A traffic flow estimation method based on unsupervised change detection

With the rapid development of intelligent transportation, the video surveillance system as its important component has been achieved much attention. Traffic condition closely related to people’s lives needs to be tracked in time. Some methods estimate traffic flow by analyzing the pictures taken by fixed cameras. However, they can only estimate the traffic condition of particular roads. Different from the traditional traffic flow estimation methods, the proposed method explores the video information rather than traffic images acquired by sensing remote-sensing sensors in this letter. More specifically, the highlights of our work include the following parts: first, change detection is performed on analyzing the difference between one frame image extracted from Unmanned Aerial Vehicle (UAV) videos and an updated background image for the sake of recognizing the whole profile of every moving object. Second, a modified fuzzy c-means method is engaged in the process of change detection, which segments the road regions to enhance the profiles of moving objects and eliminate the noise of complex backgrounds. Finally, the estimation of traffic flow can be achieved by analyzing the change detection result. Besides, the videos shot by UAV on a crossroad are used to analyze the effectiveness of the proposed method. Experimental results on a series of binary images and proportion illustrations demonstrate the promising performance of the proposed method in terms of human visual perception and segmentation accuracy.