The Evaluation of Gaussian Mixture Approximation of the Probability Hypothesis Density Approach for Multi-Object Tracking

Simple item page
dc.contributor.authorChen, Jiandan
dc.contributor.authorOyekanlu, Emmanuel A.
dc.contributor.authorOnidare, Samuel O.
dc.contributor.authorWlodek, Kulesza
dc.date.accessioned2018-06-07T09:49:38Z
dc.date.available2018-06-07T09:49:38Z
dc.date.issued2010
dc.description.abstractThis paper describes the performance of the Gaussian Mixture Probability Hypothesis Density (GMPHD) filter for multiple human tracking in an intelligent vision system. Human movement trajectories were observed with a camera and tracked by the GM-PHD filter. The filter multi-target tracking ability was validated by two random motion trajectories in the paper. To evaluate the filter performance in relation to the target movement, the motion velocity and angular velocity as key evaluation factors were proposed. A circular motion model was implemented for simplified analysis of the filter tracking performance. The results indicate that the mean absolute error defined as the difference between the filter prediction and the ground truth is proportional to the motion speed and angular velocity of the target. The error is only slightly affected by the tracking targets’ number.en_US
dc.identifier.urihttp://hdl.handle.net/123456789/387
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.subjectHuman Trackingen_US
dc.subjectProbability Hypothesis Densityen_US
dc.subjectPerformance Evaluationen_US
dc.subjectVision Systemen_US
dc.titleThe Evaluation of Gaussian Mixture Approximation of the Probability Hypothesis Density Approach for Multi-Object Trackingen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
IST PAPER FROM IEEE WEBSITE.pdf
Size:
248.31 KB
Format:
Adobe Portable Document Format
Description:
Main Article of an edited IEEE International conference proceedings
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections