Real-time tracker with fast recovery from target loss

Simple item page
dc.contributor.authorBay, A.
dc.contributor.authorSidiropoulos, P.
dc.contributor.authorVazquez, E.
dc.contributor.authorSasdelli, M.
dc.contributor.conferenceIEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP) (12 May 2019 - 17 May 2019 : Brighton, UK)
dc.date.issued2019
dc.description.abstractIn this paper, we introduce a variation of a state-of-the-art real-time tracker (CFNet), which adds to the original algorithm robustness to target loss without a significant computational overhead. The new method is based on the assumption that the feature map can be used to estimate the tracking confidence more accurately. When the confidence is low, we avoid updating the object’s position through the feature map; instead, the tracker passes to a single-frame failure mode, during which the patch’s low-level visual content is used to swiftly update the object’s position, before recovering from the target loss in the next frame. The experimental evidence provided by evaluating the method on several tracking datasets validates both the theoretical assumption that the feature map is associated to tracking confidence, and that the proposed implementation can achieve target recovery in multiple scenarios, without compromising the real-time performance.
dc.description.statementofresponsibilityAlessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez, Michele Sasdelli
dc.identifier.citationProceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing / sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society. ICASSP (Conference), 2019, vol.2019-May, pp.1932-1936
dc.identifier.doi10.1109/ICASSP.2019.8682171
dc.identifier.isbn147998132X
dc.identifier.isbn9781479981328
dc.identifier.issn1520-6149
dc.identifier.issn2379-190X
dc.identifier.orcidSasdelli, M. [0000-0003-1021-6369]
dc.identifier.urihttp://hdl.handle.net/2440/128708
dc.language.isoen
dc.publisherIEEE
dc.publisher.placePiscataway, NJ
dc.relation.ispartofseriesInternational Conference on Acoustics Speech and Signal Processing ICASSP
dc.rights©2019 IEEE
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/8671773/proceeding
dc.subjectReal-time tracking; Siamese convolutional neural networks; Correlation filters; Target loss recovery; Census transform
dc.titleReal-time tracker with fast recovery from target loss
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications