Optical Flow Based Real-time Moving Object Detection in Unconstrained Scenes

TL;DR

This paper presents a real-time moving object detection framework using optical flow and homography matrices, effectively handling dynamic backgrounds and scene variations, and outperforming existing methods.

Contribution

The proposed optical flow based framework introduces a dual-mode judgment mechanism and redefined evaluation metrics for improved detection in unconstrained scenes.

Findings

Outperforms state-of-the-art methods in various scene conditions

Adapts effectively to dynamic backgrounds and changing foregrounds

Validated through quantitative and qualitative experiments

Abstract

Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. In this paper, an optical flow based moving object detection framework is proposed to address this problem. We utilize homography matrixes to online construct a background model in the form of optical flow. When judging out moving foregrounds from scenes, a dual-mode judge mechanism is designed to heighten the system's adaptation to challenging situations. In experiment part, two evaluation metrics are redefined for more properly reflecting the performance of methods. We quantitatively and qualitatively validate the effectiveness and feasibility of our method with videos in various scene conditions. The experimental results show that our method adapts itself to different situations and outperforms the state-of-the-art methods, indicating the advantages of optical flow based methods.