Multiscale Cascaded Scene-Specific Convolutional Neural Networks for Background Subtraction

Abstract

Recent years have witnessed the widespread success of convolutional neural networks (CNNs) in computer vision and multimedia. The CNNs based background subtraction methods, which are effective for addressing the challenges (such as shadows, dynamic backgrounds, illumination changes) existing in real-world applications, have attracted much attention. However, these methods usually require a large amount of densely labeled video training data, which are hardly collected in the real-world. To address this problem, in this paper, we propose a multiscale cascaded scene-specific CNNs based background subtraction method equipped with a novel training strategy, which takes advantage of the balance of positive and negative training samples. The proposed method can rely on a small number of training samples to effectively train the robust neural network models. Experimental results on the CDnet-2014 dataset show that the proposed method obtains better performance with much less training samples compared with the state-of-the-art methods.