Robust background subtraction via online robust PCA using image decomposition
Sajid Javed, Seon Ho Oh, Jun-Hyeok Heo, Soon Ki Jung · 2014
Accurate and efficient background subtraction is an important task in video surveillance system. The task becomes more critical when the background scene shows more variations, such as water surface, waving trees and lighting conditions, etc. Recently, Robust Principal Components Analysis (RPCA) shows a nice framework for moving object detection. The background sequence is modeled by a low-dimensional subspace called low-rank matrix and sparse error constitutes the foreground objects. But RPCA presents the limitations of computational complexity and memory storage due to batch optimization methods, as a result it is hard to apply for real-time system. To handle these challenges, this paper presents a robust background subtraction algorithm via Online Robust PCA (OR-PCA) using image decomposition. OR-PCA with image decomposition approach improves the accuracy of foreground detection and the computation time as well. Comprehensive simulations on challenging datasets such as Wallflower, I2R and Change Detection 2014 demonstrate that our proposed scheme significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex background scenes.