HOME | Research | Media | Careers | Contacts | Products | Search | Publications | Site Map
CSIRO Mathematics, Informatics and Statistics

 

 

Image Analysis
Biotech Imaging Group
Application Areas
 Biotechnology
 Cellular Screening
 Health
 Asset Monitoring
 Exploration
 Other Areas
Skills
 Segmentation
 Feature Extraction
 Statistical Analysis
 Stereo Vision
 Image Motion
 
Projects
Imaging Services
Imaging Products
Track Record
Publications
Patents
Staff

Image Analysis Activities

Corridor Mapping Using Stereo Vision

Powerline InspectionPowerlines

Corridor mapping has a number of applications. One of these is powerline inspection. Power companies in Australia (and many other countries) are required to maintain a regulated clearance space around all powerlines for bushfire mitigation and safety purposes. Current methods for checking clearances involve laborious, ground based, manual visual inspection of distribution networks to determine which trees must be cleared, together with extensive aerial audits of the network to ensure effective clearance of the network prior to the bushfire season. These are expensive, time consuming and subject to observer bias or a failure to observe trouble spots at the right time. 

For several years, Powercor Australia Ltd, the largest electricity distributor in the Australian state of Victoria, has been interested in the possibility of developing a cost effective airborne image capture and processing system to automatically measure the clearance of trees from powerlines to support bushfire mitigation operations. It is envisaged that such a system will involve an aircraft flying at approximately 80 metres above the ground, mounted with forward looking cameras beneath the tip of each wing, that capture a continuous series of images of the powerline infrastructure. The system will also carry differential global positioning systems (GPS) and inertial navigation systems (INS) to provide position and orientation data for the aircraft. 

Powercor came to CSIRO scientists from the Biotech Imaging Group of Mathematics, Informatics and Statistics to carry out several studies to develop a cost effective airborne image capture and processing system to automatically measure the clearance of trees from powerlines. Using stereo vision techniques, the CSIRO developed a software post-processing system that automatically creates three-dimensional (3D) space from the images. Then, after extracting key features from the images (e.g. power poles and powerlines), it measures and reports on the offset of the trees from the powerlines. 

The following are examples showing the input images and output digital surface model, orthoimages, and 3D visualisations. 

Powerlines from the air

The technology will make it possible for power companies to measure the distances of tree branches from power lines from the air
Mosaiced digital surface model
Mosaicked digital surface model and orthoimages from a sequence of stereo images
3-Dimensional display of the scene
A three-dimensional display of the trees, the powerpoles and powerlines

Corridor Mapping - An Opportunity

This technology has the potential to be applied in the mapping and positioning of linear and other features such as roads, railways, pipelines, fibre optic cables, streams and rivers, and, on a large scale, valley systems and shorelines. It could also be used for inventory updating , and geohazard and slope stability assessment of roads and railways. An opportunity exists for an enterprising company to develop a corridor mapping service for asset monitoring.

More Information

Here is a press release about this technology

A web demo on our fast matching algorithms for 3D reconstruction is also available

C. Sun, R. Jones, H. Talbot, X. Wu, K. Cheong, R. Beare, M.J. Buckley, and M. Berman, Measuring the Distance of Vegetation from Powerlines Using Stereo Vision. ISPRS Journal of Photogrammetry and Remote Sensing, 60(4):269-283, June 2006.

For further information contact:
Dr Mark Berman (phone: +61 2 9325 3205) or
Dr Changming Sun (phone: +61 2 9325 3207) 

To top

last updated May 01, 2011 02:15 AM
Ryan.Lagerstrom@csiro.au

 

© Copyright 2013, CSIRO Australia
Use of this web site and information available from
it is subject to our
Legal Notice and Disclaimer and Privacy Statement