top of page
< Back

Multi-Object Tracking of Animals

Theoretical Ecology and Evolution Laboratory.
Indian Institute of Science, Bengaluru.

2015 - 2021

Multi-Object Tracking of Animals

1. Video recordings of animals are used for many research areas such as collective movement, animal space-use, animal censuses and behavioural neuroscience.They provide us with behavioural data at scales and resolutions not possible withmanual observations. Many automated methods are being developed to extractdata from such high-resolution videos. However, the task of animal detection andtracking for videos taken in natural settings remains challenging due to heterogeneous environments.


2. We present an end-to-end open-source package called Multi-Object Tracking inHeterogenous environments (MOTHe) 1 , a python-based application that usesa basic convolutional neural network for object detection. MOTHe allows researchers with minimal coding experience to track multiple animals in their natural habitat. It identifies animals even when individuals are stationary or partially camouflaged.


3. MOTHe has a Graphical User Interface (GUI) with functions for various tasksassociated with object detection, for example, finding animals in an image andtracking each individual. The algorithm’s parameters are well described on thehelp page along with example values for different types of tracking scenario.MOTHe doesn’t require any sophisticated infrastructure and can be run on basicdesktop computing units.


4. We demonstrate MOTHe on six video clips from two species in their naturalhabitat - wasp colonies on their nests (up to 12 individuals per colony) andantelope herds in four different types of habitats (up to 156 individuals in aherd). Using MOTHe, we can detect and track all individuals in these animalgroup videos. MOTHe’s computing time on a personal computer with 4 GB RAMand i5 processor is 5 minutes for a 30-second long ultra-HD (4K resolution) videorecorded at 30 frames per second.


5. MOTHe is available as an open-source repository with a detailed user guide anddemonstrations at Github (https://github.com/tee-lab/MOTHe-GUI).Publication:Rathore A., Sharma A., Sharma N., Torney C., Guttal V. (2020). Multi-Object Tracking inHeterogeneous environments (MOTHe) for animal space-use studies. bioRxiv doi-https://doi.org/10.1101/2020.01.10.899989








Publication:


Rathore A., Sharma A., Sharma N., Torney C., Guttal V. (2020). MultiObject Tracking in Heterogeneous environments (MOTHe) for animal space-use studies. bioRxiv doi-https://doi.org/10.1101/2020.01.10.899989


Logo by: Mohit Agarwal

bottom of page