期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 44, 期 3, 页码 1357-1370出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2020.3022878
关键词
Crowd counting; vehicle counting; object counting; density map generation; density map estimation; deep learning
资金
- Research Grants Council of the Hong Kong Special Administrative Region, China [T32-101/15-R, CityU 11212518]
- City University of Hong Kong [7004887]
Crowd counting is an important topic in computer vision, which uses density maps generated from ground-truth dot maps and deep learning models to improve counting performance. However, the hand-crafted methods used for generating density maps may not be optimal for specific networks or datasets. To address this, an adaptive density map generator is proposed, which is trained jointly with a counter within an end-to-end framework.
Crowd counting is an essential topic in computer vision due to its practical usage in surveillance systems. The typical design of crowd counting algorithms is divided into two steps. First, the ground-truth density maps of crowd images are generated from the ground-truth dot maps (density map generation), e.g., by convolving with a Gaussian kernel. Second, deep learning models are designed to predict a density map from an input image (density map estimation). The density map based counting methods that incorporate density map as the intermediate representation have improved counting performance dramatically. However, in the sense of end-to-end training, the hand-crafted methods used for generating the density maps may not be optimal for the particular network or dataset used. To address this issue, we propose an adaptive density map generator, which takes the annotation dot map as input, and learns a density map representation for a counter. The counter and generator are trained jointly within an end-to-end framework. We also show that the proposed framework can be applied to general dense object counting tasks. Extensive experiments are conducted on 10 datasets for 3 applications: crowd counting, vehicle counting, and general object counting. The experiment results on these datasets confirm the effectiveness of the proposed learnable density map representations.
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