2015 | OriginalPaper | Buchkapitel
Compressive Tracking Based on Particle Filter
verfasst von : Yun Gao, Hao Zhou, Guowu Yuan, Xuejie Zhang
Erschienen in: Computer Vision
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Robust object tracking has been a challenging issue due to pose variation, illumination change, abrupt motion, background clutter, and etc.. Compressive sensing theory provided a new and effective way for real-time object tracking. In this paper, a compressive tracking method based on Particle Filter (PFCT) was proposed. The candidate objects were predicted based on Particle Filter. The sparse random Gaussian matrix was as the measurement matrix. The element number of a measurement vector was set as a special value, which was different for each video sequence. The proposed PFCT method ran in real-time and outperformed FCT on many challenging video sequences in terms of efficiency, accuracy and robustness.