Learning about Activities from Video

从视频中了解活动

• 批准号: EP/D061334/1
• 负责人: David Hogg
• 金额: $ 54.35万
• 依托单位: University of Leeds
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2006
• 资助国家: 英国
• 起止时间: 2006 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FD061334%2F1
• 关键词: Learning; about; Activities; Video

Imagine a system that could search the web for video clips containing an activity similar to one already highlighted (e.g. a car parking or two people having a conversation); that could participate in a card game after observing others do the same; and that could detect someone involved in an unfamiliar activity in a car park. Furthermore, suppose that it could do all of these things with no prior knowledge about the specific objects and activities depicted. All of these capabilities can be couched in terms of looking for similar or analogous activities in video clips.A lot of work has been done over the past forty years on devising methods for finding objects and activities in pictures and video clips by hand-crafting computer-models of what they are expected to look like. Ways have now been found to fully automate the creation of such models for objects (e.g. pedestrians) and simple movements (e.g. running) by learning from large sets of pictures and video clips. This should therefore make it possible to search for similar objects and movements with no prior knowledge of those things.Some progress has been made recently on extending this level of automation to handle a limited range of more complex activities in very simple scenes. This has been achieved by firstly learning about the appearance of objects and then learning about the activities in which they are involved using logical induction. Unfortunately there isn't yet an easy way to ensure the object categories produced are appropriate for the activities to be learnt. Our main aim is to resolve this problem by steering the search for object categories towards those that lead to the most coherent set of activities. A consequence of this could be to change the way we think about age-old problems in computer vision and logical reasoning.

想象一个可以在网络上搜索的系统，以获取包含类似于已经突出显示的活动的视频剪辑（例如，停车场或两个人进行对话）；观察其他人也这样做后，可能会参加纸牌游戏。这可以检测到参与停车场不熟悉活动的人。此外，假设它可以完成所有这些事情，而对所描绘的特定对象和活动没有任何知识。所有这些功能都可以通过在视频剪辑中寻找相似或类似活动的方式来表达。在过去的四十年中，已经完成了许多工作，以设计方法，以通过手工制作图片和视频剪辑来查找对象和活动，这些方法是通过手工制作计算机模型的方式，这些方法是他们所期望的。现在发现方法可以通过从大量图片和视频剪辑中学习来完全自动化对象（例如行人）和简单动作（例如运行）此类模型的创建。因此，这应该使搜索相似的对象和动作不在不知情的情况下搜索类似的对象和动作。这是通过首先学习对象的出现，然后学习使用逻辑归纳参与的活动来实现的。不幸的是，还没有一种简单的方法来确保生成的对象类别适合学习。我们的主要目的是通过将搜索对象类别转移到导致最连贯的活动集的搜索中来解决此问题。结果可能是改变我们考虑计算机视觉和逻辑推理中古老的问题的方式。

项目成果

Inferring additional knowledge from QTCN relations

从 QTCN 关系推断附加知识

• DOI: 10.1016/j.ins.2010.12.021
• 发表时间: 2011
• 期刊: Information Sciences
• 影响因子: 8.1
• 作者: Delafontaine M

REASONING WITH TOPOLOGICAL AND DIRECTIONAL SPATIAL INFORMATION

利用拓扑和方向空间信息进行推理

• DOI: 10.1111/j.1467-8640.2012.00431.x
• 发表时间: 2012
• 期刊: Computational Intelligence
• 影响因子: 2.8
• 作者: Li S

Navigational strategies in behaviour modelling

• DOI: 10.1016/j.artint.2008.10.011
• 发表时间: 2009-02
• 期刊: Artif. Intell.
• 作者: Hannah M. Dee;David C. Hogg

Explaining Activities as Consistent Groups of Events A Bayesian Framework Using Attribute Multiset Grammars

使用属性多重集语法将活动解释为一致的事件组的贝叶斯框架

• DOI: 10.1007/s11263-011-0497-0
• 发表时间: 2011
• 期刊: International Journal of Computer Vision
• 影响因子: 19.5
• 作者: Damen D

Learning functional object categories from a relational spatio-temporal representation

从关系时空表示中学习功能对象类别

• 发表时间: 2008
• 作者: K Sridhar