End-to-End Deep Background Subtraction based on Encoder–Decoder Network

Background subtraction or change detection aims to segment the moving object from the background, and it has become a vital task in many video analysis and surveillance systems. There are different approaches were proposed to solve this problem effectively. In the past, all background subtraction methods use low-level handcraft features such as raw color space or local pattern. Recently, there are many background subtraction methods based on a convolutional neural network that have demonstrated astonishing results. Therefore, in this paper, we introduce an end-to-end convolutional neural network for background subtraction. The network is based on the idea of encoder-decoder deep neural network. In the encoder part, deep features from target frame and reference frame are extracted and compared to measure the difference. Then the decoder converts these features from an encoder to into segmentation map with fine detail. The experimental results tested on CDNet 2014 dataset show that the proposed structure archives the state-of-the-art performance.