Dual Camera-Based Supervised Foreground Detection for Low-End Video Surveillance Systems

Deep learning-based algorithms showed promising prospects in the computer vision domain. However, their deployment in real-time systems is challenging due to their computational complexity, high-end hardware prerequisites, and the amount of annotated data for training. This paper proposes an efficient foreground detection (EFDNet) algorithm based on deep spatial features extracted from an RGB input image using VGG-16 convolutional neural networks (CNN). The VGG-16 CNN is modified by concatenated residual (CR) blocks to learn better global contextual features and recover lost feature information due to several convolution operations. A new upsampling network is designed using bilinear interpolation sandwiched between 3 x 3 convolutions to upsample and refine feature maps for pixel-wise prediction. This helps to propagate loss errors from the upsampling network during backpropagation. The experiments showed the effectiveness of the EFDNet in outperforming top-ranked foreground detection algorithms. EFDNet trains faster on low-end hardware and demonstrated promising results with a minimum of 50 training frames with binary ground-truth.