Multi-object tracking using feed-forward neural networks
Multi-object tracking using feed-forward neural networks
复制标题
DOI：
10.1109/socpar.2010.5686086
复制
发表时间：
2010-12
期刊：
影响因子：
--
通讯作者：
Uwe Jänen;C. Paul;Michael Wittke;J. Hähner
中科院分区：
文献类型：
--
作者：
Uwe Jänen;C. Paul;Michael Wittke;J. Hähner
在本文中，我们提出了一种稳健的多目标跟踪方法。通常，对象跟踪任务可以分为两个子任务：对象检测和对象标记。这里介绍的工作的主要焦点是一种使用神经网络在一系列视频帧中一致地标记对象的方法。由于目标检测算法的专业化，有必要将检测和标记分开以提高各自的技能。在评估中，我们表明所开发的标签对于遮挡具有鲁棒性，并且可以处理低物体检测率。
In this article we present an approach for robust multi-object tracking. Typically the task of object tracking can be divided into two subtasks: object detection and object labeling. The main focus of the work presented here is on an approach for consistently labeling objects across a series of video frames using neural networks. Due to the specialization of object detection algortihms it is necessary to divide detection and labeling to enhance their individual skills. In the evaluation we show that the developed labeling is robust against occlusions and can handle low object detection rates.