Multi-view gait-based human identification with automatic joint detection

This research work proposes a joint detection approach to detect locations of body joint automatically by applying a priori knowledge of body proportion. The joint detection approach does not attempt to detect each lower limb of a human, so it can detect the body joints even from self-occluded silho...

全面介绍

Saved in:
书目详细资料
主要作者: Ng, Hu
格式: Thesis
出版: 2014
主题:
标签: 添加标签
没有标签, 成为第一个标记此记录!
实物特征
总结:This research work proposes a joint detection approach to detect locations of body joint automatically by applying a priori knowledge of body proportion. The joint detection approach does not attempt to detect each lower limb of a human, so it can detect the body joints even from self-occluded silhouettes or those occluded by apparel (long blouses or baggy trousers) or bags (handbag or rucksack). In this research work, an improved perspective correction technique to normalize oblique-view walking sequences to side-view plane has been developed. The silhouettes from oblique-view walking sequences are vertical and horizontal adjusted to fit the sideview.