Multiple ant tracking with global foreground maximization and variable target proposal distribution

Mary Fletcher, Anna Dornhaus, Min C. Shin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

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%.

Original languageEnglish (US)
Title of host publication2011 IEEE Workshop on Applications of Computer Vision, WACV 2011
Pages570-576
Number of pages7
DOIs
StatePublished - 2011
Event2011 IEEE Workshop on Applications of Computer Vision, WACV 2011 - Kona, HI, United States
Duration: Jan 5 2011Jan 7 2011

Other

Other2011 IEEE Workshop on Applications of Computer Vision, WACV 2011
CountryUnited States
CityKona, HI
Period1/5/111/7/11

Fingerprint

Chain length
Markov processes
Pixels
Personnel

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Fletcher, M., Dornhaus, A., & Shin, M. C. (2011). Multiple ant tracking with global foreground maximization and variable target proposal distribution. In 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011 (pp. 570-576). [5711555] https://doi.org/10.1109/WACV.2011.5711555

Multiple ant tracking with global foreground maximization and variable target proposal distribution. / Fletcher, Mary; Dornhaus, Anna; Shin, Min C.

2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. p. 570-576 5711555.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fletcher, M, Dornhaus, A & Shin, MC 2011, Multiple ant tracking with global foreground maximization and variable target proposal distribution. in 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011., 5711555, pp. 570-576, 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011, Kona, HI, United States, 1/5/11. https://doi.org/10.1109/WACV.2011.5711555
Fletcher M, Dornhaus A, Shin MC. Multiple ant tracking with global foreground maximization and variable target proposal distribution. In 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. p. 570-576. 5711555 https://doi.org/10.1109/WACV.2011.5711555
Fletcher, Mary ; Dornhaus, Anna ; Shin, Min C. / Multiple ant tracking with global foreground maximization and variable target proposal distribution. 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. pp. 570-576
@inproceedings{b9ac81b041eb466fb6ea872b48ade40d,
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{\%}.",
author = "Mary Fletcher and Anna Dornhaus and Shin, {Min C.}",
year = "2011",
doi = "10.1109/WACV.2011.5711555",
language = "English (US)",
isbn = "9781424494965",
pages = "570--576",
booktitle = "2011 IEEE Workshop on Applications of Computer Vision, WACV 2011",

}

TY - GEN

T1 - Multiple ant tracking with global foreground maximization and variable target proposal distribution

AU - Fletcher, Mary

AU - Dornhaus, Anna

AU - Shin, Min C.

PY - 2011

Y1 - 2011

N2 - 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%.

AB - 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%.

UR - http://www.scopus.com/inward/record.url?scp=79952521097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952521097&partnerID=8YFLogxK

U2 - 10.1109/WACV.2011.5711555

DO - 10.1109/WACV.2011.5711555

M3 - Conference contribution

SN - 9781424494965

SP - 570

EP - 576

BT - 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011

ER -