视频分割的MoT-混合树概率图模型MoT - Mixture of Trees Probabilistic Graphical Model for Video Segmentation |
|
课程网址: | http://videolectures.net/bmvc2012_budvytis_video_segmentation/ |
主讲教师: | Ignas Budvytis |
开课单位: | 剑桥大学 |
开课时间: | 2012-10-09 |
课程语种: | 英语 |
中文简介: | 提出了一种新的混合树图像分割模型。这种混合中的每个组件表示视频序列从第一帧到最后一帧的超级像素之间的树结构时间链接。我们的时间序列模型明确地捕获了相邻帧之间时间连接的不确定性,从而提高了分割精度。我们为该模型提供了一个变分推理方案来估计超像素标签及其在近实时的置信度。通过对具有挑战性的SegTrack联合分割和跟踪数据集的定量比较,证明了我们方法的有效性。 |
课程简介: | We present a novel mixture of trees (MoT) graphical model for video segmentation. Each component in this mixture represents a tree structured temporal linkage between super-pixels from the first to the last frame of a video sequence. Our time-series model explicitly captures the uncertainty in temporal linkage between adjacent frames which improves segmentation accuracy. We provide a variational inference scheme for this model to estimate super-pixel labels and their confidences in nearly realtime. The efficacy of our approach is demonstrated via quantitative comparisons on the challenging SegTrack joint segmentation and tracking dataset. |
关 键 词: | 计算机视觉; 视频分析; 视频分割 |
课程来源: | 视频讲座网 |
最后编审: | 2021-01-30:nkq |
阅读次数: | 24 |