Challenges of ground truth evaluation of multi-target tracking

Simple item page
dc.contributor.authorMilan, A.
dc.contributor.authorSchindler, K.
dc.contributor.authorRoth, S.
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition Workshops (2013 : Portland, Oregon)
dc.date.issued2013
dc.description.abstractEvaluating multi-target tracking based on ground truth data is a surprisingly challenging task. Erroneous or ambiguous ground truth annotations, numerous evaluation protocols, and the lack of standardized benchmarks make a direct quantitative comparison of different tracking approaches rather difficult. The goal of this paper is to raise awareness of common pitfalls related to objective ground truth evaluation. We investigate the influence of different annotations, evaluation software, and training procedures using several publicly available resources, and point out the limitations of current definitions of evaluation metrics. Finally, we argue that the development an extensive standardized benchmark for multi-target tracking is an essential step toward more objective comparison of tracking approaches.
dc.description.statementofresponsibilityAnton Milan, Konrad Schindler, Stefan Roth
dc.identifier.citationProceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013: pp.735-742
dc.identifier.doi10.1109/CVPRW.2013.111
dc.identifier.isbn9780769549903
dc.identifier.urihttp://hdl.handle.net/2440/83887
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeUSA
dc.rights© 2013 IEEE
dc.source.urihttp://dx.doi.org/10.1109/cvprw.2013.111
dc.titleChallenges of ground truth evaluation of multi-target tracking
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RA_hdl_83887.pdf
Size:
443.03 KB
Format:
Adobe Portable Document Format
Description:
Restricted Access
Download

Collections

Computer Science publications