Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Multimedia tools and applications, 2020-06, Vol.79 (21-22), p.15095-15115
2020
Volltextzugriff (PDF)

Details

Autor(en) / Beteiligte
Titel
Spatial and semantic convolutional features for robust visual object tracking
Ist Teil von
  • Multimedia tools and applications, 2020-06, Vol.79 (21-22), p.15095-15115
Ort / Verlag
New York: Springer US
Erscheinungsjahr
2020
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
  • Robust and accurate visual tracking is a challenging problem in computer vision. In this paper, we exploit spatial and semantic convolutional features extracted from convolutional neural networks in continuous object tracking. The spatial features retain higher resolution for precise localization and semantic features capture more semantic information and less fine-grained spatial details. Therefore, we localize the target by fusing these different features, which improves the tracking accuracy. Besides, we construct the multi-scale pyramid correlation filter of the target and extract its spatial features. This filter determines the scale level effectively and tackles target scale estimation. Finally, we further present a novel model updating strategy, and exploit peak sidelobe ratio (PSR) and skewness to measure the comprehensive fluctuation of response map for efficient tracking performance. Each contribution above is validated on 50 image sequences of tracking benchmark OTB-2013. The experimental comparison shows that our algorithm performs favorably against 12 state-of-the-art trackers.

Weiterführende Literatur

Empfehlungen zum selben Thema automatisch vorgeschlagen von bX