A cross-modal fusion based approach with scale-aware deep representation for RGB-D crowd counting and density estimation

作者：

Highlights：

• Introduce depth information into density estimation pipeline for counting improvement.

• Modeling global and local contexts is designed for learning more deep representation.

• A completed cross-modal fusion based approach for RGB-D crowd counting is validated.

摘要

•Introduce depth information into density estimation pipeline for counting improvement.•Modeling global and local contexts is designed for learning more deep representation.•A completed cross-modal fusion based approach for RGB-D crowd counting is validated.

论文关键词：RGB-D crowd counting,Depth information,Density estimation

论文评审过程：Received 7 December 2020, Revised 12 March 2021, Accepted 16 April 2021, Available online 21 April 2021, Version of Record 10 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115071