![]() Although adaptations of deep learning-based approaches originally developed for human pose estimation have made animal pose estimation for single individuals possible 5, 6, 7, reliably tracking multiple, interacting animals and their poses remains a challenging problem, presenting an impediment to studies of social behaviors.ĭetecting body parts is sufficient for single-animal pose estimation (Fig. ![]() Methods for pose estimation, the task of predicting the location of animal body parts in images, have grown in popularity as a state-of-the-art requirement for behavioral quantification across disciplines including neuroscience 3 and ecology 4. Quantitative measurements of animal motion are foundational to the study of animal behavior 1, 2. ![]() This makes SLEAP usable for real-time applications, which we demonstrate by controlling the behavior of one animal on the basis of the tracking and detection of social interactions with another animal. SLEAP achieves greater accuracy and speeds of more than 800 frames per second, with latencies of less than 3.5 ms at full 1,024 × 1,024 image resolution. We applied SLEAP to seven datasets across flies, bees, mice and gerbils to systematically evaluate each approach and architecture, and we compare it with other existing approaches. SLEAP features an accessible graphical user interface, a standardized data model, a reproducible configuration system, over 30 model architectures, two approaches to part grouping and two approaches to identity tracking. ![]() This system enables versatile workflows for data labeling, model training and inference on previously unseen data. Here we present Social LEAP Estimates Animal Poses (SLEAP), a machine learning system for multi-animal pose tracking. While advances in deep learning and computer vision have enabled markerless pose estimation in individual animals, extending these to multiple animals presents unique challenges for studies of social behaviors or animals in their natural environments. ![]() The desire to understand how the brain generates and patterns behavior has driven rapid methodological innovation in tools to quantify natural animal behavior. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |