LCNNet: Light-weight convolutional neural networks for understanding the highly congested scenes

With the development of convolutional neural networks, many improved algorithms have been successively proposed to promote the accuracy of dense crowd counting. However, these algorithms are deployed with expensive computing resources, which is unbearable for small devices such as embedded systems with limited computing resources. To realize the real-time counting on the small devices, it is of great significance how to trade off the computation cost and processing accuracy of the dense crowd-counting algorithm. Thus, we propose a lightweight dense crowd-counting algorithm (LCNNet) to improve this issue. Specifically, the proposed LCNNet consists of two subnetworks, a feature extraction subnetwork, and a regression subnetwork, with a bottleneck depth-separable convolution with a residuals module as the basic module. The LCNNet effectively improves computational efficiency and reduces the computational cost, which can be performed on small devices. Extensive evaluations on four benchmark datasets well demonstrate the effectiveness of the proposed LCSNet for dense crowd-counting models. Meanwhile, the proposed LCNNet can maintain a comparable level of computational accuracy and computational cost on Vehicle counting datasets.