A Deep Convolutional Neural Network for Background Subtraction
This work addresses the problem of automated video analysis for applications like surveillance by providing a more efficient and accurate background subtraction method, though it is incremental as it builds on existing CNN techniques.
The authors tackled background subtraction in video by developing a deep Convolutional Neural Network (CNN) that eliminates the need for feature engineering and parameter tuning, achieving real-time processing and outperforming existing algorithms in average ranking on datasets like CDnet 2014.
In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the network parameters can be learned from data by training a single CNN that can handle various video scenes. Additionally, we propose a new approach to estimate background model from video. For the training of the CNN, we employed randomly 5 percent video frames and their ground truth segmentations taken from the Change Detection challenge 2014(CDnet 2014). We also utilized spatial-median filtering as the post-processing of the network outputs. Our method is evaluated with different data-sets, and the network outperforms the existing algorithms with respect to the average ranking over different evaluation metrics. Furthermore, due to the network architecture, our CNN is capable of real time processing.