Unauthorized Parking Detection using Deep Networks at Real Time

Abstract

Although many public areas have installed CCTV to help monitor the traffic conditions, manually inspecting these videos to recognize unauthorized parking behaviors is extremely tedious and inefficient. In this paper, we propose a framework for automatic detection of illegally parked vehicle. The framework comprises two major components, namely object detection and movement tracking. To be more specific, we adopt one of the most prevalent object detection algorithm YOLO (v3) to detect vehicles and template matching methods using normalized cross correlation for movement tracking. Experiments show that the proposed method can achieve a very high accuracy and is robust to different camera angles, weather conditions and illuminations of the video.