报告人：上海科技大学 高盛华研究员
报告地点：#腾讯会议：943-963-794
报告时间：2022年11月1日（周二）上午10点
报告题目： Locating and Counting Heads in Crowds With a Depth Prior
个人简介: 高盛华，上海科技大学研究员(终身教授)，入选国家海外高水平人才计划青年项目，上海市浦江人才计划，曙光学者，上海市优秀学术带头人。研究方向涵盖图像和视频的处理和理解、三维重建及图像视频内容编辑和生成。2008年本科毕业于中国科学技术大学。2012博士毕业于新加坡南洋理工大学。随后在伊利诺伊大学新加坡高等研究院做研究科学家。2014年加入上海科技大学信息学院。迄今为止，在计算机视觉和人工智能领域顶级会议和期刊发表论文120余篇，总引用次数近10000次。他十余次担任ICCV/CVPR/AAAI等国际顶级会议的领域主席，计算机视觉领域顶级期刊IEEE TCSVT和Neurocomputing的副主编等，十余次担任国际顶级会议研讨会主席。
报告摘要: We resort to detection-based crowd counting by leveraging RGB-D data and design a dual-path guided detection network (DPDNet). Specifically, we propose a density map guided detection module, which leverages density map to improve the head/non-head classification in detection network where the density implies the probability of a pixel being a head, and a depth-adaptive kernel that considers the variances in head sizes is also introduced to generate high-fidelity density map for more robust density map regression. We utilize such a density map for post-processing of head detection and propose a density map guided NMS strategy. Meanwhile, we also propose a depth-guided detection module to generate a dynamic dilated convolution to extract features of heads of different scales, and a depth-aware anchor. Then we use the bounding boxes whose sizes are generated with depth to train our DPDNet. We collect two large-scale RGB-D crowd counting datasets, which comprise a synthetic dataset and a real-world dataset, respectively. Since the depth value at long-distance positions cannot be obtained in the real-world dataset, we further propose a depth completion method with meta learning. Extensive experiments show that our method achieves the best performance for RGB-D crowd counting and localization.
