CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 1091 - 1100
• Main Authors: Li, Yuhong, Zhang, Xiaofan, Chen, Deming
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Convolution; Feature extraction; Image analysis; Kernel; Pattern recognition; Task analysis; Training

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...