Crowd Density Estimation Using Fusion of Multi-Layer Features

作     者：Ding, Xinghao He, Fujin Lin, Zhirui Wang, Yu Guo, Huimin Huang, Yue 

作者机构：Xiamen Univ Sch Informat Key Lab Underwater Acoust Commun & Marine Informa Minist Educ Xiamen 361005 Fujian Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 (IEEE智能运输系统汇刊)

年 卷 期：2021年第22卷第8期

页      面：4776-4787页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0814[工学-土木工程] 0823[工学-交通运输工程] 

基　　金：National Natural Science Foundation of China [81671766, 61971369, U19B2031,61671309] Open Fund of Science and Technology on Automatic Target Recognition Laboratory Fundamental Research Funds for the Central Universities [20720180059, 20720190116, 20720200003] Tencent Open Fund 

主　　题：Crowd counting fusion encoder-decoder density map 

摘      要：Crowd counting is very important in many tasks such as video surveillance, traffic monitoring, public security, and urban planning, so it is a very important part of the intelligent transportation system. However, achieving an accurate crowd counting and generating a precise density map are still challenging tasks due to the occlusion, perspective distortion, complex backgrounds, and varying scales. In addition, most of the existing methods focus only on the accuracy of crowd counting without considering the correctness of a density distribution;namely, there are many false negatives and false positives in a generated density map. To address this issue, we propose a novel encoder-decoder Convolution Neural Network (CNN) that fuses the feature maps in both encoding and decoding sub-networks to generate a more reasonable density map and estimate the number of people more accurately. Furthermore, we introduce a new evaluation method named the Patch Absolute Error (PAE) which is more appropriate to measure the accuracy of a density map. The extensive experiments on several existing public crowd counting datasets demonstrate that our approach achieves better performance than the current state-of-the-art methods. Lastly, considering the cross-scene crowd counting in practice, we evaluate our model on some cross-scene datasets. The results show our method has a good performance in cross-scene datasets.