Pixel Level Tracking of Multiple Targets in Crowded Environments-猫眼课题宝

DOI：

10.1007/978-3-319-48881-3_49

发表时间：

2016-10

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

M. Babaee;Yue You;G. Rigoll

研究了在拥挤环境下利用检测跟踪算法对多目标进行跟踪的问题。虽然这些技术是相当成功的，但它们遭受关于检测框中的目标的非常详细的信息的丢失，这在许多应用中是非常期望的，如活动识别。为了解决这个问题，我们提出了一种方法，跟踪超像素，而不是多视图视频序列中的检测框。具体来说，我们首先从检测框中提取超像素，然后将它们在每个检测框中关联起来，经过几个视图和时间步长，从而实现超像素的组合分割，重建和跟踪。我们构建了一个流图，并将视觉和几何线索的全局优化框架，以尽量减少其成本。因此，我们同时实现分割，重建和跟踪的视频目标。实验结果证实，所提出的方法优于国家的最先进的跟踪技术，同时实现可比的分割结果。

Tracking of multiple targets in a crowded environment using tracking by detection algorithms has been investigated thoroughly. Although these techniques are quite successful, they suffer from the loss of much detailed information about targets in detection boxes, which is highly desirable in many applications like activity recognition. To address this problem, we propose an approach that tracks superpixels instead of detection boxes in multi-view video sequences. Specifically, we first extract superpixels from detection boxes and then associate them within each detection box, over several views and time steps that lead to a combined segmentation, reconstruction, and tracking of superpixels. We construct a flow graph and incorporate both visual and geometric cues in a global optimization framework to minimize its cost. Hence, we simultaneously achieve segmentation, reconstruction and tracking of targets in video. Experimental results confirm that the proposed approach outperforms state-of-the-art techniques for tracking while achieving comparable results in segmentation.

Pixel Level Tracking of Multiple Targets in Crowded Environments

文献摘要

相似文献