Lightweight Crowd Counting Network based on Depthwise Separable Convolution

Dengguo Yao, Yuanping Xu, Chaolong Zhang, Zhijie Xu, Jian Huang, Benjun Guo

Research output: Contribution to journalConference articlepeer-review


Crowd counting on the image is a challenging problem. Many neural network-based methods usually use two-branch and multi-branch networks to extract high-level features of different scales or densities, and then merge these features by a fusion operation. Although these methods can reduce the error of crowd counting, it makes the amount of parameters is enormous, so that the efficiency of training and optimization of the model is low, and the calculation resource consumption is high. To this end, a residual network based on depthwise separable convolution is proposed for image crowd counting. The network can not only reduce the amount of calculation through depthwise separable convolution, but also deepen the network depth through the residual structure to extract more effective high-level features. The experiment proves that, compared with the start-of-the-art methods, the method in this paper dramatically reduces the parameter amount to 1.91 Million when the accuracy is comparable.

Original languageEnglish
Article number012016
Number of pages7
JournalJournal of Physics: Conference Series
Issue number1
Early online date13 Oct 2020
Publication statusPublished - 13 Oct 2020
Event3rd International Conference on Computer Information Science and Application Technology - Dali, China
Duration: 17 Jul 202019 Jul 2020
Conference number: 3


Dive into the research topics of 'Lightweight Crowd Counting Network based on Depthwise Separable Convolution'. Together they form a unique fingerprint.

Cite this