Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

Automatic Extraction of Pylons Using IRS P5 Satellite Images

Document Type : Research Paper

Authors
Shahab Sherafati 1
Manuchehr Masumi 2
1 M.S of Remote Sensing, Survey Engineering Board, Tehran University
2 M.S student of IT, Malek-e-Ashtar University
Abstract
Lots of parameters like growing of plants, trees falling across power line, land sliding and flood may lead to massive damage of power line corridors. Therefore, several methods have been used for monitoring and inspecting power lines including field surveying, aerial image analysis and LIDAR analysis which are very time consuming and expensive. Implimantation of satellite images and remote sensing technology may be an alternative method. But this new method too, may have some limitations in analyzing small features. In this paper, the main objective is to discuss satellite images capabilities in automatic pylon extraction and finding power lines. For this purpose, IRS-P5 satellite images have been used as the main data. This sensor provides panchromatic images with spatial resolution of 2.5 meter. In contrast with some high spatial resolution sensors like WorldviewII and GeoEyeI that provides multispectral images with better spatial and spectral resolution (about 1.6m in multispectral bands and 0.5m in panchromatic band), it is more troublesome to extract pylons in P5 images. Indeed, these sensors can show a pylon and its shadow like two separate triangles, but in P5 images pylons are like dark speckels. Therefore, in this paper several conditions have been used to distinguish pylons and power lines correctly. Results show that the proposed method can satisfactorily extract pylons in homogeneous areas, but in rough regins that have lots of small dark speckles (like vegetation areas), the accuracy decreases. As the second objective of this paper, the capability of satellite images in measuring pylons’ height has been discussed. P5 stereo images can not find the height of the pylons, but sensors with higher spatial resolution, like Worldview I, have this capability. Although, even in this sensors, reaching stereo images matching pylons’ pixel may be a challenging task.
Keywords
Satellite images
Feature Extraction
power line corridors
  1. Beltrame, A.M.K, M.G.M Jardini, R.M Acbsen, and J.A Uintanilha. “Vegetation identification and classification in the domain limits of powerlines in Brazilian Amazon forest.” IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2007. 2314-2317.
  2. Clode, S, and F Rottensteiner. “Classification of trees and powerlines from medium resolution airborne laserscanner data in urban environments.” APRS Workshop on Digital Image Computing. Brisbane, Australia, 2005.
  3. Jahjah, M, and C Ulivieri. “Automatic archaeological feature extraction from satellite VHR images.” Acta Astronautica, 2010: 1302-1310.
  4. Jin, X, and H Davis. “Vehicle detection from high-resolution satellite imagery using morphological sharde-weight neural networks.” Image and Vision Computing, 2007: 1422-1431.
  5. Jones, D, J Golightly, J Roverts, K Usher, and G Earp. “power line inspection - a uav concept.” IEE Forum on Autonomous Systems. London, United Kingdom, 2005.
  6. Jwa, Y, G Sohn, and H.B Kim. “Automatic 3D power line reconstruction using airborne lidar data.” ISPRS Laserscanning 2009. Paris, France,: ISPRS, 2009.
  7. Li, Z, R Hayward, J Zhang, Y Liu, and R Walker. “Towards automatic tree crown detection and delineation in spectral feature space using PCNN and morphological reconstruction.” IEEE International Conference on Image Processing. Cairo, Egypt: IEEE, 2009.
  8. Li, Zhengrongi, Rodney Walker, Ross Hayward, and Luis Mejias. “Advances in Vegetation Management for Power Line Corridor Monitoring Using Aerial Remote Sensing Techniques.” 1st International Conference on Applied Robotics for the Power Industry. Montréal, Canada, 2010.
  9. Lu, M. L, and Z Kieloch. “Accuracy of transmission line modeling based on aerial LiDAR survey.” IEEE Transactions on Power Delivery 23 (2008): 1655-1663.

10. Michaelsen, E, and U Stilla. “Estimating urban activity on high-resolution thermal image sequence aided by large scale vector maps.” IEEE/ISPRS Goint Workshop on Remote Sensing and Data Fusion over Urban Areas. Rome, 2001.

11. Mills, S, J Ford, and L Mejias. “Vision based control for fixed wing UAVs inspecting locally linear infrastructure with skid-to-turn maneuvers.” International Conference on Unmanned Aerial Vehicles. Dubai, UAE, 2010.

12. Moeller, Matthias S. “MONITORING POWERLINE CORRIDORS WITH STEREO SATELLITE IMAGERY.” MAPPS/ASPRS. San Antonio, Texas, 2006.

13. Mokhtarzade, M, and M Valadane Zoej. “Road detection from high-resolution satellite images using artificial networks.” International Journal of Applied Earth Observation and Geoinformation, 2007: 32-40.

14. Sun, C, et al. “Measuring the distance of vegetation from powerlines using stereo vision.” ISPRS Journal of Photogrammetry & Remote Sensing 60 (2006): 269-283.

15. Tupin, F, H Maitre, J mangin, and J Nicolas. “detection of linear features in SAR images: applications to road network extraction.” IEEE Transactions on Geoscince and Remote Sensing, 1998.