No manual annotation
Training images and labels are generated automatically from the input video after you configure foreground segmentation.
AMADEUS: Annotation-free multi-animal tracking
AMADEUS tracks individual animals and estimates their oriented bounding boxes (OBBs) and head direction without manual training annotation. It learns from interaction images synthesized from the input video to track animals during crossings and crowding.
AMADEUS 1.2.8News
Oct 29, 2026 AMADEUS v1.2.8 was released. You can update using the Update button in the GUI.
Oct 16, 2026 Add-on support was added. See Add-ons.
Sep 26, 2026 The AMADEUS preprint is now available.
AMADEUS features
Batch processing
Configure segmentation, then specify the animal count, overlap severity, and whether animals move backward. Training and tracking then run automatically.
Graphical user interface
Use the graphical interface to configure segmentation, run processing stages, and review and correct tracking results.
Position, shape and direction estimation
Each animal is represented by an oriented bounding box (OBB) enclosing its body, together with its head direction.
Robust to interactions
Training on synthetic interaction images supports tracking during crossings and crowding.
Works with diverse videos
AMADEUS can analyze laboratory videos of diverse species.
Workflow
- Open Easy Tracking, follow the on-screen guidance to select the input video, then select Launch Segmentation.
- In Segmentation, adjust the settings so that the animals are properly extracted from the background, then select Analyze.
- Adjust the red lines (lower and upper bounds) on the box plot (or the Absolute range) so that isolated individuals are shown in blue and contacting animals, fragments, and other outliers are shown in orange, then select Processing. When processing finishes, AMADEUS automatically returns to Easy Tracking.
- Enter the animal count, select the overlap severity and whether animals move backward, then select Processing.
- Review the result video and CSV. Use Refinement to correct remaining errors if needed.
Install and launch
Recommended environment
AMADEUS supports NVIDIA GPUs on Windows and Linux, Apple Silicon on macOS, and some AMD GPUs via ROCm.
For NVIDIA and AMD GPUs, 8 GB or more of VRAM is recommended, although the required memory depends on factors such as video resolution and the number of animals. AMADEUS has also been confirmed to run on GPUs with 4 GB of VRAM.
Download and run the installer for your operating system. Initial setup requires an internet connection.
If you encounter an error, please contact Yusuke Notomi at jpmyrmecol [at] gmail.com and include your operating system, installation method, and the error message.
Recommended recording conditions
AMADEUS learns directly from the input videos, so tracking performance depends on recording conditions. The following conditions are recommended.
- For head direction estimation, a clear body axis and visually distinguishable front and rear. Use Without direction estimation when front and rear cannot be distinguished.
- A fixed camera viewing the animals from above, with movement approximately confined to a two-dimensional plane.
- Stable illumination, an essentially static background, and sufficient contrast between the animals and the background.
- Sufficient spatial resolution, frame rate, and shutter speed for reliable visual tracking in each frame.
- Sufficient periods in which animals are separated from one another. Images of isolated individuals are used to generate training data.
- A constant number of animals throughout the video. Variable population mode is also available, but identity association tends to be less reliable.
Training and analysis videos may be recorded separately, provided that the recording conditions are the same.
Citation
Preprint: Notomi et al. (2026), AMADEUS: Annotation-free multi-animal direction estimation using self-supervised learning. See the Publication page for the recommended citation format.
License
AMADEUS is released under the GNU Affero General Public License v3.0 only (AGPL-3.0-only). Bundled third-party components remain subject to their respective licenses. See LICENSE and third-party license information for details.
The mouse footage in the demo video uses mice_10_600x686_40Hz_6min.mp4 from the dataset published by Li et al. (CC BY 4.0).
The fish footage in the demo video uses the Fish dataset released by Itoh et al. for the Fish Tracking Challenge 2024 (CC BY-NC-SA 4.0).
The fruit fly footage in the demo video was used in the paper describing the behavior detection approach YORU (Yamanouchi et al., 2026, Science Advances). It was provided directly by the authors.