AntVis: A web-based visual analytics tool for exploring ant movement data

Hu, Tianxiao; Zheng, Hao; Chen, Liang; Zhu, Sirou; Imirzian, Natalie; Zhang, Yizhe; Wang, Chaoli; Hughes, David; Chen, Danny Z.

doi:10.1016/j.visinf.2020.02.001

Cited by 6 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, AntVis [ 19 ] employs computer vision to visualize fluxes of ants moving in the same direction, without implementing individual ant identification over extended periods of time. Conceived for observation in natural conditions, AntVis identifies individual ants by accurately tracking their trajectories within the video frame, without relying on individual matrix code tags [ 39 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Integrating real-time data analysis into automatic tracking of social insects

et al. 2021

View full text Add to dashboard Cite

Automatic video tracking has become a standard tool for investigating the social behaviour of insects. The recent integration of computer vision in tracking technologies will probably lead to fully automated behavioural pattern classification within the next few years. However, many current systems rely on offline data analysis and use computationally expensive techniques to track pre-recorded videos. To address this gap, we developed BACH (Behaviour Analysis maCHine), a software that performs video tracking of insect groups in real time. BACH uses object recognition via convolutional neural networks and identifies individually tagged insects via an existing matrix code recognition algorithm. We compared the tracking performances of BACH and a human observer (HO) across a series of short videos of ants moving in a two-dimensional arena. We found that BACH detected ant shapes only slightly worse than the HO. However, its matrix code-mediated identification of individual ants only attained human-comparable levels when ants moved relatively slowly, and fell when ants walked relatively fast. This happened because BACH had a relatively low efficiency in detecting matrix codes in blurry images of ants walking at high speeds. BACH needs to undergo hardware and software adjustments to overcome its present limits. Nevertheless, our study emphasizes the possibility of, and the need for, further integrating real-time data analysis into the study of animal behaviour. This will accelerate data generation, visualization and sharing, opening possibilities for conducting fully remote collaborative experiments.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Although the technology underlying insect video tracking advances rapidly and significantly, many recently developed systems rely on offline data processing [11,[17][18][19][20][21]. This means that researchers often perform tracking on previously recorded videos and analyse data a posteriori.…”

Section: Introductionmentioning

confidence: 99%

Integrating real-time data analysis into automatic tracking of social insects

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The system identifies these episodes based on the relative position and orientation of matrix codes, confirming such identifications via custom computer vision algorithms. Contrarily, AntVis 33 employs computer vision to visualize fluxes of ants moving in the same direction, without implementing individual ant identification over extended periods of time. Conceived for observation in natural conditions, AntVis identifies individual ants by accurately tracking their trajectories within the video frame, without relying on individual matrix code tags 34 .…”

Section: Discussionmentioning

confidence: 99%

Integrating real-time data analysis into automatic tracking of social insect behavior

Sclocco

Sjy

Syp

et al. 2020

Preprint

View full text Add to dashboard Cite

Automatic video tracking has become a standard tool for investigating the social behavior of insects. The recent integration of computer vision in tracking technologies will likely lead to fully automated behavioral pattern classification within the next few years. However, most current systems rely on offline data analysis and use computationally expensive techniques to track pre-recorded videos. To address this gap, we developed BACH (Behavior Analysis maCHine), a software that performs video tracking of insect groups in real time. BACH uses object recognition via convolutional neural networks and identifies individually tagged insects via an existing matrix code recognition algorithm. We compared the tracking performances of BACH and a human observer across a series of short videos of ants moving in a 2D arena. We found that, concerning computer vision-based ant detection only, BACH performed only slightly worse than the human observer. Contrarily, individual identification only attained human-comparable levels when ants moved relatively slow, and fell when ants walked relatively fast. This happened because BACH had a relatively low efficiency in detecting matrix codes in blurry images of ants walking at high speeds. BACH needs to undergo hardware and software adjustments to overcome its present limits. Nevertheless, our study emphasizes the possibility of, and the need for, integrating real time data analysis into the study of animal behavior. This will accelerate data generation, visualization and sharing, opening possibilities for conducting fully remote collaborative experiments.

show abstract