权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

HFVSA: Human Focused Visual Scene Understanding

HFVSA：以人为本的视觉场景理解

基本信息

批准号：
229087185
负责人：
Professor Dr. Jürgen Gall
金额：
--
依托单位：
Institut für Informatik
依托单位国家：
德国
项目类别：
Independent Junior Research Groups
财政年份：
2013
资助国家：
德国
起止时间：
2012-12-31 至 2016-12-31
项目状态：
已结题

来源：
https://gepris.dfg.de/gepris/projekt/229087185?language=en
关键词：
HFVSA Human Focused Visual Scene

项目摘要

A meaningful interpretation of an observed scene covers many important aspects like the similarity of observed objects, the categorization of objects, the functionality of objects, and the action of humans. While visual data like images or videos can be efficiently interpreted by humans, computers still struggle to solve these tasks. This indicates that existing learning procedures and representations of categories are insufficient for scene understanding. For instance, a detector for a specific object class is typically trained on thousands of images containing class examples. Although such a detector might see even more examples than a human, it is not able to learn the intrinsic similarity of the object class and thus lacks the ability of humans to categorize objects reliably. Indeed, humans do not learn only from images but observe a continuous data stream which includes additional cues like hand motion and transformations of the object during object manipulation. In this project, we aim to investigate the facilitative effect of observing human-object interactions for scene understanding. The main focus will be on understanding and learning the intrinsic similarity of visual categories by taking these additional cues into account. Finally, we plan to develop a system that processes automatically visual data streams, extracts the human motion, infers the objects humans interact with, and learns the similarity of objects and their functionality.

对观察到的场景进行有意义的解释包括许多重要方面，如观察到的物体的相似性、物体的分类、物体的功能和人类的行为。虽然图像或视频等视觉数据可以由人类有效地解释，但计算机仍然难以解决这些任务。这表明现有的学习过程和类别表示不足以理解场景。例如，特定对象类的检测器通常在包含类示例的数千张图像上进行训练。尽管这样的检测器可能比人类看到更多的例子，但它无法学习对象类的内在相似性，因此缺乏人类对对象进行可靠分类的能力。事实上，人类不仅从图像中学习，而且观察连续的数据流，其中包括额外的线索，如手部运动和物体在操作过程中的转换。在这个项目中，我们的目标是研究观察人-物交互对场景理解的促进作用。主要的焦点将是通过考虑这些额外的线索来理解和学习视觉类别的内在相似性。最后，我们计划开发一个系统，该系统可以自动处理视觉数据流，提取人体运动，推断人类与之交互的物体，并学习物体的相似性及其功能。

项目成果

期刊论文数量（4）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation

DOI：
10.1007/s11263-016-0895-4
发表时间：
2015-06
期刊：
International Journal of Computer Vision
影响因子：
19.5
作者：
Dimitrios Tzionas;Luca Ballan;A. Srikantha;Pablo Aponte;M. Pollefeys;Juergen Gall
通讯作者：
Dimitrios Tzionas;Luca Ballan;A. Srikantha;Pablo Aponte;M. Pollefeys;Juergen Gall

Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images