Human Mobility Monitoring in Very Low Resolution Visual Sensor Network

Autor: Samuel Van de Velde, Maarten Slembrouck, Nyan Bo Bo, Wilfried Philips, Junzhi Guan, Dirk Van Haerenborgh, Heidi Steendam, Jorge Nino, Francis Deboeverie, Hamid Aghajan, Richard Kleihorst, Xingzhe Xie, Mohamed Eldib, Peter Veelaert
Jazyk: angličtina
Rok vydání: 2014
Předmět:
Technology and Engineering
Computer science
Visual sensor network
Image processing
Walking
Motor Activity
lcsh:Chemical technology
Tracking (particle physics)
Biochemistry
Sensitivity and Specificity
Article
Analytical Chemistry
Pattern Recognition
Automated
Computer Communication Networks
Image Interpretation
Computer-Assisted
Photography
Humans
lcsh:TP1-1185
Computer vision
Whole Body Imaging
low resolution imagery
Electrical and Electronic Engineering
Instrumentation
Ground truth
Signal processing
Pixel
business.industry
Reproducibility of Results
Tracking system
Signal Processing
Computer-Assisted
Equipment Design
tracking
Actigraphy
Atomic and Molecular Physics
and Optics
Equipment Failure Analysis
visual sensor network
Pattern recognition (psychology)
distributed processing
mobility analysis
Artificial intelligence
business
Zdroj: Sensors
Volume 14
Issue 11
Pages 20800-20824
Sensors (Basel, Switzerland)
SENSORS
Sensors, Vol 14, Iss 11, Pp 20800-20824 (2014)
ISSN: 1424-8220
DOI: 10.3390/s141120800
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: