Automatically Identification and Classification of Moving Vehicles at Night

Todays moving object detection plays an important role in computer vision filed. Although a lot of moving objects detection methods has been proposed but monitoring at nights is still a challenging topic. In this paper, a robust algorithm is proposed for automatic detection moving vehicles at night or in environments with low level of light which has quality problems. In this algorithm, first preprocessing steps were conducted. Then all of vehicles in frame identify and classify according their type. Finally, the moving vehicles detected. The results demonstrate that the proposed algorithm significantly outperforms existing algorithm for the detecting and classification of moving vehicles at night.