|
多目标跟踪和集体活动识别的统一框架
A Unified Framework for Multi-Target Tracking and Collective Activity Recognition |
|
| |
| 课程网址: |
http://videolectures.net/eccv2012_choi_recognition/
|
| 主讲教师: |
Wongun Choi, Ivan Laptev, Michael J. Black
|
| 开课单位: |
密歇根大学
|
| 开课时间: |
2012-11-12
|
| 课程语种: |
英语
|
| 中文简介: |
我们提出了一个连贯的，有区别的框架，用于同时跟踪多个人并估计他们的集体活动。我们的模型不是单独处理这两个问题，而是基于这样的直觉：人的运动，活动以及附近其他人的运动和活动之间存在强烈的相关性。我们不是将解决方案直接链接到这两个问题，而是引入一种活动类型的层次结构，这种活动类型创建了一个自然的进展，从特定的人的运动到整个群体的活动。我们的模型能够共同追踪多个人，识别个人活动（原子活动），人与人之间的互动（互动活动），最后是人群的行为（集体活动）。我们还提出了一种算法，通过将置信传播与配备有整数规划的分支定界算法的版本相结合来解决这个难以处理的联合推理问题。有挑战性的视频数据集的实验结果证明了我们的理论主张，并表明我们的模型达到了迄今为止最好的集体活动分类结果。
|
| 课程简介: |
We present a coherent, discriminative framework for simultaneously tracking multiple people and estimating their collective activities. Instead of treating the two problems separately, our model is grounded in the intuition that a strong correlation exists between a person's motion, their activity, and the motion and activities of other nearby people. Instead of directly linking the solutions to these two problems, we introduce a hierarchy of activity types that creates a natural progression that leads from a specific person's motion to the activity of the group as a whole. Our model is capable of jointly tracking multiple people, recognizing individual activities (atomic activities), the interactions between pairs of people (interaction activities), and finally the behavior of groups of people (collective activities). We also propose an algorithm for solving this otherwise intractable joint inference problem by combining belief propagation with a version of the branch and bound algorithm equipped with integer programming. Experimental results on challenging video datasets demonstrate our theoretical claims and indicate that our model achieves the best collective activity classification results to date.
|
| 关 键 词: |
人的运动; 原子活动; 互动活动
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-03-20：lxf
|
| 阅读次数: |
82
|
|
图 书 馆