检索结果-南通市图书馆

FaSRnet:a feature and semantics refinement network for human pose estimation

Frontiers of Information Technology & Electronic Engineering 2024年第4期25卷 513-526页

作者： Yuanhong ZHONG Qianfeng XU Daidi ZHONG Xun YANG Shanshan WANG School of Microelectronics and Communication Engineering Chongqing UniversityChongqing 400044China Bioengineering College of Chongqing University Chongqing UniversityChongqing 400044China School of Information Science and Technology University of Science and Technology of ChinaHefei 230039China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230039China

Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging *** temporal consistency between consecutive frames is an efficient approach for addressing this ***,most methods explore temporal consistency through refinements of the final *** heatmaps contain the semantics information of key points,and can improve the detection quality to a certain ***,they are generated by features,and feature-level refinements are rarely *** this paper,we propose a human pose estimation framework with refinements at the feature and semantics *** align auxiliary features with the features of the current frame to reduce the loss caused by different feature *** attention mechanism is then used to fuse auxiliary features with current *** terms of semantics,we use the difference information between adjacent heatmaps as auxiliary features to refine the current *** method is validated on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018,and the results demonstrate the effectiveness of our method.

关键词： Human pose estimation Multi-frame refinement Heatmap and offset estimation feature alignment Multi-person

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

FAANet: feature-aligned attention network for real-time multiple object tracking in UAV videos

引用

Chinese Optics Letters 2022年第8期20卷 6-11页

作者： Zhenqi Liang Jingshi Wang Gang Xiao Liu Zeng School of Aeronautics and Astronautics Shanghai Jiao Tong UniversityShanghai 200240China Jiangsu Automation Research Institute Lianyungang 222061China

Multiple object tracking(MOT)in unmanned aerial vehicle(UAV)videos has attracted *** of the observation perspectives of UAV,the object scale changes dramatically and is relatively ***,most MOT algorithms in UAV videos cannot achieve real-time due to the tracking-by-detection *** propose a feature-aligned attention network(FAANet).It mainly consists of a channel and spatial attention module and a feature-aligned aggregation *** also improve the real-time performance using the joint-detection-embedding paradigm and structural re-parameterization *** validate the effectiveness with extensive experiments on UAV detection and tracking benchmark,achieving new state-of-the-art 44.0 MOTA,64.6 IDF1 with 38.24 frames per second running speed on a single 1080Ti graphics processing unit.

关键词： multiple object tracking unmanned aerial vehicle feature alignment deep learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：