8 91. Video recordings of animals are used for many areas of research such as collective movement, animal 10 space-use, animal censuses and behavioural neuroscience. They provide us with behavioural data at 11 scales and resolutions not possible with manual observations. Many automated methods are being 12 developed to extract data from these high-resolution videos. However, the task of animal detection and 13 tracking for videos taken in natural settings remains challenging due to heterogeneous environments. 14 2. We present an open-source end-to-end pipeline called Multi-Object Tracking in Heterogenous environ-15 ments (MOTHe), a python-based application that uses a basic convolutional neural network for object 16 detection. MOTHe allows researchers with minimal coding experience to track multiple animals in their 17 natural habitats. It identifies animals even when individuals are stationary or partially camouflaged.18 3. MOTHe has a command-line-based interface with one command for each action, for example, finding 19 animals in an image and tracking each individual. Parameters used by the algorithm are well described 20 in a configuration file along with example values for different types of tracking scenario. MOTHe 21 doesn't require any sophisticated infrastructure and can be run on basic desktop computing units.22 4. We demonstrate MOTHe on six video clips from two species in their natural habitat -wasp colonies 23 on their nests (up to 12 individuals per colony) and antelope herds in four different types of habitats 24 (up to 156 individuals in a herd). Using MOTHe, we are able to detect and track all individuals in 25 these animal group videos. MOTHe's computing time on a personal computer with 4 GB RAM and i5 26 processor is 5 minutes for a 30-second long ultra-HD (4K resolution) video recorded at 30 frames per 27 second. 28 5. MOTHe is available as an open-source repository with a detailed user guide and demonstrations at 29 Github (https://github.com/tee-lab/MOTHe).30 1 Introduction 31Video-recording of animals is increasingly becoming a norm in behavioural studies of space-use patterns, be-32 havioural neuroscience, animal movement and group dynamics [1, 2]. High-resolution images from aerial pho-33 tographs and videos can also be used for animal census [3, 4, 5]. This mode of observation can help us gather 34 high-resolution spatio-temporal data at unprecedented detail and help answer a novel set of questions that were 35 previously difficult to address. For example, we can obtain movement trajectories of animals to describe space-36 use patterns of animals, to infer fine-scale interactions between individuals within groups and to investigate 37 how these local interactions scale to emergent properties of groups [6, 7, 8, 9, 10, 11, 12, 13]. To address these 38 questions, as a first step, videos need to be converted into data -typically in the form of positions and trajec-39 tories of animals. Manually extracting this information from videos can be time-consuming, tedious and, often 40 not feasible...

No abstract

No abstract

Aerial imagery and video recordings of animals are used for many areas of research such as animal behaviour, behavioural neuroscience and field biology. Many automated methods are being developed to extract data from such high-resolution videos. Most of the available tools are developed for videos taken under idealised laboratory conditions. Therefore, the task of animal detection and tracking for videos taken in natural settings remains challenging due to heterogeneous environments. Methods that are useful for field conditions are often difficult to implement and thus remain inaccessible to empirical researchers. To address this gap, we present an open-source package called Multi-Object Tracking in Heterogeneous environments (MOTHe), a Python-based application that uses a basic convolutional neural network for object detection. MOTHe offers a graphical interface to automate the various steps related to animal tracking such as training data generation, animal detection in complex backgrounds and visually tracking animals in the videos. Users can also generate training data and train a new model which can be used for object detection tasks for a completely new dataset. MOTHe doesn’t require any sophisticated infrastructure and can be run on basic desktop computing units. We demonstrate MOTHe on six video clips in varying background conditions. These videos are from two species in their natural habitat—wasp colonies on their nests (up to 12 individuals per colony) and antelope herds in four different habitats (up to 156 individuals in a herd). Using MOTHe, we are able to detect and track individuals in all these videos. MOTHe is available as an open-source GitHub repository with a detailed user guide and demonstrations at: https://github.com/tee-lab/MOTHe-GUI.