• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Iranica Journal of Energy and Environment >Sensing Image Regions for Enhancing Accuracy in People Re-identification
【24h】

Sensing Image Regions for Enhancing Accuracy in People Re-identification

机译：Sensing Image Regions for Enhancing Accuracy in People Re-identification

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

Video surveillance systems are widely used in the public and private sectors for maintainingsecurity and healthcare purposes. Performance of surveillance systems directly depends on theiraccuracy in re-identification. There are three regions in a camera view, including person’s body,background, and possible carried object by the person. Background, in existing approaches, iseither overlooked or treated like a person’s body in re-identification. In this paper, these threeregions are considered in re-identification but with different importance. In our proposedtechnique, first, the input image is semantically segmented into the three regions using a deepsemantic segmentation approach. Then, the effect of each region on characteristic features ofpeople is tuned depending on the region’s importance in re-identification. The proposedtechnique, leveraging robust descriptors, such as the Gaussian of Gaussian (GOG) and HierarchicalGaussian Descriptors (HGD), can enhance existing methods in dealing with the challenging issuessuch as partial occlusion caused by carried objects and background in re-identification.Experimental results on commonly used people re-identification datasets demonstrateeffectiveness of the proposed technique in improving performance of existing re-identificationmethods.

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号