Comparative Study of Background Subtraction Algorithm for Moving Object Detection using OpenCV

Abstract

The object detection involves detecting objects in images and videos using computer vision, image processing, and deep learning. OpenCV is a cross-platform library for developing real-time computer vision applications. In addition to image processing and video capture, it includes face and object detection features. This paper proposes a background subtraction algorithm for detecting moving objects. Video sequences are detected using background subtraction methods. Several parameters of the video sequence could complicate this process like noise, wind, rain, etc. This paper aims to compare the Background subtraction algorithm which is a Mixture Of Gaussians – MOG, K-Nearest Neighbour (KNN), CNT (COUNT), GMG, and MOG2 on the same data set.