Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions
Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions
复制标题
DOI：
10.1109/cvpr.2013.87
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Dong Zhang;O. Javed;M. Shah
中科院分区：
文献类型：
--
作者：
Dong Zhang;O. Javed;M. Shah
在本文中，我们提出了一种新颖的方法，以在“对象建议”域中的视频中提取主要对象段。然后，提取的主要对象区域用于构建对象模型以优化视频分割。所提出的方法有几个贡献：首先，提出了一种基于新型的分层定向无环图（DAG）框架，以检测和分割视频中的主要对象。我们利用这样一个事实，通常，对象在空间上具有凝聚力，并以局部光滑的运动轨迹为特征，以根据跨帧的运动，外观和预测形状的相似性从所有可用建议的集合中提取主要对象。其次，使用增强的对象提案集初始化了DAG，其中使用基于运动的建议预测（来自相邻帧）来扩展特定帧的对象建议集。最后，本文提出了一个运动评分函数，用于选择对象建议，该提议强调了在提案边界处的高光流梯度，以区分移动对象和背景。使用几个具有挑战性的基准视频评估了所提出的方法，它的表现既优于无监督和监督的最新方法。
In this paper, we propose a novel approach to extract primary object segments in videos in the `object proposal' domain. The extracted primary object regions are then used to build object models for optimized video segmentation. The proposed approach has several contributions: First, a novel layered Directed Acyclic Graph (DAG) based framework is presented for detection and segmentation of the primary object in video. We exploit the fact that, in general, objects are spatially cohesive and characterized by locally smooth motion trajectories, to extract the primary object from the set of all available proposals based on motion, appearance and predicted-shape similarity across frames. Second, the DAG is initialized with an enhanced object proposal set where motion based proposal predictions (from adjacent frames) are used to expand the set of object proposals for a particular frame. Last, the paper presents a motion scoring function for selection of object proposals that emphasizes high optical flow gradients at proposal boundaries to discriminate between moving objects and the background. The proposed approach is evaluated using several challenging benchmark videos and it outperforms both unsupervised and supervised state-of-the-art methods.