Utility line localization from aerial images

At least one non-transitory machine-readable medium having instructions stored thereon that, in response to execution, cause an unmanned aerial vehicle (UAV) to perform operations comprising:

• capturing a plurality of aerial images of a ground area below the UAV;
• recording a position of the UAV when capturing each of the aerial images;
• detecting a presence of an object in the aerial images suspected to be a utility line;
• identifying two offset pixel points in each of the aerial images that coincide with the object in each of the aerial images;
• converting the two offset pixel points in each of the aerial images to a world frame;
• defining a plurality of geometric planes in the world frame each corresponding to one of the aerial images, wherein each of the geometric planes is defined by the position of the UAV when capturing a corresponding one of the aerial images and the two offset pixel points in the world frame corresponding to the one of the aerial images;
• determining an intersection approximation of the geometric planes in the world frame to localize the object;
• localizing the object based upon the intersection approximation;
• and
• navigating the UAV around the object based upon the localizing.

At least one non-transitory machine-readable medium having instructions stored thereon that, in response to execution, cause an unmanned aerial vehicle (UAV) to perform operations comprising:

• capturing a plurality of aerial images of a ground area below the UAV;
• detecting a presence of an object in the aerial images suspected to be a utility line;
• identifying two offset pixel points in each of the aerial images that coincide with the object in each of the aerial images;
• defining a plurality of geometric planes each of which corresponds to one of the aerial images, wherein each of the geometric planes is determined based at least in part on a position of the UAV when capturing a corresponding one of the aerial images and the two offset pixel points corresponding to the one of the aerial images;
• determining an intersection approximation of the geometric planes to localize the object;
• and
• navigating the UAV around the object based at least in part upon the intersection approximation.