• K. Kishore Anthuvan Sahayaraj
• Dr. K. Venkatachalapathy
• A. Sabitha
• S. Ramya
• S.Mehathaj Begam

Intelligent traffic surveillance system plays a vital role in modern day traffic analysis. Numerous ways have been developed to streamline the process of analyzing traffic. The counting and classification of the vehicle during some period of time in an area require more effort even the couple of proximity sensors can calculate the track of moving the vehicle, but they are not economical. Therefore this paper proposes a framework for vision-based moving vehicle counting and classification system by combining background subtraction, proposal generation network and iterative refinement Convolution Neural Network (CNN). These approaches are applied in a cascade way to obtain the classification and counting. The experiment results show that the proposed approach has the best classification accuracy on the MOT dataset.

background subtraction, faster RCNN, object detection,

"VEHICLE CLASSIFICATION BASED ON BACKGROUND SUBTRACTION WITH DEEP LEARNING IN TRAFFIC SCENE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.192-196, January-2019, Available :http://www.jetir.org/papers/JETIR1901A25.pdf

"VEHICLE CLASSIFICATION BASED ON BACKGROUND SUBTRACTION WITH DEEP LEARNING IN TRAFFIC SCENE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp192-196, January-2019, Available at : http://www.jetir.org/papers/JETIR1901A25.pdf