Department of Electrical Engineering and Computer Science, Automation and Systems Research Institute, Seoul National University, Kwanak, Seoul, Korea.
IEEE Trans Pattern Anal Mach Intell. 2013 Oct;35(10):2427-41. doi: 10.1109/TPAMI.2013.32.
A novel tracking algorithm is proposed for targets with drastically changing geometric appearances over time. To track such objects, we develop a local patch-based appearance model and provide an efficient online updating scheme that adaptively changes the topology between patches. In the online update process, the robustness of each patch is determined by analyzing the likelihood landscape of the patch. Based on this robustness measure, the proposed method selects the best feature for each patch and modifies the patch by moving, deleting, or newly adding it over time. Moreover, a rough object segmentation result is integrated into the proposed appearance model to further enhance it. The proposed framework easily obtains segmentation results because the local patches in the model serve as good seeds for the semi-supervised segmentation task. To solve the complexity problem attributable to the large number of patches, the Basin Hopping (BH) sampling method is introduced into the tracking framework. The BH sampling method significantly reduces computational complexity with the help of a deterministic local optimizer. Thus, the proposed appearance model could utilize a sufficient number of patches. The experimental results show that the present approach could track objects with drastically changing geometric appearance accurately and robustly.
提出了一种新的跟踪算法，用于跟踪随时间剧烈变化的目标的几何外观。为了跟踪这些目标，我们开发了一种基于局部补丁的外观模型，并提供了一种有效的在线更新方案，自适应地改变补丁之间的拓扑结构。在在线更新过程中，通过分析补丁的似然度景观来确定每个补丁的稳健性。基于此稳健性度量，提出的方法为每个补丁选择最佳特征，并随着时间的推移通过移动、删除或新添加补丁来修改补丁。此外，将粗糙的物体分割结果集成到所提出的外观模型中以进一步增强它。由于模型中的局部补丁可作为半监督分割任务的良好种子，因此该框架可以轻松地获得分割结果。为了解决由于补丁数量过多而导致的复杂性问题，将盆地跳跃 (BH) 采样方法引入到跟踪框架中。在确定性局部优化器的帮助下，BH 采样方法显著降低了计算复杂度。因此，所提出的外观模型可以利用足够数量的补丁。实验结果表明，该方法能够准确、稳健地跟踪具有剧烈变化的几何外观的目标。
