D-Track—A semi-automatic 3D video-tracking technique to analyse movements and routines of aquatic animals with application to captive dolphins

Rachinas-Lopes, Patrícia; Ribeiro, Ricardo Pereira; Santos, Manuel Eduardo dos; Costa, Rui M.

doi:10.1371/journal.pone.0201614

Cited by 9 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, hand-tracking is time consuming and can be inefficient when hundreds of hours of data have been collected from multiple sensors. Recent efforts have been made to automate this process for cameras, primarily through heuristically-crafted computer-vision techniques [ 14 , 15 ]. However, these techniques were either limited in execution due to prohibitive costs (e.g.…”

Section: Introductionmentioning

confidence: 99%

Computer-vision object tracking for monitoring bottlenose dolphin habitat use and kinematics

et al. 2022

View full text Add to dashboard Cite

This research presents a framework to enable computer-automated observation and monitoring of bottlenose dolphins (Tursiops truncatus) in a zoo environment. The resulting approach enables detailed persistent monitoring of the animals that is not possible using manual annotation methods. Fixed overhead cameras were used to opportunistically collect ∼100 hours of observations, recorded over multiple days, including time both during and outside of formal training sessions, to demonstrate the viability of the framework. Animal locations were estimated using convolutional neural network (CNN) object detectors and Kalman filter post-processing. The resulting animal tracks were used to quantify habitat use and animal kinematics. Additionally, Kolmogorov-Smirnov analyses of the swimming kinematics were used in high-level behavioral mode classification. The object detectors achieved a minimum Average Precision of 0.76, and the post-processed results yielded 1.24 × 107 estimated dolphin locations. Animal kinematic diversity was found to be lowest in the morning and peaked immediately before noon. Regions of the zoo habitat displaying the highest activity levels correlated to locations associated with animal care specialists, conspecifics, or enrichment. The work presented here demonstrates that CNN object detection is viable for large-scale marine mammal tracking, and results from the proposed framework will enable future research that will offer new insights into dolphin behavior, biomechanics, and how environmental context affects movement and activity.

show abstract

Section: Introductionmentioning

confidence: 99%

Computer-vision object tracking for monitoring bottlenose dolphin habitat use and kinematics

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Several studies have explained animal motion from a biological perspective (Baker et al, 2013), but few have studied physics in the scope of science. It is because analyzing the aquatic animals' motion is a process that takes a long time, and the subjective tendency, proneness to errors due to the fatigue factor of the researcher (Rachinas-Lopes et al, 2018). Therefore, investigating natural phenomena in the motion of aquatic animals becomes a tight thought, but it becomes easy using technology.…”

Section: Introductionmentioning

confidence: 99%

Jumping Motion of Gourami Fish Using Tracker Software as a Mechanical Energy Conservation Practicum

Ilma

Kuswanto

Hujatulatif

2022

jppipa, pendidikan ipa, fisika, biologi, kimia

View full text Add to dashboard Cite

One of the phenomena of gourami fish is the jumping motion. In analyzing the fish motion, errors are often experienced in observations, tend to be subjective or take a long time. An alternative software to analyze the fish motion is the Tracker software. The study aims to analyze the video of the Gourami fish motion phenomenon using Tracker software in the mechanical energy conservation practicum. This type of research is experimental research. Based on the results, the greater the mass of the fish indicates the greater the kinetic energy and potential energy in the motion of the fish. Kinetic energy depends on the mass and speed of the Gourami fish jumping. While the potential energy depends on the height of the Gourami fish when jumping. It is also affected by the fish's mass and the acceleration of gravity. The video analysis of the motion of the jumping gourami using Tracker can be used in science learning, especially in physics practicum about the law of conservation of mechanical energy

show abstract

“…This hand-tracking is time consuming and can be inefficient when hundreds of hours of data have been collected from multiple sensors. Recent efforts have been made to automate this process for cameras, primarily through heuristically-crafted computer-vision techniques [19,20]. However, these techniques were either limited in execution due to prohibitive costs (e.g.…”

Section: Introductionmentioning

confidence: 99%

Vision-based monitoring and measurement of bottlenose dolphins’ daily habitat use and kinematics

Gabaldon

Ding

Lauderdale

et al. 2021

Preprint

View full text Add to dashboard Cite

This research presents a framework to enable computer-automated observation and monitoring of bottlenose dolphins (Tursiops truncatus) in a professionally managed environment. Results from this work provide insight into the dolphins' movement patterns, kinematic diversity, and how changes in the environment affect their dynamics. Fixed overhead cameras were used to collect ~100 hours of observations, recorded over multiple days including time both during and outside of formal training sessions. Animal locations were estimated using convolutional neural network (CNN) object detectors and Kalman filter post-processing. The resulting animal tracks were used to quantify habitat use and animal dynamics. Additionally, Kolmogorov-Smirnov analyses of the swimming kinematics were used for high-level behavioral mode classification. The detectors achieved a minimum Average Precision of 0.76. Performing detections and post-processing yielded 1.24x10^7 estimated dolphin locations. Animal kinematic diversity was found to be lowest in the morning and peaked immediately before noon. Regions of the habitat displaying the highest activity levels correlated to locations associated with animal care specialists, conspecifics, or enrichment. The work presented here demonstrates that CNN object detection is not only viable for large-scale marine mammal tracking, it also enables automated analyses of dynamics that provide new insight into animal movement and behavior.

show abstract

D-Track—A semi-automatic 3D video-tracking technique to analyse movements and routines of aquatic animals with application to captive dolphins

Cited by 9 publications

References 29 publications

Computer-vision object tracking for monitoring bottlenose dolphin habitat use and kinematics

Computer-vision object tracking for monitoring bottlenose dolphin habitat use and kinematics

Jumping Motion of Gourami Fish Using Tracker Software as a Mechanical Energy Conservation Practicum

Vision-based monitoring and measurement of bottlenose dolphins’ daily habitat use and kinematics

Contact Info

Product

Resources

About