# OpenDroneKit facts

> OpenDroneKit is an open-source, offline-first drone inspection and GIS toolkit for Windows.

Updated 2026-10-02. Checked against the public repository at commit 1ef6351ba387aaace7e6907d10babc6feb2351d3 (2026-09-01). Canonical page: https://opendronekit.com/facts

## What OpenDroneKit is

- OpenDroneKit is an open-source, offline-first drone inspection and GIS toolkit for Windows. ([README.md#L5](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L5))
- It plans inspection missions, flies them over MAVLink, reconstructs the imagery into georeferenced products, detects defects, measures them and writes the report, in one desktop app. ([README.md#L5](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L5))
- Outputs land in a real coordinate reference system and open directly in QGIS. ([README.md#L9](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L9))
- OpenDroneKit is written as one word. It is not affiliated with DroneKit (dronekit.io, the Python MAVLink SDK from 3D Robotics) or with OpenDroneMap. (Owner statement, 2026-10-02)
- It is built by Prabal Khare. Source code: github.com/00PrabalK00/OpenDroneKit. (Owner statement, 2026-10-02)

## Price, licence and availability

- OpenDroneKit is free: no account, no licence key and no paid tier. (Owner statement, 2026-10-02)
- The owner chose the MIT License (copyright 2026 Prabal Khare) on 2026-10-02. As of commit 1ef6351 (2026-09-01) the LICENSE file is not yet on the public main branch, so GitHub shows no licence for the repository. (Owner statement, 2026-10-02)
- There is no Windows installer and no tagged release as of 2026-10-02. OpenDroneKit runs from source: clone the repository, create a Python 3.11 environment and run pip install -r requirements.txt. ([Download page](https://opendronekit.com/download))
- It needs Python 3.11 or newer, pip and Git; everything else is a Python package. ([docs/INSTALLATION.md#L11](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/INSTALLATION.md#L11))
- It is developed and tested on Windows and Linux. On Windows the desktop shell uses the built-in Edge WebView2; there is no bundled browser and no Qt dependency. ([docs/INSTALLATION.md#L86](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/INSTALLATION.md#L86))
- No GPU is required. A GPU matters only for dense reconstruction (a CUDA build of COLMAP) and for training models. ([docs/INSTALLATION.md#L71](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/INSTALLATION.md#L71))
- Model weights are not stored in the Git repository. ([README.md#L135](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L135))

## Mission planning

- The planner offers 22 mission templates, derived from its alias table by available_templates(): grid, double_grid, corridor, solar_inspection, magnetic_mapping, smart_adaptive, roof_inspection, facade, facade_mapping, multi_facade, box_inspection, tower_mapping, wind_turbine, dome_inspection, orbit, closed_loop, linear_inspection, lateral_capture, waypoints, panorama, bubble_360, linked_mission. (The README on main still says 16.) ([mission/planner.py#L277](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/mission/planner.py#L277))
- Missions are laid out with constraint geometry: ray-cast geofence containment, no-fly polygons with segment-level detours, altitude bands, stand-off and return-to-home rules. ([README.md#L14](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L14))
- Terrain-aware planning follows AGL or AMSL using a GeoTIFF, an ESRI ASCII grid, CSV samples or a fitted plane. ([README.md#L19](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L19))
- Missions export to six formats: QGroundControl .plan, QGC WPL 110 .waypoints, DJI WPML .kmz, Litchi CSV, KML and GeoJSON. ([mission/exporters.py#L706](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/mission/exporters.py#L706))
- The exporters on public main have known defects that the development branch fixes or still carries; each format page lists them. ([Mission file formats](https://opendronekit.com/formats))

## Flight

- Flight control is MAVLink 2 to ArduPilot. Mission, geofence and rally upload use the request/ack transfer protocol and land in the correct mission slot; gimbal, yaw, dwell and camera-trigger items survive an upload/download round trip. ([README.md#L125](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L125))
- DJI and Litchi aircraft are supported by export only: the file is flown with their own apps. ([mission/exporters.py](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/mission/exporters.py))
- A mock flight driver is selectable and is always labelled SIMULATED in the UI. ([README.md#L126](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L126))
- Flight code is tested against ArduPilot Copter 4.5.7 in simulation (SITL). As of 2026-10-02, run locally in Docker, two of three SITL flight tests pass; the third (home position reporting) exposed a bug that is being fixed. (Owner statement, 2026-10-02)
- SITL caught missions putting NAV_TAKEOFF at sequence 0, which MAVLink reserves for home, after every mock-based test had passed. ([README.md#L122](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L122))

## Reconstruction

- Reconstruction uses COLMAP structure-from-motion with bundle adjustment, camera intrinsics from an EXIF sensor database, and georeferencing solved as a RANSAC Helmert similarity between camera centres and image geotags. ([README.md#L26](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L26))
- It outputs a Cloud-Optimized GeoTIFF orthomosaic, DSM, DTM and hillshade, plus a point cloud (.ply), a Poisson mesh (.ply/.obj) and a camera-track GeoJSON. ([README.md#L29](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L29))
- The UTM zone is chosen automatically from the mean position of the images' geotags (EPSG 32600 + zone in the north, 32700 + zone in the south); an explicit EPSG code can be passed instead. ([core/geo.py#L317](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/core/geo.py#L317))
- Dense multi-view stereo needs a CUDA build of COLMAP. The pycolmap wheels are CPU-only, so without one dense stereo is skipped, raster resolution drops to what the sparse cloud supports, and the run says so. ([README.md#L107](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L107))
- On the public OpenDroneMap Aukerman survey, main's README records 77 of 77 images registered, 1.27 px mean reprojection error and 1.22 m georeference RMSE in EPSG:32617. The homepage figures (1.255 px, 1.12 m) come from a later run of the development branch. ([README.md#L105](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L105))
- Cloud reconstruction is not implemented. Requesting it runs locally and reports that it did; no imagery leaves the machine. ([README.md#L124](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L124))

## Defect models

- crack_segmentation (SegFormer-B5 (run crack_segformer_b5, 40 epochs)): IoU 0.637 on the held-out test, threshold 0.85 split. Known weakness: At 0.85 thin and faint cracks are missed, so an empty mask is not evidence of a sound surface. ([docs/features/registry.py#L737](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/features/registry.py#L737))
- corrosion_severity_segmentation (SegFormer-B2 (run corrosion_segformer_b2_cs, 80 epochs, log-inverse class weighting)): Severe-pixel recall 0.788 on the validation split. Known weakness: Errors are almost entirely between adjacent grades: of the 653,071 severe pixels it recovers 514,827 (recall 0.788) and loses 124,241 of the rest to 'poor', one step down. A reported grade can be one step optimistic. ([docs/features/registry.py#L764](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/features/registry.py#L764))
- solar_cell_defect_detector (YOLO11l (run pvel_ad_yolo11l, 60 epochs)): mAP50 0.8835 on the validation split. Known weakness: EL cell-level imagery only (module manufacturing and lab inspection). It is not an aerial or thermal model and must not be applied to drone photographs of installed panels. ([models/model_registry.json#L143](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/models/model_registry.json#L143))
- solar_thermal_anomaly_classifier (ResNet18 (run solar_thermal_cls, 26 epochs, early-stopped)): Balanced accuracy 0.724 on the validation split. Known weakness: Soiling is the weak class at 0.367 recall and 0.344 precision on 30 validation samples: roughly two in three soiled modules are missed, and a third of soiling calls are wrong. ([models/model_registry.json#L165](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/models/model_registry.json#L165))
- A model's finding keeps the model key, the SHA-256 of the weights that produced it, and its confidence; the reviewer's decision is stored separately, so review never erases what the model asserted. ([docs/features/registry.py#L843](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/features/registry.py#L843))
- The installed weights file is hashed at load and compared with the registry; a replaced file is reported as a mismatch, and a model with no recorded digest is reported as unrecorded, never as verified. ([README.md#L117](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L117))
- No model has been measured on Indian sites. ([README.md#L116](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L116))
- Three trained models were rejected rather than shipped, with the reasons kept: an RGB solar panel-condition detector, a corrosion detector and mine change detection. ([docs/features/registry.py#L758](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/features/registry.py#L758))

## Measurement and reports

- Area, perimeter, volume and change are computed against the real DSM and DTM. Volume is verified to 0.00 m³ error against an analytic test surface. ([README.md#L123](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L123))
- Without georeferenced rasters the report states that measurements are absent rather than printing zeros. ([README.md#L123](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L123))
- Reports are written as HTML, PDF, DOCX and Markdown from the same report sections. ([core/report_formats.py#L1](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/core/report_formats.py#L1))

## Offline and data

- Processing, detection, measurement and reporting run on the operator's machine. ([README.md#L124](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/README.md#L124))
- Projects are stored in SQLite with geometry as GeoJSON text; PostgreSQL with PostGIS is optional, for multi-user deployments. ([docs/INSTALLATION.md#L69](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/INSTALLATION.md#L69))
- Basemap tiles can be cached for offline use (the Hub's Offline tiles panel on main). ([app/web/hub.html#L35](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/app/web/hub.html#L35))
- Thermal temperatures are computed from radiometric counts plus the camera's Planck constants. Reading a FLIR or DJI thermal JPEG directly is not implemented on main and is refused with that reason. ([core/thermal.py#L244](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/core/thermal.py#L244))

## How status is measured

- A capability is only 'verified' when the tests it names pass against real inputs. Status is computed by tools/feature_status.py from test results, never set by hand. ([docs/features/registry.py#L3](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/features/registry.py#L3))
- docs/FEATURES.md on main tracks 167 capabilities: 163 verified, 0 implemented, 2 in progress, 2 not started. It was computed on a machine with trained weights installed; a run without weights reaches a lower verified count. ([docs/FEATURES.md#L9](https://github.com/00PrabalK00/OpenDroneKit/blob/1ef6351ba387aaace7e6907d10babc6feb2351d3/docs/FEATURES.md#L9))
- OpenDroneKit has published no user counts, customer names, testimonials, ratings or benchmarks against other products; this site does not claim any. (Owner statement, 2026-10-02)