Show simple item record

dc.contributor.advisor王其聪
dc.contributor.author赵津浩
dc.date.accessioned2018-12-05T01:48:20Z
dc.date.available2018-12-05T01:48:20Z
dc.date.issued2018-01-02
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/170694
dc.description.abstract随着机器学习和成像传感器技术的快速发展,近些年基于RGB-D传感器的智能应用在许多领域受到了越来越广泛的重视,例如智能监控、智能检索、人机交互、自动标注等等,其中对运动目标的分析是关键技术之一。因此,在针对成像场景中的人体行为识别以及与此相关的时空特征学习受到了广泛的关注。从技术层面分析,基于RGB-D传感器的人体行为识别应该充分利用传感器能够提供的所有序列信息,特别是深度序列信息,并基于运动视觉分析理论,结合机器学习、人工智能、计算机视觉以及模式识别等领域的前沿,设计或学习得到最优的具有可区分性的空时特征来有效表征不同类别的行为动作,进而实现高精度和高可靠性的行为识别系统,因而具有较强的研究...
dc.description.abstractWith the rapid development of machine learning and imaging sensor technology, for the past few years, intelligent applications based on RGB-D sensors have been paid more and more attention in many fields such as intelligent monitoring, intelligent retrieval, human-computer interaction, automatic labeling and so on, Of which the analysis of the moving target is one of the key technologies. Therefor...
dc.language.isozh_CN
dc.relation.urihttps://catalog.xmu.edu.cn/opac/openlink.php?strText=58738&doctype=ALL&strSearchType=callno
dc.source.urihttps://etd.xmu.edu.cn/detail.asp?serial=62676
dc.subject行为识别
dc.subject卷积神经网络
dc.subject流形空间
dc.subject多任务学习
dc.subjectAction Recognition
dc.subjectConvolutional Neural Network
dc.subjectManifold Space
dc.subjectMulti-Task Learning
dc.title基于多模态空时特征学习的3D人体行为识别
dc.title.alternativeMulti-Modal Space-Time Feature Learning Based 3D Human Action Recognition
dc.typethesis
dc.date.replied2017-06-13
dc.description.note学位:工学硕士
dc.description.note院系专业:信息科学与技术学院_计算机科学与技术
dc.description.note学号:23020141153165


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record