Occlusion vehicle detection algorithm in crowded scene for Traffic Surveillance System

Abstract

Traffic Surveillance System (TSS) plays an important role in extracting necessary information (count, type, speed, etc.). In the area of Traffic Surveillance System (TSS), vehicle detection has emerged as an influential field of study. So far there has been a considerable amount of research to accommodate this subject. However, these studies almost address problems in developed countries where the traffic infrastructure is constructed to appropriate automobiles. Detecting moving vehicles in urban areas is difficult because the inter-vehicle space is significantly reduced, increasing the occlusion between vehicles. This issue is more challenging in developing countries where the roads are crowded with 2-wheeled motorbikes in rush hours. This paper presents a method to improve the occlusion vehicle detection from static surveillance cameras. The proposed method is a vision-based approach in which undefined blobs of occluded vehicles are examined to extract the vehicles individually based on the geometric and the ellipticity characteristic of objects' shapes. Experiments have been carried out with the real-world data to evaluate the performance and the accuracy of our method. The assessment results are promising for a detection rate of 84.10% at daytime.