PT - JOURNAL ARTICLE AU - Akanksha Rathore AU - Ananth Sharma AU - Nitika Sharma AU - Vishwesha Guttal TI - Multi-Object Tracking in Heterogeneous environments (MOTHe) for animal space-use studies AID - 10.1101/2020.01.10.899989 DP - 2020 Jan 01 TA - bioRxiv PG - 2020.01.10.899989 4099 - http://biorxiv.org/content/early/2020/01/13/2020.01.10.899989.short 4100 - http://biorxiv.org/content/early/2020/01/13/2020.01.10.899989.full AB - Videographic observations of animals are important for studying many ecological phenomena such as collective movement, space use patterns of animals and animal census. They provide us with behavioural data at scales and resolutions which are not possible with manual observations. However, extracting data from these high-resolution videos is challenging, specially in the natural settings due to heterogeneity in the habitat.We present an open-source end-to-end pipeline called Multi-Object Tracking in Heterogenous environments (MOTHe), a python based repository that uses convolutional neural network for object detection. MOTHe allows researchers with minimal coding experience to track multiple animals in the natural settings. It identifies animals even when individuals are stationary or camouflaged with the background.MOTHe has a command-line-based interface with one command for each action, for example, finding animals in an image and tracking each individual. Parameters used by the algorithm are well described in a configuration file along with example values for different types of tracking scenario. MOTHe doesn’t require any sophisticated infrastructure and can be run on basic desktop computing units.We demonstrate MOTHe on six video clips from two species in their natural habitat - wasp groups on their natural nests and antelope herds in four different type of habitats. Maximum group size in example videos for wasp colonies is 12 and for blackbuck herds is 156; we were able to detect and track all the individuals in these videos. MOTHe’s computing time on a personal computer with 4 GB RAM and i5 processor is 5 minutes for a 30 second long ultra-HD (4K resolution) video at 30 FPS.MOTHe is available as an open-source repository with detailed user guide and demonstrations via Github.Link: https://github.com/aakanksharathore/MOTHe