图 书 馆
用整数规划优化跟踪交互对象Tracking Interacting Objects Optimally Using Integer Programming |
|
| 课程网址: | http://videolectures.net/eccv2014_wang_interacting_objects/ |
| 主讲教师: | Xinchao Wang |
| 开课单位: | 洛桑联邦理工学院 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  在本文中，我们展示了可以将跟踪不同种类的交互对象的公式表示为网络流混合整数程序。通过同时跟踪所有对象并表示一个对象可以出现或消失的事实，就可以通过线性流动约束在另一个对象上出现或消失这一事实。我们展示了我们的方法在以下场景中的威力：涉及汽车和行人，有人携带和放下行李，在篮球比赛中将球从一个球员传到另一个球员。特别是，我们表明，通过联合和全局估计不同类型对象的轨迹，可以从其他对象的检测中推断出最初不是仅基于图像证据检测到的对象的存在。 |
| 课程简介: | In this paper, we show that tracking different kinds of interacting objects can be formulated as a network-flow Mixed Integer Program. This is made possible by tracking all objects simultaneously and expressing the fact that one object can appear or disappear at locations where another is in terms of linear flow constraints. We demonstrate the power of our approach on scenes involving cars and pedestrians, bags being carried and dropped by people, and balls being passed from one player to the next in a basketball game. In particular, we show that by estimating jointly and globally the trajectories of different types of objects, the presence of the ones which were not initially detected based solely on image evidence can be inferred from the detections of the others. |
| 关 键 词: | 整数规划; 数据交互; 图像检测 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-04：zyk |
| 最后编审: | 2020-11-04：zyk |
| 阅读次数: | 26 |