Precision aware drone-based object mapping based on spatial pattern recognition

A computer readable storage medium storing a program of instructions executable by a machine to perform a method of controlling an unmanned aerial vehicle, the method comprising:

• receiving an image of a region captured by the unmanned aerial vehicle flying at a current altitude;
• executing a computer vision algorithm with the image as an input to the computer vision algorithm, the computer vision algorithm computing an overall confidence score associated with detecting one or more candidate objects in the image;
• responsive to determining that the overall confidence score is below a predefined minimum threshold, controlling the unmanned aerial vehicle to reduce the current altitude and recapture the image of the region at the reduced altitude;
• responsive to determining that the overall confidence score is not below the predefined minimum threshold, storing on a storage device the image, the object detected in the image, the confidence score, location coordinates of the unmanned aerial vehicle, and the current altitude;
• repeating the receiving, the executing, the triggering and the storing while the region is not fully mapped with images and the unmanned aerial vehicle has energy capacity above a level needed to return to a designated base location.

A system of controlling an unmanned aerial vehicle, comprising:

• at least one hardware processor coupled to an unmanned aerial vehicle;
• and
• a storage device coupled to the at least one hardware processor;
• the at least one hardware processor operable to perform:
• receiving an image of a region captured by the unmanned aerial vehicle flying at a current altitude;
• executing a computer vision algorithm with the image as an input to the computer vision algorithm, the computer vision algorithm computing an overall confidence score associated with detecting one or more candidate objects in the image;
• responsive to determining that the overall confidence score is below a predefined minimum threshold, controlling the unmanned aerial vehicle to reduce the current altitude and recapture the image of the region at the reduced altitude;
• responsive to determining that the overall confidence score is not below the predefined minimum threshold, storing on a storage device the image, the object detected in the image, the confidence score, location coordinates of the unmanned aerial vehicle, and the current altitude;
• repeating the receiving, the executing, the triggering and the storing while the region is not fully mapped with images and the unmanned aerial vehicle has energy capacity above a level needed to return to a designated base location.