Tracking multiple ants in a colony

Thomas Fasciano, Hoan Nguyen, Anna Dornhaus, Min C. Shin

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

8 Citations (Scopus)

Abstract

The automated tracking of social insects, such as ants, could dramatically increase the fidelity and amount of analyzed data for studying complex group behaviors. Recently, data association based multiple object tracking methods have shown promise in improving handling of occlusions. However, the tracking of ants in a colony is still challenging as (1) their motion is often sporadic and irregular and (2) they are mostly present the entire duration of video. In this paper, we propose to improve the data association based tracking of multiple ants. First, we model the ant's motion using a set of irregular motion features including random walk model. Second, we use the convergence of particle filter based tracking to match tracklets with a long temporal gap. Testing results of two-fold cross validation on a 10,000 frame video shows that our proposed method was able to reduce the number of fragments by 61% and ID switches by 57%.

Original languageEnglish (US)
Title of host publicationProceedings of IEEE Workshop on Applications of Computer Vision
Pages534-540
Number of pages7
DOIs
StatePublished - 2013
Event2013 IEEE Workshop on Applications of Computer Vision, WACV 2013 - Clearwater Beach, FL, United States
Duration: Jan 15 2013Jan 17 2013

Other

Other2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
CountryUnited States
CityClearwater Beach, FL
Period1/15/131/17/13

Fingerprint

Switches
Testing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Fasciano, T., Nguyen, H., Dornhaus, A., & Shin, M. C. (2013). Tracking multiple ants in a colony. In Proceedings of IEEE Workshop on Applications of Computer Vision (pp. 534-540). [6475065] https://doi.org/10.1109/WACV.2013.6475065

Tracking multiple ants in a colony. / Fasciano, Thomas; Nguyen, Hoan; Dornhaus, Anna; Shin, Min C.

Proceedings of IEEE Workshop on Applications of Computer Vision. 2013. p. 534-540 6475065.

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

Fasciano, T, Nguyen, H, Dornhaus, A & Shin, MC 2013, Tracking multiple ants in a colony. in Proceedings of IEEE Workshop on Applications of Computer Vision., 6475065, pp. 534-540, 2013 IEEE Workshop on Applications of Computer Vision, WACV 2013, Clearwater Beach, FL, United States, 1/15/13. https://doi.org/10.1109/WACV.2013.6475065
Fasciano T, Nguyen H, Dornhaus A, Shin MC. Tracking multiple ants in a colony. In Proceedings of IEEE Workshop on Applications of Computer Vision. 2013. p. 534-540. 6475065 https://doi.org/10.1109/WACV.2013.6475065
Fasciano, Thomas ; Nguyen, Hoan ; Dornhaus, Anna ; Shin, Min C. / Tracking multiple ants in a colony. Proceedings of IEEE Workshop on Applications of Computer Vision. 2013. pp. 534-540
@inproceedings{dbf8651e135142c79d8b5915fcf4d684,
title = "Tracking multiple ants in a colony",
abstract = "The automated tracking of social insects, such as ants, could dramatically increase the fidelity and amount of analyzed data for studying complex group behaviors. Recently, data association based multiple object tracking methods have shown promise in improving handling of occlusions. However, the tracking of ants in a colony is still challenging as (1) their motion is often sporadic and irregular and (2) they are mostly present the entire duration of video. In this paper, we propose to improve the data association based tracking of multiple ants. First, we model the ant's motion using a set of irregular motion features including random walk model. Second, we use the convergence of particle filter based tracking to match tracklets with a long temporal gap. Testing results of two-fold cross validation on a 10,000 frame video shows that our proposed method was able to reduce the number of fragments by 61{\%} and ID switches by 57{\%}.",
author = "Thomas Fasciano and Hoan Nguyen and Anna Dornhaus and Shin, {Min C.}",
year = "2013",
doi = "10.1109/WACV.2013.6475065",
language = "English (US)",
isbn = "9781467350532",
pages = "534--540",
booktitle = "Proceedings of IEEE Workshop on Applications of Computer Vision",

}

TY - GEN

T1 - Tracking multiple ants in a colony

AU - Fasciano, Thomas

AU - Nguyen, Hoan

AU - Dornhaus, Anna

AU - Shin, Min C.

PY - 2013

Y1 - 2013

N2 - The automated tracking of social insects, such as ants, could dramatically increase the fidelity and amount of analyzed data for studying complex group behaviors. Recently, data association based multiple object tracking methods have shown promise in improving handling of occlusions. However, the tracking of ants in a colony is still challenging as (1) their motion is often sporadic and irregular and (2) they are mostly present the entire duration of video. In this paper, we propose to improve the data association based tracking of multiple ants. First, we model the ant's motion using a set of irregular motion features including random walk model. Second, we use the convergence of particle filter based tracking to match tracklets with a long temporal gap. Testing results of two-fold cross validation on a 10,000 frame video shows that our proposed method was able to reduce the number of fragments by 61% and ID switches by 57%.

AB - The automated tracking of social insects, such as ants, could dramatically increase the fidelity and amount of analyzed data for studying complex group behaviors. Recently, data association based multiple object tracking methods have shown promise in improving handling of occlusions. However, the tracking of ants in a colony is still challenging as (1) their motion is often sporadic and irregular and (2) they are mostly present the entire duration of video. In this paper, we propose to improve the data association based tracking of multiple ants. First, we model the ant's motion using a set of irregular motion features including random walk model. Second, we use the convergence of particle filter based tracking to match tracklets with a long temporal gap. Testing results of two-fold cross validation on a 10,000 frame video shows that our proposed method was able to reduce the number of fragments by 61% and ID switches by 57%.

UR - http://www.scopus.com/inward/record.url?scp=84875611875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875611875&partnerID=8YFLogxK

U2 - 10.1109/WACV.2013.6475065

DO - 10.1109/WACV.2013.6475065

M3 - Conference contribution

SN - 9781467350532

SP - 534

EP - 540

BT - Proceedings of IEEE Workshop on Applications of Computer Vision

ER -