摘要：The task of crowd counting and density map estimation is riddled with many challenges, such as occlusions, non-uniform density, intra-scene and inter-scene variations in scale and perspective. Due to the development of deep learning and large crowd datasets in recent years, most crowd counting methods have achieved notable success. This paper aims to solve crowd density estimation problem for both sparse and dense conditions. To this end, we make two contributions: (1) a network named Patch Scale Discriminant Regression Network (PSDR). Given an input crowd image, it divides the image into patches and sends image patches of different density levels into different regression networks to get the corresponding density maps. It combines all patch density maps to predict the entire density map as the output. (2) A person classification activation map (CAM) method. CAM provides person location information and guides the generation of the entire density map in the final stage. Experiment confirms that CAM allows PSDR to gain another round of performance boost. For instance, on the SmartCity dataset, we achieve (8.6-1.1) MAE and (11.6-1.4) MSE. Our method combining above two methods performs better than state-of-the-art methods.

关键字：Crowd density estimation Image patch Density level Attention mechanism Classification activation map

ISSN号：0941-0643

卷、期、页：卷: 32 期: 9 页: 5105-5116 特刊: SI

发表日期：2020-05-01

影响因子：4.774400

期刊分区（SCI为中科院分区）：二区

收录情况：SCIE（科学引文索引网络版）,EI（工程索引）

发表期刊名称：NEURAL COMPUTING & APPLICATIONS

参与作者：Yang, Zhongguo,Yuan, Kun

通讯作者：李承阳

第一作者：朱丽萍,王尚旭

论文类型：期刊论文

论文概要：朱丽萍,李承阳,Yang, Zhongguo,Yuan, Kun,王尚旭，Crowd density estimation based on classification activation map and patch density level，NEURAL COMPUTING & APPLICATIONS，2020，卷: 32 期: 9 页: 5105-5116 特刊: SI

论文题目：Crowd density estimation based on classification activation map and patch density level