Detection of Moving Vehicles Using ANN-Based Clustering of Optical Flow
International Journal of Advances in Mechanical & Automobile Engineering · 2017
This paper presents the detection of moving vehicles using clustering of optical flow.ANN (Artificial Neural Network) algorithms are employed to group pixels of moving vehicles from traffic images based on the clustering of optical flow.For the estimation of optical flow, the pyramidal Lucas-Kanade optical flow algorithm using our feature tracking system is then implemented.The information after estimating the optical flow can be used in the later tracking and detecting processes.To verify the efficiency of optical flow clustering, we use the Autonomous Agents for On-Scene Networked Incident Management (ATON) project's highway video files.Experimental results demonstrate good performance for the segmentation of moving vehicles.The study confirms that the proposed method can efficiently detect moving vehicles out of background and accurately estimate the velocity of moving vehicle.