Related Experiment Video
Updated: Feb 22, 2026

Photorealistic Learned Landscapes for Augmented Reality
Published on: June 27, 2025
3D Power Line Extraction from Multiple Aerial Images
1Department of Civil Engineering, Chonnam National University, Gwangju 61186, Korea. ojh@jnu.ac.kr.
Abstract:
Power lines are cables that carry electrical power from a power plant to an electrical substation. They must be connected between the tower structures in such a way that ensures minimum tension and sufficient clearance from the ground. Power lines can stretch and sag with the changing weather, eventually exceeding the planned tolerances. The excessive sags can then cause serious accidents, while hindering the durability of the power lines. We used photogrammetric techniques with a low-cost drone to achieve efficient 3D mapping of power lines that are often difficult to approach. Unlike the conventional image-to-object space approach, we used the object-to-image space approach using cubic grid points. We processed four strips of aerial images to automatically extract the power line points in the object space. Experimental results showed that the approach could successfully extract the positions of the power line points for power line generation and sag measurement with the elevation accuracy of a few centimeters.

