检索结果-南通市图书馆

Behaviour recognition based on the integration of multigranular motion features in the Internet of Things

Digital Communications and Networks 2024年第3期10卷 666-675页

作者： Lizong Zhang Yiming Wang Ke Yan Yi Su Nawaf Alharbe Shuxin Feng School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China Beijing Institute of Remote Sensing Equipment Beijing100039China Applied College Taibah UniversityMedina42353Saudi Arabia

With the adoption of cutting-edge communication technologies such as 5G/6G systems and the extensive development of devices,crowdsensing systems in the Internet of Things(IoT)are now conducting complicated video analysis tasks such as behaviour *** applications have dramatically increased the diversity of IoT ***,behaviour recognition in videos usually requires a combinatorial analysis of the spatial information about objects and information about their dynamic actions in the temporal *** recognition may even rely more on the modeling of temporal information containing short-range and long-range motions,in contrast to computer vision tasks involving images that focus on understanding spatial ***,current solutions fail to jointly and comprehensively analyse short-range motions between adjacent frames and long-range temporal aggregations at large scales in *** this paper,we propose a novel behaviour recognition method based on the integration of multigranular(IMG)motion features,which can provide support for deploying video analysis in multimedia IoT crowdsensing *** particular,we achieve reliable motion information modeling by integrating a channel attention-based short-term motion feature enhancement module(CSEM)and a cascaded long-term motion feature integration module(CLIM).We evaluate our model on several action recognition benchmarks,such as HMDB51,Something-Something and *** experimental results demonstrate that our approach outperforms the previous state-of-the-art methods,which confirms its effective-ness and efficiency.

关键词： Behaviour recognition motion features Attention mechanism Internet of things Crowdsensing

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

The Experimental Investigations on motion features of Groundwater Flow near the Pumping Well

引用

Journal of Groundwater Science and Engineering 2014年第1期2卷 1-11页

作者： Zong-jun GAO College of Geological Science and Engineering Shandong University of Science and Technology

Using the 3D pumping test device, the author has completed a number of pumping tests about phreatic and artesian water and obtained a large amount of observational data. Experiments show that: as for both phreatic and artesian water, the water head variation of the observation wells, from the pumping well is far more higher and nearer than the lower, leading to significant groundwater cone of depression distribution around the underground water pumping well. At the same time, the water heads of different observation pointing at different heights of each observation well are higher to lower from top to bottom, which are characterized by showing that the water has a top to bottom motion component while groundwater has migration and accumulation from the surrounding water boundary to the pumping well, i.e. the water movement direction is inclined. The same is true for artesian water. An analysis found the result is that not only head pressure plays an important role, but also water gravity does this too. When the water is pumped, the artesian aquifer near the top roof has a stronger water flow near the supply source.

关键词： 3D Pumping Test Device Pumping Well Groundwater Flow motion features

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：