Dragonfly is a computer vision technology that uses computer vision to provide the precise position of vehicles, robots, drones, forklifts and any other moving assets equipped with a monocular camera or stereoscopic camera. For computer vision technologies there are 2 types of accuracy measurements described in the following sections

• accuracy in a mapped venue.
• accuracy in an un-mapped venue.

Accuracy in a mapped venue

When navigating inside a known environment, when Dragonfly relocates the device inside a venue already mapped, the accuracy depends on the precision of the triangulation of known points (features). The radius of confidence, is typically 5-10 cm, and depends on several factors, including:

• The quality of the camera;
• The quality of the camera calibration process;
• The quality of the mapping process;
• The quality of the geo-referencing process;
• The type of the environment:
  • lighting;
  • amount of objects/real-world reference (and thus features);
  • availability/type of textures;
  • dimension of the map.

Accuracy in an un-mapped venue

The “drift” is the position error accumulated over time during the simultaneous navigation and mapping of unknown environments (areas in which Dragonfly has not been used before and thus for which there are no features within an existing 3D map yet). An example of this situation is when a forklift that makes use of Dragonfly enters into an area of a warehouse never explored before.

The drift can be expressed as a percentage:

• When using monocular cameras the drift in itself can be pretty high. The drift is high enough to NOT recommend relying on the position provided by Dragonfly engine in an un-mapped venue after 1 minute of navigation. This is why when Dragonfly is used with a monocular camera in an unknown environment it is mandatory to perform a pre-mapping of the entire environment with frequent loop closures (see below). After a pre-mapping of the venue, the radius of confidence is usually 1% of the distance of the camera from the closest real-world reference (visual or virtual marker).
• When using stereoscopic cameras the drift has been verified to range between 0.6% and 1.3%. This means that if you drive a forklift with Dragonfly installed on board along a 100 meters linear path, at the end Dragonfly will report a position with a ROC of 60-130 cm (the position could 60-130 cm away from the real position of the forklift).

Loop closing

The drift of Dragonfly when used with monocular cameras (and also with stereoscopic cameras) is automatically corrected by Dragonfly each time there is a loop-closure. A loop-closure is triggered each time the camera is moved from an area already mapped to an unknown area and then back to an area already mapped. When this happens, Dragonfly corrects the position and the map is also updated. Loop-closures are the key to get the maximum accuracy when Dragonfly is used with monocular cameras. It is strongly recommended to perform frequent loop-closures during the initial mapping, for both monocular and stereo cameras installations. A loop closure is triggered also when an existing map is fused with a new one (if the map fusion option is active inside the Dragonfly settings).