Robust Human Tracking to Occlusion in Crowded Scenes
Robust Human Tracking to Occlusion in Crowded Scenes
复制标题
DOI：
10.1109/dicta.2015.7371302
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Hiromasa Takada;K. Hotta
中科院分区：
文献类型：
--
作者：
Hiromasa Takada;K. Hotta
拥挤场景中的人体跟踪是一个具有挑战性的问题，因为经常发生遮挡。在本文中，我们提出了一种在线的人体跟踪方法，可以有效地处理遮挡。我们的方法自动改变学习率更新跟踪模型根据情况。如果跟踪目标被遮挡，则降低学习速率以减小遮挡的影响。然而，相似性得分会因跟踪目标的尺度变化以及遮挡而降低。为了判断遮挡或尺度变化，使用对数极坐标上的相似性分数。此外，搜索区域的大小也根据前一帧的遮挡信息而改变。使用PETS 2009数据集的实验表明，我们的方法提高了在拥挤的场景中的跟踪精度。
Human tracking in crowded scenes is a challenging problem because occlusion is frequently occurred. In this paper, we propose an online human tracking method which can handle occlusion effectively. Our method automatically changes a learning rate for updating tracking model according to the situation. If the tracking target is under occlusion, the learning rate decreases to reduce the influence of occlusion. However, the similarity score decreases by scale change of a tracking target as well as occlusion. To judge the occlusion or scale change, the similarity score on the Log-Polar coordinate is used. Furthermore, the size of search region is also changed according to the information about occlusion at previous frame. Experiments using the PETS2009 dataset show that our method improves tracking accuracy in crowded scenes.