Multiple People Tracking Using Camera Networks with Overlapping Views

We present a novel framework for multiple pedestrian tracking using overlapping cameras in which the problems of object detection and data association are solved alternately. In each round of our algorithm, the people are detected by inference on a factor graph model at each time slice. The outputs...

Full description

Saved in:
Bibliographic Details
Main Authors: Wan Jiuqing, Li Achuan
Format: Article
Language:English
Published: Wiley 2015-01-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2015/591067
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849308824081530880
author Wan Jiuqing
Li Achuan
author_facet Wan Jiuqing
Li Achuan
author_sort Wan Jiuqing
collection DOAJ
description We present a novel framework for multiple pedestrian tracking using overlapping cameras in which the problems of object detection and data association are solved alternately. In each round of our algorithm, the people are detected by inference on a factor graph model at each time slice. The outputs of the inference, namely, the probabilistic occupancy maps, are used to define a cost network model. Data association is achieved by solving a min-cost flow problem on the resulting network model. The outputs of the data association, namely, the ground occupancy maps, are used to control the size of factors in graph model in the next round. By alternating between object detection and data association, a desirable compromise between complexity and accuracy is obtained. Experiments results on public datasets demonstrate the competitiveness of our method compared with other state-of-the-art approaches.
format Article
id doaj-art-1807aaeb20384df3af2c3b230a37869c
institution Kabale University
issn 1550-1477
language English
publishDate 2015-01-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-1807aaeb20384df3af2c3b230a37869c2025-08-20T03:54:20ZengWileyInternational Journal of Distributed Sensor Networks1550-14772015-01-011110.1155/2015/591067591067Multiple People Tracking Using Camera Networks with Overlapping ViewsWan JiuqingLi AchuanWe present a novel framework for multiple pedestrian tracking using overlapping cameras in which the problems of object detection and data association are solved alternately. In each round of our algorithm, the people are detected by inference on a factor graph model at each time slice. The outputs of the inference, namely, the probabilistic occupancy maps, are used to define a cost network model. Data association is achieved by solving a min-cost flow problem on the resulting network model. The outputs of the data association, namely, the ground occupancy maps, are used to control the size of factors in graph model in the next round. By alternating between object detection and data association, a desirable compromise between complexity and accuracy is obtained. Experiments results on public datasets demonstrate the competitiveness of our method compared with other state-of-the-art approaches.https://doi.org/10.1155/2015/591067
spellingShingle Wan Jiuqing
Li Achuan
Multiple People Tracking Using Camera Networks with Overlapping Views
International Journal of Distributed Sensor Networks
title Multiple People Tracking Using Camera Networks with Overlapping Views
title_full Multiple People Tracking Using Camera Networks with Overlapping Views
title_fullStr Multiple People Tracking Using Camera Networks with Overlapping Views
title_full_unstemmed Multiple People Tracking Using Camera Networks with Overlapping Views
title_short Multiple People Tracking Using Camera Networks with Overlapping Views
title_sort multiple people tracking using camera networks with overlapping views
url https://doi.org/10.1155/2015/591067
work_keys_str_mv AT wanjiuqing multiplepeopletrackingusingcameranetworkswithoverlappingviews
AT liachuan multiplepeopletrackingusingcameranetworkswithoverlappingviews