首页|Discriminative Learning with Scale Decomposition for Person Detection

Discriminative Learning with Scale Decomposition for Person Detection

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
Person detection,which can locate the person regions in the image,continues to be a hot research topic in both computer vision and signal processing communities.However,detecting person at small scale remains a challenging problem due to the lack of discriminative details in the typical image at small scale.In this paper,we propose a decomposition mapping method which contains two subnets: encoder subnet and decoder subnet.Encoder subnet can exploit decomposition transformation for person regions from big scale to small scale.Decoder subnet reverses the process of the encoder subnet.We add deconvolution network to the decoder subnet to make up for the lost information and a discriminative mapping has been restructured to transform the person regions from the small scale to the big scale.Therefore,person-regions and background-regions can then be separated according to their decomposition positions in the new scale space.The proposed approach is evaluated on two challenging person datasets: Caltech dataset and the KITTI dataset.Compared with SAF R-CNN,the miss rate has been optimized by 3.96％ on Caltech person dataset and the mean average precision has been optimized by 1.76％ on KITTI person dataset.

discriminative learningscale decompositionperson detection

WANG Xiao、CHEN Jun、LIANG Chao、HU Ruimin

展开 >

National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, Hubei, China

Supported by the National Key R&D Program of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaHubei Province Technological Innovation Major ProjectHubei Province Technological Innovation Major Project

2017YFC0803700U161146161876135618620152018AAA0622018CFA024

2020

10.19823/j.cnki.1007-1202.2020.0042

武汉大学自然科学学报(英文版)
武汉大学

武汉大学自然科学学报(英文版)

CSTPCDCSCD
影响因子：0.066
ISSN：1007-1202
年,卷(期)：2020.25(4)
  • 1