Traffic Jam Detection Based on Corner Feature of Background Scene In Video-Based ITS

In recent years, traffic event detection has become an important topic in intelligent transportation systems. A novel method to extract jam events by analyzing the road background feature is developed in this research, in which the multiple background images have been used in order to extract ultimate background from low-speed vehicles in congestion condition. The proposed algorithm includes two stages: background extraction and jam detection. The background image was extracted by performing the difference on three consecutive frames. According to the extracted background image, we analyze the corner feature to detect traffic jam. The proposed method has been tested on a number of traffic-image sequences and the experimental results show that the algorithm is robust and realtime.