Large scale crowd analysis based on convolutional neural network

作者：

Highlights：

• A method to estimate the number of crowd flow with CNN models is proposed.

• A database with 140 thousand samples from real scenes is build.

• The experiments perform robust under various scenes, weather or crowded condition.

摘要

Highlights•A method to estimate the number of crowd flow with CNN models is proposed.•A database with 140 thousand samples from real scenes is build.•The experiments perform robust under various scenes, weather or crowded condition.

论文关键词：Crowd analysis,Flow counting,CNN,Large scale data

论文评审过程：Received 8 October 2014, Revised 6 March 2015, Accepted 2 April 2015, Available online 15 April 2015, Version of Record 17 June 2015.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.04.001