Publication
Segment tracking via a spatiotemporal linking process including feedback stabilization in an n-d lattice model
Journal Article (2009)
Journal
Sensors
Pages
9355-9379
Volume
9
Number
11
Doc link
http://www.mdpi.com/1424-8220/9/11/9355
File
Abstract
Model-free tracking is important for solving tasks such as moving-object tracking and action recognition in cases where no prior object knowledge is available. For this purpose, we extend the concept of spatially synchronous dynamics in spin-lattice models to the spatiotemporal domain to track segments within an image sequence. The method is related to synchronization processes in neural networks and based on superparamagnetic clustering of data. Spin interactions result in the formation of clusters of correlated spins, providing an automatic labeling of corresponding image regions. The algorithm obeys detailed balance. This is an important property as it allows for consistent spin-transfer across subsequent frames, which can be used for segment tracking. In the tracking process the correct equilibrium will, thus, always be found, which is an important advance as compared to other, more heuristic, tracking procedures. In the case of long image sequences, i.e. movies, the algorithm is augmented with a feedback mechanism, further stabilizing segment tracking.
Categories
pattern recognition.
Author keywords
image segmentation
Scientific reference
B. Dellen, E.E. Aksoy and F. Wörgötter. Segment tracking via a spatiotemporal linking process including feedback stabilization in an n-d lattice model. Sensors, 9(11): 9355-9379, 2009.
Follow us!