Format

Send to

Choose Destination
Sensors (Basel). 2014 Nov 4;14(11):20800-24. doi: 10.3390/s141120800.

Human mobility monitoring in very low resolution visual sensor network.

Author information

1
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. Nyan.BoBo@telin.ugent.be.
2
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. francis.deboeverie@ugent.be.
3
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. meldib@telin.ugent.be.
4
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. jguan@telin.ugent.be.
5
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. xxie@telin.ugent.be.
6
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. jorge.nino@telin.ugent.be.
7
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. dirk.vanhaerenborgh@telin.ugent.be.
8
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. mslembro@telin.ugent.be.
9
Digital Communications, Gent University/iMinds, Gent 9000, Belgium. Samuel.VandeVelde@telin.ugent.be.
10
Digital Communications, Gent University/iMinds, Gent 9000, Belgium. Heidi.Steendam@telin.ugent.be.
11
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. peter.veelaert@ugent.be.
12
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. richard@kleihorst.com.
13
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. Hamid.Aghajan@UGent.be.
14
Image Processing and Interpretation, Gent University/iMinds, Gent 9000, Belgium. philips@telin.UGent.be.

Abstract

This paper proposes an automated system for monitoring mobility patterns using a network of very low resolution visual sensors (30 × 30 pixels). The use of very low resolution sensors reduces privacy concern, cost, computation requirement and power consumption. The core of our proposed system is a robust people tracker that uses low resolution videos provided by the visual sensor network. The distributed processing architecture of our tracking system allows all image processing tasks to be done on the digital signal controller in each visual sensor. In this paper, we experimentally show that reliable tracking of people is possible using very low resolution imagery. We also compare the performance of our tracker against a state-of-the-art tracking method and show that our method outperforms. Moreover, the mobility statistics of tracks such as total distance traveled and average speed derived from trajectories are compared with those derived from ground truth given by Ultra-Wide Band sensors. The results of this comparison show that the trajectories from our system are accurate enough to obtain useful mobility statistics.

PMID:
25375754
PMCID:
PMC4279512
DOI:
10.3390/s141120800
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center