Data association based ant tracking with interactive error correction

Nguyen, Hong-Thu; Fasciano, Thomas; Charbonneau, Daniel; Shin, Min Chul

doi:10.1109/wacv.2014.6836003

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the characteristics used for estimating the association probability are different for various types of objects. Therefore, researchers interactively adapt the association scoring function, thus improving tracking reliability [19].…”

Section: Data Association Methodsmentioning

confidence: 99%

Online tracking of ants based on deep association metrics: method, dataset and evaluation

Cao

Guo

Lin

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Tracking insect movement in a social group (such as ants) is challenging, because they are not only visually identical but also likely to perform intensive body contact and sudden movement adjustment (start/stop, direction turning). To address this challenge, we introduced an online multi-object tracking framework by combining both the motion and appearance information of ants. We obtained the appearance descriptors by using the ResNet model for offline training on a small (N=50) sample dataset. For online association, cosine similarity metric computes the matching degree between historical appearance sequences of the trajectory and the current detection. We validated our method in both indoor (lab-setup) and outdoor video sequences. The results show that the accuracy and precision of the model are 99.22%±0.37% and 91.93%±1.46% across 46041 testing samples, with real-time tracking performance. Additionally, we offered a public dataset of ant tracking with 46091 samples for future research in relevant domains.

show abstract

Section: Data Association Methodsmentioning

confidence: 99%

Online tracking of ants based on deep association metrics: method, dataset and evaluation

Cao

Guo

Lin

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…We used semi-automated tracking software that tracked the spatial positions of individual workers in the same videos we used for behavioral analysis to measure worker spatial fidelity, movement speeds, and proximity interaction networks (Poff et al 2012;Nguyen et al 2014). The software provides x, y coordinates for each worker at each frame of the video (at 24 fps) as well as the orientation of the worker.…”

Section: Spatial Datamentioning

confidence: 99%

Who Are the “Lazy” Ants? The Function of Inactivity in Social Insects and a Possible Role of Constraint: Inactive Ants Are Corpulent and May Be Young and/or Selfish

Charbonneau

Poff

Nguyen

et al. 2017

Integrative and Comparative Biology

Self Cite

View full text Add to dashboard Cite

Social insect colonies are commonly thought of as highly organized and efficient complex systems, yet high levels of worker inactivity are common. Although consistently inactive workers have been documented across many species, very little is known about the potential function or costs associated with this behavior. Here we ask what distinguishes these "lazy" individuals from their nestmates. We obtained a large set of behavioral and morphological data about individuals, and tested for consistency with the following evolutionary hypotheses: that inactivity results from constraint caused by worker (a) immaturity or (b) senescence; that (c) inactive workers are reproducing; that inactive workers perform a cryptic task such as (d) acting as communication hubs or (e) food stores; and that (f) inactive workers represent the "slow-paced" end of inter-worker variation in "pace-of-life." We show that inactive workers walk more slowly, have small spatial fidelity zones near the nest center, are more corpulent, are isolated in colony interaction networks, have the smallest behavioral repertoires, and are more likely to have oocytes than other workers. These results are consistent with the hypotheses that inactive workers are immature and/or storing food for the colony; they suggest that workers are not inactive as a consequence of senescence, and that they are not acting as communication hubs. The hypotheses listed above are not mutually exclusive, and likely form a "syndrome" of behaviors common to inactive social insect workers. Their simultaneous contribution to inactivity may explain the difficulty in finding a simple answer to this deceptively simple question.

show abstract

Accurate detection and tracking of ants in indoor and outdoor environments

Cao

Guo

2020

Preprint

View full text Add to dashboard Cite

Monitoring social insects' activity is critical for biologists researching their group mechanism. Manually labelling individual insects in a video is labour-intensive. Automated tracking social insects is particularly challenging: (1) individuals are small and similar in appearance; (2) frequent interactions with each other cause severe and long-term occlusion. We propose a detection and tracking framework for ants by: (1) adopting a two-stage object detection framework using ResNet-50 as backbone and coding the position of regions of interest to locate ants accurately; (2) using the ResNet model to develop the appearance descriptors of ants; (3) constructing long-term appearance sequences and combining them with motion information to achieve online tracking. To validate our method, we build a video database of ant colony captured in both indoor and outdoor scenes. We achieve a state-of-the-art performance of 95.7% mMOTA and 81.1% mMOTP in indoor videos, 81.8% mMOTA and 81.9% mMOTP in outdoor videos. Our method runs 6-10 times faster than existing methods for insect tracking. The datasets and code are made publicly available, we aim to contribute to an automated tracking tool for biologists in relevant domains.

show abstract

Data association based ant tracking with interactive error correction

Cited by 4 publications

References 14 publications

Online tracking of ants based on deep association metrics: method, dataset and evaluation

Online tracking of ants based on deep association metrics: method, dataset and evaluation

Who Are the “Lazy” Ants? The Function of Inactivity in Social Insects and a Possible Role of Constraint: Inactive Ants Are Corpulent and May Be Young and/or Selfish

Accurate detection and tracking of ants in indoor and outdoor environments

Contact Info

Product

Resources

About