University of Cape Coast Institutional Repository

Parallel kalman filter-based multi-human tracking in surveillance video

Show simple item record

dc.contributor.author Yussiff, Abdul-Lateef
dc.contributor.author Yong, Suet-Peng
dc.contributor.author Baharudin, Baharum B.
dc.date.accessioned 2021-07-28T13:20:38Z
dc.date.available 2021-07-28T13:20:38Z
dc.date.issued 2020
dc.identifier.issn 23105496
dc.identifier.uri http://hdl.handle.net/123456789/5781
dc.description 6p:, ill. en_US
dc.description.abstract A novel approach to robust and fexible person tracking using an algorithm that integrates state of the arts techniques; an Enhanced Person Detector (EPD) and Kalman fltering algorithm. This proposed algorithm employs multiple instances of Kalman Filter with complex assignment constraints using Graphics Processing Unit (GPU-NVDIA CUDA) as a parallel computing environment for tracking multiple persons even in the presence of occlusion. A Kalman flter is a recursive algorithm which predict the state variables and further uses the observed data to correct the predicted value. Data association in different frames is solved using Hungarian technique to link data in previous frame to the current frame. The benefit of this research is an adoption of standard Kalman Filter for multiple target tracking of humans in real time. This can further be used in all applications where human tracking is needed. The parallel implementation has increased the frame processing speed by 20- 30 percent over the CPU implementation en_US
dc.language.iso en en_US
dc.publisher University of Cape Coast en_US
dc.subject Human Tracking en_US
dc.subject Kalman Filter en_US
dc.subject Multi-person tracking en_US
dc.title Parallel kalman filter-based multi-human tracking in surveillance video en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search UCC IR


Advanced Search

Browse

My Account