Skip to Main content Skip to Navigation

Revisiting Perspective Information for Efficient Crowd Counting

Abstract : Crowd counting is the task of estimating people numbers in crowd images. Modern crowd counting methods employ deep neural networks to estimate crowd counts via crowd density regressions. A major challenge of this task lies in the perspective distortion, which results in drastic person scale change in an image. Density regression on the small person area is in general very hard. In this work, we propose a perspective-aware convolutional neural network (PACNN) for efficient crowd counting, which integrates the perspective information into density regression to provide additional knowledge of the person scale change in an image. Ground truth perspective maps are firstly generated for training; PACNN is then specifically designed to predict multi-scale perspective maps, and encode them as perspective-aware weighting layers in the network to adaptively combine the outputs of multi-scale density maps. The weights are learned at every pixel of the maps such that the final density combination is robust to the perspective distortion. We conduct extensive experiments on the ShanghaiTech, WorldExpo'10, UCF_CC_50, and UCSD datasets, and demonstrate the effectiveness and efficiency of PACNN over the state-of-the-art.
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download
Contributor : Miaojing Shi <>
Submitted on : Sunday, December 9, 2018 - 8:43:05 PM
Last modification on : Tuesday, February 25, 2020 - 8:08:12 AM
Document(s) archivé(s) le : Sunday, March 10, 2019 - 1:41:36 PM


Files produced by the author(s)


  • HAL Id : hal-01831109, version 2



Miaojing Shi, Zhaohui Yang, Chao Xu, Qijun Chen. Revisiting Perspective Information for Efficient Crowd Counting. [Research Report] Inria Rennes - Bretagne Atlantique. 2018, pp.1-10. ⟨hal-01831109v2⟩



Record views


Files downloads