Abstract
In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. However, obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and it is worthwhile devoting much effort to this. In this paper, a new framework is proposed to resolve the problem. The proposed framework includes two parts. The first part is a fully convolutional neural network (CNN) consisting of backend and upsampling. In the first part, backend uses the residual network (ResNet) to encode the features of the input picture, and upsampling uses the deconvolution layer to decode the feature information. The first part processes the input image, and the processed image is input to the second part. The second part is a peak confidence map (PCM), which is proposed based on an improvement over the density map (DM). Compared with DM, PCM can not only solve the problem of crowd counting but also accurately predict the location of the person. The experimental results on several datasets (Beijing-BRT, Mall, Shanghai Tech, and UCF_CC_50 datasets) show that the proposed framework can achieve higher crowd counting performance in dense scenarios and can accurately predict the location of crowds.
Highlights
In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics
Backend uses the residual network (ResNet) to encode the features of the input picture, and upsampling uses the deconvolution layer to decode the feature information. e first part processes the input image, and the processed image is input to the second part. e second part is a peak confidence map (PCM), which is proposed based on an improvement over the density map (DM)
Many excellent models and algorithms are proposed to solve these problems in crowd counting. e methods for solving crowd counting can be classified into two categories: traditional methods and methods based on convolutional neural network (CNN). e conventional methods focus on carefully designed features extraction algorithms to solve this problem
Summary
In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. Obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and it is worthwhile devoting much effort to this. Compared with DM, PCM can solve the problem of crowd counting and accurately predict the location of the person. E experimental results on several datasets (Beijing-BRT, Mall, Shanghai Tech, and UCF_CC_50 datasets) show that the proposed framework can achieve higher crowd counting performance in dense scenarios and can accurately predict the location of crowds. E methods for solving crowd counting can be classified into two categories: traditional methods and methods based on convolutional neural network (CNN). The DM-based methods lead to the following problems [3]: (1) higher the proportion of false positives and (2) loss of crowd location information. Erefore, a new crowd detection and counting framework is proposed to solve this problem Most of Journal of Advanced Transportation the current research methods only focus on the design of the network structure and ignore the fundamental problem brought by DM: “location information loss.” Location information and the number of people are complementary to each other. erefore, a new crowd detection and counting framework is proposed to solve this problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
