Crowd counting via learning perspective for multi-scale multi-view Web images
Crowd counting via learning perspective for multi-scale multi-view Web images
Chong SHANG;Haizhou AI;Yi YANG
【期刊名称】《中国高等学校学术文摘·计算机科学》 【年(卷),期】2024(013)003
【摘要】Estimating the number of people in Web images still remains a challenging problem owing to the perspective variation,different views,and diverse backgrounds.Existing deep learning models still have difficulties in dealing with scenarios where the size of a person is either extremely large or extremely small.In this paper,we propose a novel perspective-aware architecture to estimate the number of people in a crowd in web images.Specifically,we use a two-stage framework,where we first learn a policy network to infer the perspective of the target scene,which outputs a scale label for the subsequent perspective normalization.Next,given the aligned inputs,we further adjust the scale-specific counting network to regress the final count.Experiments on challenging datasets demonstrate our approach can deal with a large perspective variation and that we have achieved state-of-theart results. 【总页数】9页(579-587) 【关键词】
【作者】Chong SHANG;Haizhou AI;Yi YANG
【作者单位】Tsinghua National Laboratory for Information Science and
Crowd counting via learning perspective for multi-scale multi-view Web images
