期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 443-453出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.2980945
关键词
Task analysis; Semantics; Estimation; Feature extraction; Convolutional neural networks; Cameras; Head; Convolutional neural network; crowd counting; density-level classification; density map estimation; multi-task learning
资金
- National Natural Science Foundation of China [61802351, 61822701, 61872324, 61772474]
- China Postdoctoral Science Foundation [2018M632802]
- Key R&D and Promotion Projects in Henan Province [192102310258]
In this study, a novel density-aware convolutional neural network (DensityCNN) method is proposed to perform crowd counting by learning density-level classification and density map estimation. Extensive experiments demonstrate the high effectiveness of the proposed method across multiple datasets.
In this paper, we present a method called density-aware convolutional neural network (DensityCNN) to perform the crowd counting task in various crowded scenes. The key idea of the DensityCNN is to utilize high-level semantic information to provide guidance and constraint when generating density maps. To this end, we implement the DensityCNN by adopting a multi-task CNN structure to jointly learn density-level classification and density map estimation. The density-level classification task learns multi-channel semantic features that are aware of the density distributions of the input image. This task is accomplished via our specially designed group-based convolutional structure in a supervised learning manner. In the density map estimation task, these semantic features are deployed together with high-dimension convolutional features to generate density maps with lower count errors. Extensive experiments on four challenging crowd datasets (ShanghaiTech, UCF_CC_50, UCF-QNCF, and WorldExpo'10) and one vehicle dataset TRANCOS demonstrate the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据