OmniTrax (V_1.0.0)

Deep learning-based multi animal tracking and pose estimation Blender Add-on

OmniTrax is an open-source Blender Add-on designed for deep learning-driven multi-animal tracking and pose-estimation. It leverages recent advancements in deep-learning-based detection (YOLOv3, YOLOv4) and computationally inexpensive buffer-and-recover tracking techniques. OmniTrax integrates with Blender's internal motion tracking pipeline, making it an excellent tool for annotating and analyzing large video files containing numerous freely moving subjects. Additionally, it integrates DeepLabCut-Live for marker-less pose estimation on arbitrary numbers of animals, using both the DeepLabCut Model Zoo and custom-trained detector and pose estimator networks.

OmniTrax is designed to be a plug-and-play toolkit for biologists to facilitate the extraction of kinematic and behavioural data of freely moving animals. OmniTrax can, for example, be used in population monitoring applications, especially, in changing environments where background subtraction methods may fail. This ability can be amplified by using detection models trained on highly variable synthetically generated data. OmniTrax also lends itself well to annotating training and validation data for detector & tracker neural networks, or providing instance and pose data for size classification and unsupervised behavioural clustering tasks.

Notes on CPU-only version

OmniTrax CPU runs on both Windows 10 / 11 as well as Ubuntu systems

If you wish to run inference on CPU-only systems, you must use Blender version 2.92 to match dependencies!

GPU inference compatibility with the latest  release of Blender LTS 3.3!  

OmniTrax GPU is built for Windows 10 / 11.

Simply install the omni_trax.zip file from within Blender in the Addon tab, as described in the README. No need to unpack the file, but make sure to run Blender in Administrator mode for the installation of this addon as additional python packages will be installed automatically.

Notes on GPU version [recommended]

Install the correct CUDA & cudNN versions (11.2 and 8.1 respectively) mentioned in the readme for GPU support. The DLLs have been built specifically to run on machines with dedicated NVIDIA GPUs with compute capability of 6.1 or higher.