A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

TLDR

Detection of moving objects in video streams is the first step in many computer vision applications, providing segmentation and focus for subsequent recognition, classification, and activity analysis. The study proposes a self‑organizing neural network approach for background subtraction in video surveillance. The method uses self‑organizing artificial neural networks to model background and is evaluated against other techniques on color video sequences for accuracy and speed. The approach robustly handles moving backgrounds, illumination changes, camouflage, and shadows, achieving high detection accuracy and fast processing compared to other techniques.

Abstract

Detection of moving objects in video streams is the first relevant step of information extraction in many computer vision applications. Aside from the intrinsic usefulness of being able to segment video streams into moving and background components, detecting moving objects provides a focus of attention for recognition, classification, and activity analysis, making these later steps more efficient. We propose an approach based on self organization through artificial neural networks, widely applied in human image processing systems and more generally in cognitive science. The proposed approach can handle scenes containing moving backgrounds, gradual illumination variations and camouflage, has no bootstrapping limitations, can include into the background model shadows cast by moving objects, and achieves robust detection for different types of videos taken with stationary cameras. We compare our method with other modeling techniques and report experimental results, both in terms of detection accuracy and in terms of processing speed, for color video sequences that represent typical situations critical for video surveillance systems.