Paper Info
Title
Multiple ant tracking with global foreground maximization and variable target proposal distribution
Abstract
Motion and behavior analysis of social insects such as ants requires tracking many ants over time. This process is highly labor-intensive and tedious. Automatic tracking is challenging as ants often interact with one another, resulting in frequent occlusions that cause drifts in tracking. In addition, tracking many objects is computationally expensive. In this paper, we present a robust and efficient method for tracking multiple ants. We first prevent drifts by maximizing the coverage of foreground pixels at at global scale. Secondly, we improve speed by reducing markov chain length through dynamically changing the target proposal distribution for perturbed ant selection. Using a real dataset with ground truth, we demonstrate that our algorithm was able to improve the accuracy by 15% (resulting in 98% tracking accuracy) and the speed by 76%.
Year
DOI
Venue
2011
10.1109/WACV.2011.5711555
Applications of Computer Vision
Keywords
Field
DocType
Markov processes,computer graphics,hidden feature removal,object detection,optimisation,target tracking,Markov chain length,automatic tracking,behavior analysis,foreground pixels,global foreground maximization,motion analysis,multiple ant tracking,occlusion,perturbed ant selection,social insects,variable target proposal distribution
Computer vision,Object detection,Markov process,Pattern recognition,Computer science,Markov chain,Ground truth,Artificial intelligence,Pixel,Motion analysis,Computer graphics,Maximization
Conference
ISSN
ISBN
Citations 
1550-5790
978-1-4244-9496-5
8
PageRank 
References 
Authors
0.55
7
3
Name
Order
Citations
PageRank
Mary Fletcher180.55
Anna Dornhaus2172.83
Min C. Shin325725.41