Learning a deep network with cross-hierarchy aggregation for crowd counting

作者：

Highlights：

• A novel deep model for crowd counting is proposed.

• We propose cross-hierarchy aggregation to reuse hierarchical features.

• Results show that our method outperforms the state-of-the-art methods.

• Cross-scene evaluation verifies the superior generalization ability of our model.

摘要

•A novel deep model for crowd counting is proposed.•We propose cross-hierarchy aggregation to reuse hierarchical features.•Results show that our method outperforms the state-of-the-art methods.•Cross-scene evaluation verifies the superior generalization ability of our model.

论文关键词：Crowd counting,Cross-hierarchy aggregation,Density maps

论文评审过程：Received 10 June 2020, Revised 26 October 2020, Accepted 16 December 2020, Available online 18 December 2020, Version of Record 24 December 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106691