CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
This work addresses crowd and object counting in congested scenes, which is important for applications like surveillance and traffic management, but it is incremental as it builds on existing CNN and dilated convolution techniques.
The paper tackled the problem of understanding highly congested scenes by proposing CSRNet, a dilated convolutional neural network for accurate count estimation and high-quality density maps, achieving a 47.3% lower Mean Absolute Error on the ShanghaiTech Part_B dataset and 15.4% lower MAE on the TRANCOS dataset compared to previous state-of-the-art methods.
We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance. In the ShanghaiTech Part_B dataset, CSRNet achieves 47.3% lower Mean Absolute Error (MAE) than the previous state-of-the-art method. We extend the targeted applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4% lower MAE than the previous state-of-the-art approach.