Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering
Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering
复制标题
DOI：
10.1109/tpami.2018.2876253
复制
发表时间：
2020-01-01
影响因子：
23.6
通讯作者：
Schiele, Bernt
中科院分区：
文献类型：
--
作者：
Keuper, Margret;Tang, Siyu;Schiele, Bernt
计算机视觉的模型通常定义为w.r.t.诸如要分组的像素或w.r.t.诸如要被检测和跟踪的语义对象之类的高级概念。将自下而上的分组与自上而下的检测和跟踪相结合，尽管是非常可取的，但却是一个具有挑战性的问题。我们把这个联合问题描述为一个共同聚类问题，这个问题是有原则的，并且可以通过现有的算法来处理。我们证明了这种方法的有效性相结合的自下而上的运动分割分组的点轨迹与高层次的多目标跟踪聚类的边界框。我们表明，解决联合问题是有益的，在低层次上，在FBMS 59运动分割基准，并在高层次上，在多目标跟踪基准MOT15，MOT16，和MOT17的挑战，是国家的最先进的一些指标。
Models for computer vision are commonly defined either w.r.t. low-level concepts such as pixels that are to be grouped, or w.r.t. high-level concepts such as semantic objects that are to be detected and tracked. Combining bottom-up grouping with top-down detection and tracking, although highly desirable, is a challenging problem. We state this joint problem as a co-clustering problem that is principled and tractable by existing algorithms. We demonstrate the effectiveness of this approach by combining bottom-up motion segmentation by grouping of point trajectories with high-level multiple object tracking by clustering of bounding boxes. We show that solving the joint problem is beneficial at the low-level, in terms of the FBMS59 motion segmentation benchmark, and at the high-level, in terms of the Multiple Object Tracking benchmarks MOT15, MOT16, and the MOT17 challenge, and is state-of-the-art in some metrics.