Home › AI & machine learning › Vector To YOLO
Vector To YOLO QGIS 4 compatibility
Not QGIS 4 ready Active
Not yet — the latest version declares max QGIS version 3.99.0, so it is not offered to QGIS 4 users.
This plugin generates image chips for YOLO training
About
VecToYOLO: Geospatial Training Data Generator VecToYOLO is a powerful QGIS plugin designed to streamline the creation of deep learning datasets. It automates the process of converting large-scale satellite imagery or drone orthomosaics into localized image "chips" (patches) with corresponding label files, formatted specifically for the YOLO (You Only Look Once) object detection and segmentation framework. Core Features Dual Task Support: Supports both Object Detection (bounding boxes) and Instance Segmentation (polygon-to-mask conversion). Flexible Data Handling: * 8-bit Drone Orthomosaics: Standard RGB processing. 16-bit Satellite Imagery: Automatic reflectance scaling (e.g., Sentinel-2 L2A) to 8-bit PNG for model compatibility. Advanced Data Splitting: Choose between Random splitting or Spatial splitting (using geographic rows) to ensure more robust validation and prevent data leakage. Customizable Overlap: Control the overlap percentage between chips—crucial for small object detection or continuous landcover mapping. Ready-to-Train Output: Generates a structured directory with train/ and val/ folders, a classes.txt file, and a pre-configured data.yaml file tailored for Kaggle, Google Colab, or Local environments. How it Works Alignment: Automatically reprojects your vector annotations to match the CRS of your raster. Tiling: Iterates through your specified map extent, creating image tiles based on your desired chip size and overlap. Label Mapping: Maps vector attributes to class IDs and converts geographic coordinates into the normalized YOLO format.
| Author | Yogi Satrio Wijoyo |
|---|---|
| Downloads | 434 |
| Latest version | 0.1 (experimental) |
| Last updated | 2026-03-26 (204 days ago) |
| Min QGIS | 3.0.0 |
| Max QGIS | 3.99.0 |
| QGIS 4 ready | No |
| Maintenance | Active |
| Category | AI & machine learning |
| Tags | vector, machine learning, computer vision, yolo, labeling, raster, semantic segmentation |
Homepage · Repository · Issue tracker · Official page
Alternatives in AI & machine learning
Raster classification in QGIS with 11 machine learning algorithms, Optuna hyperparameter search, SHAP explanations, class imbalance handling
- ArcGeek CalculatorQGIS 4 ready
ArcGeek Calculator is a QGIS plugin that provides a comprehensive set of tools for coordinate calculations, conversions, spatial operations,
- Bunting Labs AI VectorizerQGIS 4 ready
Autocomplete for vectorizing and georeferencing raster maps.
Related plugins
- GeoOSAMNot QGIS 4 ready
AI-powered segmentation for QGIS — SAM2.1 & SAM3 with text prompts, similar object detection, vector ROI, and professional GIS workflow feat
- TreeEyedNot QGIS 4 ready
TreeEyed is a QGIS plugin for tree monitoring using AI.
- Geo SAMQGIS 4 ready
Segment Landform with Segment-Anything AI Model (SAM)
- QGIS Full Motion VideoQGIS 4 ready
Full Motion Video plugin for QGIS 4.
- Aerial LiDAR ClassifierQGIS 4 ready
Classify airborne and mobile mapping LiDAR point clouds with deep learning (LitePT-L, SegFormer 3D).
- AI Segmentation by TerraLabQGIS 4 ready
AI segmentation in QGIS 3.22 to 4. Draw a zone, name an object and get every building footprint, tree or solar panel as vector polygons, or
Maintenance: Active = updated within 1 year, Quiet = 1–3 years, Likely abandoned = over 3 years.