文章基本信息

标题：Using Feed-Forward Neural Networks for Data Association on Multi-Object Tracking Tasks
本地全文：下载
作者：Uwe Jaenen ; Carsten Grenz ; Christian Paul 等
期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2012
卷号：4
页码：383-391
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：This article presents an approach for data associ- ation in single camera, multi-object tracking scenarios using feed-forward neural networks (FFNN). The challenges of data association are object occlusions and changing features which are used to describe objects during the process. The presented algorithm within this article can be applied to any kind of ob- ject which has to be tracked, e.g. persons and vehicles. This approach arises within a project to detect critical behavior of persons. Besides, person tracking is one of the most challeng- ing scenarios. People have different velocities and often change the moving direction. In addition, a variety of occlusions are caused by the movement as a group. Also in most surveillance scenarios the illumination conditions are not optimal. The us- age of a feed-forward neural network is a mostly new approach in this research field. The advantage is the lightweight com- putational complexity and the fixed termination time in con- trast to recursive neural networks like Hopfield networks which are used for plot association during radar tracking. FFNN is a non-probabilistic approach in contrast to common algorithms within this filed. They deliver decisions not probability values. The handling of the FFNN output will be presented in this arti- cle. During the evaluation we will show that the developed ap- proach is capable to handle completely different scenarios like tracking people moving mostly straight forward but also com- plex scenarios like a soccer game.
关键词：single camera; multi-object tracking; data association; ; feed-forward; neural network