摘要： 针对复杂环境下非刚体目标轮廓跟踪存在跟踪失败的问题,提出一种基于在线学习的Snake 模型及其轮 廓跟踪算法。利用跟踪-学习-检测(TLD)机制实现目标快速跟踪,通过跟踪结果在线更新Snake 模型约束,进而提 高目标轮廓跟踪的准确性。初始化阶段,在GrabCut 算法的基础上,将待跟踪目标分成若干个子块,并在后续跟踪 过程中,利用TLD 实现各子目标的定位跟踪,形成目标的轮廓置信图。同时针对各子目标提取特征,产生正负样 本,更新各子目标跟踪模型。应用置信图建立参数化Snake 模型的约束条件,进而得到目标轮廓。实验结果表明,该算法能适应光暗变化与较为复杂坏境下的跟踪,并获得精确的轮廓。

关键词: 轮廓跟踪, GrabCut 算法, Snake 模型, 跟踪-学习-检测算法, 在线学习, 置信图

Abstract: For non-rigid target contour tracking in a complicated environment has tracking failure problems,this paper proposes a snake model and its contour tracking algorithm based on online learning. The algorithm utilizes the Tracking-Learning-Detection(TLD) mechanism to achieve the goal of fast tracking,and updates snake model constraints through the tracking results to improve the accuracy of the target contour tracking. In the phase of initialization,the target to be tracking is divided into several blocks on the basis of GrabCut algorithm,and the algorithm realizes the sub-targets locating and tracking by the use of TLD in the subsequent tracking process,which forms the confident map of target outline. At the same time,the algorithm produces positive and negative samples and updates each target tracking model for each target feature extraction. The constraint of parameterized snake model is built through confident map and the contour of target is obtained. Experimental results show that the algorithm can adapt to the changing light and dark,and even more complex tracking environment,and obtains precise contour.

Key words: contour tracking, GrabCut algorithm, snake model, Tracking-Learning-Detection(TLD) algorithm, online learning, confident map

中图分类号: 

• TP37