Measuring the distance of vegetation from powerlines using stereo vision

• Published in: ISPRS journal of photogrammetry and remote sensing 2006-06, Vol.60 (4), p.269-283
• Main Authors: Sun, Changming, Jones, Ronald, Talbot, Hugues, Wu, Xiaoliang, Cheong, Kevin, Beare, Richard, Buckley, Michael, Berman, Mark
• Format: Article
• Language: English
• Subjects: 3D vegetation surface; Animal, plant and microbial ecology; Applied geophysics; Biological and medical sciences; Computation and Language; Computer Science; Earth sciences; Earth, ocean, space; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; General aspects. Techniques; Internal geophysics; power pole segmentation; powerline inspection; stereo matching; Teledetection and vegetation maps; vegetation clearance
• ISSN: 0924-2716; 1872-8235
• DOI: 10.1016/j.isprsjprs.2006.03.004

Electricity distribution companies in many countries are required to maintain a regulated clearance space around all powerlines for bushfire mitigation and safety purposes. Vegetation encroachment of high voltage electricity line clearance space is a major problem for electricity distribution utilities. If not properly controlled, vegetation encroachment can lead to bushfire and public safety risks as well as degrading electricity supply reliability. In this paper we describe a prototype airborne system for the automated measurement of the distance of vegetation from powerlines using stereo vision from a stream of stereo images. A fundamental problem with the images from the prototype system is that the powerlines are usually difficult to see, although the power poles are visible. The proposed strategy has been to recover the vegetation surface using stereo vision techniques, identify successive power poles, model the powerlines between successive poles as a catenary, and measure the distance between the vegetation surface and the modelled line. Some suggestions about how to improve the system are also made.