Crowd counting via scale-adaptive convolutional neural network

13 Nov 2017  ·  Lu Zhang, Miaojing Shi, Qiaobo Chen ·

The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-column CNN architectures to regress density maps of crowd images. Multiple columns have different receptive fields corresponding to pedestrians (heads) of different scales. We instead propose a scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields. We extract feature maps from multiple layers and adapt them to have the same output size; we combine them to produce the final density map. The number of people is computed by integrating the density map. We also introduce a relative count loss along with the density map loss to improve the network generalization on crowd scenes with few pedestrians, where most representative approaches perform poorly on. We conduct extensive experiments on the ShanghaiTech, UCF_CC_50 and WorldExpo datasets as well as a new dataset SmartCity that we collect for crowd scenes with few people. The results demonstrate significant improvements of SaCNN over the state-of-the-art.

PDF Abstract

Datasets


Introduced in the Paper:

SmartCity

Used in the Paper:

MS COCO ShanghaiTech

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here