Mustatil 5.6

Now with ADAF detection and RF-DETR, training and detection.

The setup exe is better than the conda launcher.

Mustatil 5.5

Added an review tab.
New blocks in AI Pipeline.

Mustatil 5.4

Added experimental support for Faster R-CNN, Mask R-CNN, U-Net and SAM/SAM2 workflows.
Added optional video detection experiments for AI model testing.
Improved GIS tooling with Rasterio, GDAL/OGR and GMT console support.
Improved geospatial conversion utilities for raster, vector, GeoPackage and model workflows.
Improved handling of large-image and satellite-map detection workflows.
Added more robust support for GeoPackage export and GIS-based review.
Continued focus on offline desktop use, large raster analysis, annotation, YOLO training and geospatial AI detection.

Mustatil 5.3

Now all detections are chunked.

Mustatil 5.2

This release extends Mustatil as a GIS-level AI vision workspace for remote sensing, archaeological detection, annotation, training, and geospatial AI pipelines. In addition to the existing YOLO workflow, the software now includes experimental support for several additional model families, including Google OWLv2, Grounding DINO, LAE-DINO, Faster R-CNN, Mask R-CNN, U-Net semantic segmentation, and SAM2-assisted segmentation.

The new model integrations expand Mustatil from a YOLO-based detection and training environment into a broader multi-model AI workspace. Faster R-CNN and Mask R-CNN provide alternative region-based object detection workflows, U-Net enables semantic segmentation from project annotations, and SAM2 can be used as a segmentation refinement step from existing detection boxes. These functions can be accessed through dedicated tabs and integrated into the visual AI pipeline using selectable AI model blocks, while existing FormLearner and rule/IF logic blocks remain available.

The update is designed for large-image and geospatial workflows, including satellite-map detection, GeoTIFF-based analysis, project-based training, visual review, and export of results to GIS-compatible formats such as GeoPackage. This makes Mustatil suitable for remote sensing workflows where object detection, segmentation, post-processing, and GIS export need to be combined in one offline desktop application.

Mustatil 5.1

Mustatil-5.1

Update README.md

Mustatil 5

Mustatil also includes experimental support for additional AI vision models beyond standard YOLO. The Google OWL-ViT / OWLv2 model enables open-vocabulary object detection from text prompts. Grounding DINO adds powerful text-guided detection for flexible object search, while LAE-DINO provides an advanced DINO-based workflow with project-based dataset creation and training support. These models extend Mustatil from a YOLO GIS workspace into a broader AI detection and training environment.

Fixed some bugs.
New models
LAE-Dino Training

Mustatil 4

Added unlimited classes. Select classes at detection tab.
Zoom feature at annotation tab.
Export classes as GPKG.
Export all classes as GPKG in pipeline tab.

The mac os installer is experimental but it worked for me after many hours of waiting. I hope that most functions are usable. Unfortunately you need to click on the start_mustatil.command file or setup file in the installation directiory.

Mustatil 3.5

Fixed Piplines, CUDA
added checkbox in detection and satellite detection to only view positives. Unfortuanelty flase positives were shown too.

Mustatil 3.4

Added a Yolo Pipeline Tab
Now with cuda support