Vehicle Detection, Tracking and Counting Using Gaussian Mixture Model and Optical Flow
Muhammad Moin Akhtar *
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China.
Yong Li
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China.
Lei Zhong
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China.
Ayesha Ansari
MCS, National University of Science and Technology, Pakistan.
*Author to whom correspondence should be addressed.
Abstract
Vehicle detection, tracking, and counting play a significant role in traffic surveillance and are principle applications of the Intelligent Transport System (ITS). Traffic congestion and accidents can be prevented with an adequate solution to problems. In this paper, we implemented different image processing techniques to detect and track the moving vehicle from the videos captured by a stationary camera and count the total number of vehicles passed by. The proposed approach consists of an optical flow method with a Gaussian mixture model (GMM) to obtain an absolute shape of particular moving objects which improves the detection performance of moving targets.
Keywords: GMM, vehicle detection, counting, optical flow, tracking