Crowd density detection method based on crowd gathering mode and multi-column convolutional neural network
作者：
Highlights：
• For the first time, a basic model of crowd gathering based on personal space theory was defined and mathematically modeled.
• For the first time, the influence of the terrain environment on the population density was discussed and mathematically quantified.
• For the first time, a MCNN was used to solve the feature extraction of different sizes of people in different perspectives.
• For the first time, the estimation of the clustering density was completed by approximate fitting techniques.
摘要
•For the first time, a basic model of crowd gathering based on personal space theory was defined and mathematically modeled.•For the first time, the influence of the terrain environment on the population density was discussed and mathematically quantified.•For the first time, a MCNN was used to solve the feature extraction of different sizes of people in different perspectives.•For the first time, the estimation of the clustering density was completed by approximate fitting techniques.
论文关键词：Computer vision,Overcrowding,Crowd gathering safety,Video surveillance,Accident analysis and early warning
论文评审过程：Received 5 December 2019, Revised 15 October 2020, Accepted 29 November 2020, Available online 5 December 2020, Version of Record 22 December 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.104084
