Monitoring and tracking of mosquitoes using image processing is important to facilitate the mosquitos’ behaviour analysis automatically over longer period of times. In this paper, we propose a simple methodology to monitor mosquitos’ activity using multiple cameras optimally placed. In order to ensure optimal camera coverage for the area of observation and desired image quality; we propose to simulate the experimental setup in a 3D virtual environment to obtain one-off optimum camera placement parameters. Our proposed methodology is demonstrated to have improved the activity monitoring process using two cameras for accurate count of occluded mosquitoes and 3D trajectory path reconstruction. This framework will enable working out more challenging tasks of constructing 3D trajectories using information received from multiple low quality cameras, which provide inconsistent and discontinuous trajectories.
History
Pagination
548-555
Location
Istanbul, Turkey
Start date
2015-11-09
End date
2015-11-12
ISSN
0302-9743
eISSN
1611-3349
ISBN-13
9783319265605
Language
eng
Publication classification
E Conference publication, E1 Full written paper - refereed
Copyright notice
2015, Springer
Editor/Contributor(s)
Arik S, Huang T, Lin W, Liu Q
Title of proceedings
ICONIP 2015 : Neural information processing : 22nd International Conference, ICONIP 2015, Istanbul, Turkey, November 9-12, 2015 : proceedings
Event
Neural Information Processing. Conference (22nd : 2015 : Istanbul, Turkey)