[论文解读] Video Object Segmentation and Tracking: A Survey

Rui Yao, Guosheng Lin+3 more|arXiv (Cornell University)|Apr 19, 2019

Video Surveillance and Tracking Methods参考文献 183被引用 42

一句话总结

本论文提供了视频对象分割与跟踪（VOST）的全面综述，提出了一种方法的分层分类，并总结数据集、度量和未来方向。

ABSTRACT

Object segmentation and object tracking are fundamental research area in the computer vision community. These two topics are diffcult to handle some common challenges, such as occlusion, deformation, motion blur, and scale variation. The former contains heterogeneous object, interacting object, edge ambiguity, and shape complexity. And the latter suffers from difficulties in handling fast motion, out-of-view, and real-time processing. Combining the two problems of video object segmentation and tracking (VOST) can overcome their respective difficulties and improve their performance. VOST can be widely applied to many practical applications such as video summarization, high definition video compression, human computer interaction, and autonomous vehicles. This article aims to provide a comprehensive review of the state-of-the-art tracking methods, and classify these methods into different categories, and identify new trends. First, we provide a hierarchical categorization existing approaches, including unsupervised VOS, semi-supervised VOS, interactive VOS, weakly supervised VOS, and segmentation-based tracking methods. Second, we provide a detailed discussion and overview of the technical characteristics of the different methods. Third, we summarize the characteristics of the related video dataset, and provide a variety of evaluation metrics. Finally, we point out a set of interesting future works and draw our own conclusions.

研究动机与目标

• 将现有 VOST 方法分为分层分类法（无监督 VOS、半监督 VOS、互动 VOS、弱监督 VOS、基于分割的跟踪）。
• 讨论每一类的技术特征以及它们如何解决 VOST 的挑战（遮挡、形变、运动模糊、尺度变化）。
• 总结用于 VOST 的相关视频数据集和评估指标。
• 确定 VOST 研究的未来方向和潜在应用。

提出的方法

• 提出一个五类分层 taxonomy 用于 VOST 方法：无监督 VOS、半监督 VOS、互动 VOS、弱监督 VOS、以及基于分割的跟踪。
• 提供每一类的技术特征的详细讨论和概述。
• 总结并比较 VOST 研究中使用的视频数据集和评估指标。
• 讨论 VOST 的实际应用和未来研究方向。

实验结果

研究问题

• RQ1 视频对象分割与跟踪方法主要类别有哪些？它们如何在层次结构中组织？
• RQ2 每个 VOST 类别中的关键技术特征和方法是什么？
• RQ3 用于评估 VOST 方法的数据集和评估指标有哪些，它们的属性是什么？
• RQ4 VOST 研究确定的未来方向和挑战是什么？

主要发现

• 综述提出了五大类的 VOST 方法分层分类。
• 对无监督 VOS、半监督 VOS、互动 VOS、弱监督 VOS、基于分割的跟踪的技术特征进行了详尽讨论。
• 总结了相关视频数据集的特征以及用于 VOST 的各种评估指标。
• 论文讨论了未来工作和推动 VOST 研究的潜在方向。
• 研究澄清了 VOS 与 VOT 之间的关系，并讨论了分割基跟踪如何整合两者。