffic videos, the first experiments are conducted by GMMCM, compared with three commonly used models including GMM, self-adaptive GMM (SAGMM) and local parameter learning algorithm for the GMM (LPLGMM). The first experimental results show that GMMCM excels GMM, SAGMM and LPLGMM in keeping the background model being unpolluted from slow-moving or temporarily stopped vehicles. The second experiments are conducted by GMMCM, compared with visual background extractor, sigma-delta with CM, SAGMM, LPLGMM and GMM. The average recalls of six methods are 0.899, 0.753, 0.679, 0.420, 0.447 and 0.205, and the average F-measures of six methods are 0.636, 0.612, 0.592, 0.373, 0.330 and 0.179, respectively. All experimental results show the effectiveness of the proposed GMMCM in vehicles detection of complex urban traffic scenes.