Affiliation:
1. Computer & Software School, Hangzhou Dianzi University, Hangzhou, Zhejiang, China
Abstract
Crowd counting has been widely studied by deep learning in recent years. However, due to scale variation caused by perspective distortion, crowd counting is still a challenging task. In this paper, we propose a Densely Connected Multi-scale Pyramid Network (DMPNet) for count estimation and the generation of high-quality density maps. The key component of our network is the Multi-scale Pyramid Network (MPN), which can extract multi-scale features of the crowd effectively while keeping the resolution of the input feature map and the number of channels unchanged. To increase the information transfer between the network layer, we used dense connections to connect multiple MPNs. In addition, we also designed a novel loss function, which can help our model achieve better convergence. To evaluate our method, we conducted extensive experiments on three challenging benchmark crowd counting datasets. Experimental results show that compared with the state-of-the-art algorithms, DMPNet performs well in both parameters and results. The code is available at: https://github.com/lpfworld/DMPNet.
Funder
Zhejiang Provincial Technical Plan Project
Xiaoshan District Science and Technology Plan Project
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. MLANet: multi-level attention network with multi-scale feature fusion for crowd counting;Cluster Computing;2024-03-04
2. Multi-branch Segmentation-guided Attention Network for crowd counting;Journal of Visual Communication and Image Representation;2023-12
3. Multi-Channel Gaussian Derivative Neural Networks for Crowd Analysis;2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS);2023-07-04
4. A Selective Multi-Unit Group Filter-Based Flexible Fast Light-CNN Training;2023 International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC);2023-06-25