Vehicles Detection and Counting Method from Overhead View based on Embedded Vision

In modern society, vehicles are indispensable carriers in transportation and daily life. The rapid increase in the number of vehicles has contributed to the development of intelligent traffic monitoring. Vehicle counting allows for a quick understanding of the traffic flow on the road and the parking situation in the parking lot. This enables the management of traffic. In recent years, vehicle counting techniques which is based on image processing have been innovated. However, there are still challenges to effectively utilize image processing methods for vehicle counting. In this paper, an efficient vehicle counting algorithm using ORB algorithm and Sliding Window Method is proposed. To be able to improve the efficiency of vehicle detection, the Frame Difference Method is used to detect whether there are moving objects. Based on the results of vehicle counting on the parking lot video. The method is able to efficiently and accurately identify the number of vehicles in a parking lot. And it can be deployed to small embedded devices.