0


21 世纪的视觉跟踪

Visual Tracking in the 21st Century
课程网址: http://videolectures.net/bmvc2012_matas_visual_tracking/  
主讲教师: Jiri Matas
开课单位: 布拉格捷克技术大学
开课时间: 信息不详。欢迎您在右侧留言补充。
课程语种: 英语
中文简介:
视觉跟踪是一个古老的领域,最近看到了活动的激增。随着检测、分割和光流等相关领域的进展,以及应用驱动的需求和可用计算能力的增加,人们的兴趣得到了推动。发布的跟踪方法在很多方面都有所不同,如速度、被跟踪实体模型的复杂性、假设的(几何)转换、操作模式(偶然和非因果)、适应和学习能力、对遮挡的鲁棒性以及对观察者的假设。我将回顾最近出版物中使用的数据集,并显示";跟踪器空间";仍有很大的开放空间,有待探索。然后,我将介绍三个由我和我的合作者开发的跟踪器,这些跟踪器在速度鲁棒性灵活空间中的不同点上工作,这些点与已发布方法的“凸壳”接近:TLD跟踪器、跟踪器群和零位移点跟踪器。我将关注跟踪者共享的一个共同方面:跟踪错误的预测和处理机制。这样的机制有助于跟踪器的鲁棒性,这将得到现场演示。
课程简介: Visual tracking is an old area that has recently seen a surge in activity. The interest has been fueled by progress in related fields like detection, segmentation and optic flow as well as by application-driven demand and the increase in the available computing power. The published tracking methods differ in many aspects such as the speed, the complexity of the model of the tracked entity, the (geometric) transformations assumed, the mode of operation (casual and non-causal), the ability to adapt and learn, the robustness to occlusion and assumptions about the observer. I will review the dataset used in recent publications and show that the "tracker space" is still wide open with large areas to be explored. I will then present three trackers developed by me and my collaborators that operate at very different points in the speed-robustness-flexibility space that are close to the "convex hull" of published methods: the TLD tracker, the Flock-of-Trackers and the Zero-Shift-Point tracker. I will focus on a common aspect shared by the trackers: mechanisms for prediction and handling of tracking errors. Such mechanisms contribute to tracker robustness, which will be demonstrated live.
关 键 词: 计算机视觉; 视觉跟踪; 跟踪器设计
课程来源: 视频讲座网
最后编审: 2019-12-10:cwx
阅读次数: 44