Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript

Automatic detection of power line clearings in Sentinel-2 images using machine learning and computer vision methods

Ya.O. Bakhramkhan¹ , D.M. Ermakov^{2, 3} , E.S. Podolskaia^{1, 4}

¹ National Research University Higher School of Economics, Moscow, Russia
² Space Research Institute RAS, Moscow, Russia
³ Kotelnikov Institute of Radioengineering and Electronics RAS, Fryazino Branch, Fryazino, Moscow Region, Russia
⁴ Isaev Centre for Forest Ecology and Productivity RAS, Moscow, Russia

Accepted: 13.05.2025
DOI: 10.21046/2070-7401-2025-22-4-11-26

Regular monitoring of the condition of power lines is imperative for ensuring uninterrupted power supply to settlements and infrastructure facilities. However, in forest areas with sparse population and limited road infrastructure, continuous monitoring is complicated. To address this challenge, the study proposes an algorithm that uses Sentinel-2 satellite images to identify forest clearings in remote, hard-to-reach forest areas. This algorithm marks a pioneering step in the automation of remote monitoring of power line clearings, particularly in the context of detecting changes (e.g., laying, overgrowing, clearing of power line clearings, etc.). The algorithm’s logic is straightforward and based on the search for objects of interest in the space of decoding features. The logistic regression model applies spectral characteristics to identify areas potentially associated with clearings. Subsequently, the probabilistic Hough transform locates linear structures within the binary mask of these areas. The developed algorithm is fully automatic, eliminating the need for individual parameter tuning for each image. We developed a set of metrics to evaluate quality of clearings extraction as a measure of algorithm’s efficiency. Performance of the algorithm is locally stable, it correctly identifies the areas of power line clearings in all satellite images of the study region that have been used.

Keywords: clearings, power lines, remote monitoring, interpretation features, interpretability of the algorithm, Hough transform, logistic regression

Full text

References:

Bakhramkhan Ya. O., Ermakov D. M., Podolskaia E. S., Experience in developing an algorithm for identifying forest clearings under power lines in forest landscapes based on Sentinel-2 data, Materialy 22-i Mezhdunarodnoi konferentsii “Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa” (Proc. 22nd Intern. Conf. “Current Problems in Remote Sensing of the Earth from Space”), Moscow: IKI RAS, 2024, p. 163 (in Russian), https://doi.org/10.21046/22DZZconf-2024a.
Ahmad J., Malik A. S., Xia L., Vegetation monitoring for high-voltage transmission line corridors using satellite stereo images, 2011 National Postgraduate Conf., 2011, 5 p., DOI: 10.1109/NatPC.2011.6136337.
Bernstein R., Di Gesù V., A combined analysis to extract objects in remote sensing images, Pattern Recognition Letters, 1999, V. 20, Iss. 11–13, pp. 1407–1414, https://doi.org/10.1016/S0167-8655(99)00126-9.
Chen S., Haralick R. M., Recursive erosion, dilation, opening, and closing transforms, IEEE Trans. Image Processing, 1995, V. 4, Iss. 3, pp. 335–345, DOI: 10.1109/83.366481.
Duda R. O., Hart P. E., Use of the Hough transformation to detect lines and curves in pictures, Communications of the ACM, 1972, V. 15, Iss 1, pp. 11–15, https://doi.org/10.1145/361237.361242.
Gorelick N., Hancher M., Dixon M. et al., Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sensing of Environment, 2017, V. 202, pp. 18–27, https://doi.org/10.1016/j.rse.2017.06.031.
Huete A. R., A soil-adjusted vegetation index (SAVI), Remote Sensing of Environment, 1988, V. 25, Iss. 3, pp. 295–309, https://doi.org/10.1016/0034-4257(88)90106-X.
Kobayashi Y., Karady G. G., Heydt G. T., Olsen R. G., The utilization of satellite images to identify trees endangering transmission lines, IEEE Trans. Power Delivery, 2009, V. 24, Iss. 3, pp. 1703–1709, DOI: 10.1109/TPWRD.2009.2022664.
Lin Y., Hong W., Tan W. et al., Airborne circular SAR imaging: Results at P-band, 2012 IEEE Intern. Geoscience and Remote Sensing Symp., 2012, pp. 5594–5597, DOI: 10.1109/IGARSS.2012.6352051.
Mahdi Elsiddig Haroun F., Mohamed Deros S. N., Din N. M. (2021a), Detection and monitoring of power line corridor from satellite imagery using RetinaNet and K-mean clustering, IEEE Access, 2021, V. 9, pp. 116720–116730, DOI: 10.1109/ACCESS.2021.3106550.
Mahdi Elsiddig Haroun F., Mohamed Deros S. N., Bin Baharuddin M. Z., Din N. M. (2021b), Detection of vegetation encroachment in power transmission line corridor from satellite imagery using support vector machine: A features analysis approach, Energies, 2021, V. 14, Iss. 12, Article 3393, https://doi.org/10.3390/en14123393.
McFeeters S. K., The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features, Intern. J. Remote Sensing, 1996, V. 17, Iss. 7, pp. 1425–1432, https://doi.org/10.1080/01431169608948714.
Moeller M. S., Monitoring powerline corridors with stereo satellite imagery, Proc. MAPPS/ASPRS Fall Conf., 2006, 6 p.
Mu C., Yu J., Feng Y., Cai J., Power lines extraction from aerial images based on Gabor filter, Intern. Symp. Spatial Analysis, Spatial-Temporal Data Modeling, and Data Mining, 2009, V. 7492, pp. 1081–1088.
Sarabandi K., Park M., Millimeter-wave radar phenomenology of power lines and a polarimetric detection algorithm, IEEE Trans. Antennas and Propagation, 1999, V. 47, Iss. 12, pp. 1807–1813, https://doi.org/10.1109/8.817656.
Sarabandi K., Pierce L., Oh Y., Ulaby F. T., Power lines: Radar measurements and detection algorithm for polarimetric SAR images, IEEE Trans. Aerospace and Electronic Systems, 1994, V. 30, Iss. 2, pp. 632–643, https://doi.org/10.1109/7.272288.
Schwarz G., Soccorsi M., Chaabouni-Chouayakh H. et al., Automated information extraction from high resolution SAR images: TerraSAR-X interpretation applications, 2009 IEEE Intern. Geoscience and Remote Sensing Symp., 2009, V. 4, pp. 677–680, DOI: 10.1109/IGARSS.2009.5417467.
Tong W.-G., Li B.-S., Yuan J.-S., Zhao S.-T., Transmission line extraction and recognition from natural complex background, 2009 Intern. Conf. Machine Learning and Cybernetics, 2009, V. 4, pp. 2473–2477, DOI: 10.1109/ICMLC.2009.5212202.
Xu H., A new index for delineating built‐up land features in satellite imagery, Intern. J. Remote Sensing, 2008, V. 29, Iss. 14, P. 4269–4276, https://doi.org/10.1080/01431160802039957.

создание сайта - TXL