Improving Vegetation Encroachment Detection in Powerline Areas Using EfficientNet-Based U-Net Semantic Segmentation
DOI:
https://doi.org/10.52436/1.jutif.2026.7.2.5863Keywords:
EfficientNet, Encroachment Area Detection, Powerline Segmentation, Semantic Segmentation, Vegetation MonitoringAbstract
Vegetation growing beyond safe limits has the potential to pose a threat to safety and the reliability of overhead powerlines, as well as cause financial losses for infrastructure providers. Identifying potential obstructions to overhead powerlines is crucial for addressing these issues. This study proposes the EFF-UNET semantic segmentation technique on the VEPL dataset to identify areas of overlap between vegetation and overhead powerlines by overlaying the two models. Visually, overhead powerlines have a thin pixel structure and are difficult to distinguish from the background or vegetation, whereas the feature extraction process in the U-Net encoder can degrade small objects due to progressive resolution loss. Modifications to the encoder in the baseline U-Net architecture utilize the EfficientNet family by comparing variants B0 through B7 to produce the best model. EfficientNet specifically employs compound scaling to optimize the network’s resolution, depth, and width during feature extraction, thereby preserving information integrity during downsampling. Experimental results demonstrate the superiority of EfficientNetB7 through a measured trade-off compared to other models, where for vegetation segmentation, this model achieves an IoU of 0.9824, Accuracy of 0.9905, Dice of 0.9911, and Loss of 0.0089. Meanwhile, for powerline segmentation, the results show an IoU of 0.9153, Accuracy of 0.9978, Dice of 0.9558, and Loss of 0.0442. Based on these findings, EFF-UNET model successfully addresses the shortcomings of conventional models in preserving feature representation. This model is capable of improving the performance of vegetation and overhead powerlines segmentation to produce precise encroachment areas, thereby enabling accurate on-site infrastructure inspections.
Downloads
References
C. A. Dekker, S. E. Baumgartner, S. R. Sumter, and J. Ohme, “Beyond the Buzz: Investigating the Effects of a Notification-Disabling Intervention on Smartphone Behavior and Digital Well-Being,” Media Psychology, vol. 28, no. 1, pp. 162–188, 2025, doi: 10.1080/15213269.2024.2334025.
L. Kiburu, N. Njiraini, and N. Boso, “Social networks and consumer technology usage: A systematic literature review and future research directions,” Cogent Business and Management, vol. 10, no. 1, 2023, doi: 10.1080/23311975.2022.2153487.
M. A. Mahfud, D. M. A. Siregar, and M. F. Malik, “Nussbaum’s Justice Theory Lens: the Digital Divide and Unfulfillment of the Right to Public Service in Traditional Society,” Media Iuris, vol. 9, no. 1, pp. 97–128, 2026, doi: 10.20473/mi.v9i1.77214.
F. Bahreini and A. Hammad, “Detection of Vegetation Proximity to Power Lines: Critical Review and Research Roadmap,” Forests, vol. 16, no. 11, pp. 1–40, 2025, doi: 10.3390/f16111658.
M. F. Pacevicius, M. Ramos, C. T. Eriksen, and N. Paltrinieri, “Data-Informed Risk Analysis of Power Grids: Application of Method for Managing Heterogeneous Datasets,” ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, vol. 11, no. 2, 2025, doi: 10.1115/1.4066257.
M. Cano-Solis, J. R. Ballesteros, and J. W. Branch-Bedoya, “VEPL Dataset: A Vegetation Encroachment in Power Line Corridors Dataset for Semantic Segmentation of Drone Aerial Orthomosaics,” Data, vol. 8, no. 8, 2023, doi: 10.3390/data8080128.
V. S. Rajkumar, A. Stefanov, A. Presekal, P. Palensky, and J. L. R. Torres, “Cyber Attacks on Power Grids: Causes and Propagation of Cascading Failures,” IEEE Access, vol. 11, no. July, pp. 103154–103176, 2023, doi: 10.1109/ACCESS.2023.3317695.
S. Paul, A. Poudyal, S. Poudel, A. Dubey, and Z. Wang, “Resilience assessment and planning in power distribution systems: Past and future considerations,” Renewable and Sustainable Energy Reviews, vol. 189, no. PB, p. 113991, 2024, doi: 10.1016/j.rser.2023.113991.
R. Suttle, B. Kane, and D. Bloniarz, “Comparing the Structure, Function, Value, and Risk of Managed and Unmanaged Trees along Rights-of-Way and Streets in Massachusetts,” Forests, vol. 13, no. 10, 2022, doi: 10.3390/f13101602.
M. A. A. Faisal, I. Mecheter, Y. Qiblawey, J. H. Fernandez, M. E. H. Chowdhury, and S. Kiranyaz, “Deep learning in automated power line inspection: A review,” Applied Energy, vol. 385, no. May 2024, p. 125507, 2025, doi: 10.1016/j.apenergy.2025.125507.
Z. Ni et al., “Research on UAV-LiDAR-Based Detection and Prediction of Tree Risks on Transmission Lines,” Forests, vol. 16, no. 4, 2025, doi: 10.3390/f16040578.
A. Kyuroson, A. Koval, and G. Nikolakopoulos, “Autonomous Point Cloud Segmentation for Power Lines Inspection in Smart Grid,” International Federation of Automatic Control, vol. 56, no. 2, pp. 11754–11761, 2023, doi: 10.1016/j.ifacol.2023.10.562.
B. Harini, G. Mp, and M. Manju, “AI-Driven Vegetation Monitoring and Fire Risk Mitigation for Wildfire Prevention and Powerline Safety,” Proceedings of 2025 3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025, pp. 145–150, 2025, doi: 10.1109/ISACC65211.2025.10969250.
A. Al-Najjar, M. Amini, S. Rajan, and J. R. Green, “Identifying Areas of High-Risk Vegetation Encroachment on Electrical Powerlines Using Mobile and Airborne Laser Scanned Point Clouds,” IEEE Sensors Journal, vol. 24, no. 14, pp. 22129–22143, 2024, doi: 10.1109/JSEN.2023.3348785.
Y. Zhou, Z. Feng, C. Chen, and F. Yu, “Bilinear Distance Feature Network for Semantic Segmentation in PowerLine Corridor Point Clouds,” Sensors, vol. 24, no. 15, 2024, doi: 10.3390/s24155021.
J. Li, H. Zheng, P. Liu, Y. Liang, F. Shuang, and J. Huang, “Safety monitoring method for powerline corridors based on single-stage detector and visual matching,” High Voltage, vol. 9, no. 4, pp. 805–815, 2024, doi: 10.1049/hve2.12464.
D. Ayobo-Abongo, W. Jaafar, and R. Langar, “A Novel Hybrid ML Approach for Powerline - Vegetation Encroachment Area Identification,” IEEE International Symposium on Industrial Electronics, no. Ml, pp. 1–7, 2025, doi: 10.1109/ISIE62713.2025.11124746.
M. Cano-Solis, J. R. Ballesteros, and G. Sanchez-Torres, “VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery,” ISPRS International Journal of Geo-Information, vol. 12, no. 11, 2023, doi: 10.3390/ijgi12110454.
C. Torres de Almeida et al., “Canopy Height Mapping by Sentinel 1 and 2 Satellite Images, Airborne LiDAR Data, and Machine Learning,” Remote Sensing, vol. 14, no. 16, pp. 1–21, 2022, doi: 10.3390/rs14164112.
M. S. A. Mohd Rapheal et al., “Machine learning approach for tenaga nasional berhad (tnb) overhead powerline and electricity pole inventory using mobile laser scanning data,” International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, vol. 46, no. 4/W3-2021, pp. 239–246, 2022, doi: 10.5194/isprs-archives-XLVI-4-W3-2021-239-2022.
N. P. Husain, “A Multi-Branch EfficientNet-U-Net Hybrid Framework for Segmentation of Oyster Mushrooms in Cultivation Media,” Journal of Embedded System Security and Intelligent Systems, vol. 7, no. 1, pp. 78–91, 2026, doi: 10.59562/jessi.v7i1.2607.
M. Ezz, A. S. Alaerjan, A. M. Mostafa, N. Laban, and H. H. Zeyada, “Progressive Attention-Enhanced EfficientNet–UNet for Robust Water-Body Mapping from Satellite Imagery,” Sensors, vol. 26, no. 3, pp. 1–25, 2026, doi: 10.3390/s26030963.
N. Siddique, S. Paheding, A. A. Reyes Angulo, M. Z. Alom, and V. K. Devabhaktuni, “Fractal, recurrent, and dense U-Net architectures with EfficientNet encoder for medical image segmentation,” Journal of Medical Imaging, vol. 9, no. 06, pp. 1–22, 2022, doi: 10.1117/1.jmi.9.6.064004.
S. Y. Lin and C. L. Lin, “Brain tumor segmentation using U-Net in conjunction with EfficientNet,” PeerJ Computer Science, vol. 10, 2024, doi: 10.7717/peerj-cs.1754.
M. J. Mahoney, L. K. Johnson, A. Z. Guinan, and C. M. Beier, “Classification and mapping of low-statured shrubland cover types in post-agricultural landscapes of the US Northeast,” International Journal of Remote Sensing, vol. 43, no. 19–24, pp. 7117–7138, 2022, doi: 10.1080/01431161.2022.2155086.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Alissa Velia Royhatul Jannah, Nanik Suciati
This work is licensed under a Creative Commons Attribution 4.0 International License.
