Temporally stable feature clusters for maritime object tracking in visible and thermal imagery
Data(s) |
25/08/2015
|
---|---|
Resumo |
This paper describes a new approach to detect and track maritime objects in real time. The approach particularly addresses the highly dynamic maritime environment, panning cameras, target scale changes, and operates on both visible and thermal imagery. Object detection is based on agglomerative clustering of temporally stable features. Object extents are first determined based on persistence of detected features and their relative separation and motion attributes. An explicit cluster merging and splitting process handles object creation and separation. Stable object clus- ters are tracked frame-to-frame. The effectiveness of the approach is demonstrated on four challenging real-world public datasets. |
Formato |
text |
Identificador |
http://centaur.reading.ac.uk/46525/1/2015_AVSS_MaritimeTracking_Osborne_Cane_Nawaz_Ferryman.pdf Osborne, C. <http://centaur.reading.ac.uk/view/creators/90005161.html>, Cane, T., Nawaz, T. <http://centaur.reading.ac.uk/view/creators/90006297.html> and Ferryman, J. <http://centaur.reading.ac.uk/view/creators/90000220.html> (2015) Temporally stable feature clusters for maritime object tracking in visible and thermal imagery. In: 12th IEEE International Conference on Advanced Video- and Signal-based Surveillance (AVSS2015), August 25-28, 2015, Karlsruhe, Germany, pp. 1-6. |
Idioma(s) |
en |
Relação |
http://centaur.reading.ac.uk/46525/ creatorInternal Osborne, Christopher creatorInternal Nawaz, Tahir creatorInternal Ferryman, James http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7301769 |
Tipo |
Conference or Workshop Item PeerReviewed |