Illumination-Invariant Feature Extraction from Multi-Time-Series Images of Transmission Lines: A Sliding Window-Based Adaptive Attenuation Fusion Method
Main Article Content
Abstract
In complex outdoor transmission-line corridors, visible-band electromagnetic-wave imaging is strongly affected by atmospheric variations, day–night cycles, and transient illumination changes, which may cause feature drift and reduce the reliability of intelligent visual inspection. Existing studies mainly focus on electrical-quantity analysis or single-frame structural assessment, while insufficient attention has been paid to illumination-invariant feature extraction from multi-temporal monitoring images. To address this problem, this paper proposes an illumination-invariant feature extraction method for transmission lines based on sliding-window adaptive attenuation fusion. The proposed method exploits local temporal continuity to dynamically construct an illumination reference benchmark within a sliding window, and designs adaptive attenuation weights to fuse multi-frame features according to the degree of illumination interference. In this way, instantaneous strong-light disturbance can be suppressed while robust structural features of transmission-line components are retained. Experimental results on simulated synthetic and real acquired multi-time-series datasets show that the proposed method improves the feature consistency index by approximately 15%–30% compared with classical illumination normalization methods. It also enhances the generalization performance of downstream target detection models under varying illumination conditions. The results indicate that the proposed feature-level fusion strategy provides an effective technical approach for all-weather and highly reliable visual inspection of power transmission lines in complex electromagnetic field environments.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
M. Touati K O, M. Boudiaf, L. Mazouz, et al., “Efficient hybrid strategy based on FFT and fuzzy logic techniques applied to fault diagnosis in power transmission line,” Soft Computing, vol. 28, no. 15, pp. 8911-8930, 2024, doi: 10.1007/s00500-023-09089-6.
P. KC, M. Naghibolhosseini, and M. Zayernouri, “Multiphysics Modeling of Power Transmission Line Failures Across Four US States,” Modelling, vol. 5, no. 4, pp. 1745-1772, 2024, doi: 10.3390/modelling5040091.
M. Wang, L. Sun, J. Jiang, et al., “Enhancing hyperspectral power transmission line defect and hazard identification with an improved YOLO-based model,” Optoelectronics Letters, vol. 20, no. 11, pp. 681-688, 2024, doi: 10.1007/s11801-024-3213-3.
M. Elkholy A, I. Panfilov D, and G. Astashev M, “The influence of transmission-line parameters and its load on losses and power quality at the load-connection point,” Russian Electrical Engineering, vol. 94, no. 6, pp. 403-411, 2023, doi: 10.3103/S1068371223060044.
S. Ab Ghani, A. Khiar M S, S. Chairul I, et al., “Effects of parameter adjustment on the electromagnetic field of an overhead power transmission line model,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 30, no. 2, pp. 643-650, 2023, doi: 10.11591/ijeecs.v30.i2.pp643-650.
N. Ekren, Z. Karagöz, and M. ¸Sahin, “A review of line suspended inspection robots for power transmission lines,” Journal of Electrical Engineering & Technology, vol. 19, no. 4, pp. 2549-2583, 2024, doi: 10.1007/s42835-023-01713-7.
R. Hoseini Vaez S, A. Fathali M, and H. Mehanpour, “A two-step approach for reliability-based design optimization in power transmission line towers,” International Journal on Interactive Design and Manufacturing (IJIDeM), vol. 16, no. 3, pp. 1015-1039, 2022, doi: 10.1007/s12008-022-00838-9.
V. Savelyeva N, A. Pilipenko V, G. Mazur N, et al., “Electromagnetic emissions from the ZEVS transmitter and northern power transmission line, registered on the CSES satellite,” Bulletin of the Russian Academy of Sciences: Physics, vol. 89, no. 5, pp. 705-713, 2025, doi: 10.1134/S106287382571102X.
M. Garanzha I, V. Tanasoglo A, A. Ademola H, et al., “Dynamic behavior of power transmission line supports under wind influence,” Magazine of Civil Engineering, vol. 18, no. 1, pp. 1-3, 2025, doi: 10.34910/MCE.133.1.
I. Murugesan, P. Gunasekaran, S. Muthusamy, et al., “A normalized Haar wavelet transformation based firefly optimization algorithm for power transmission line fault detection problems,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, vol. 45, no. 2, pp. 4965-4981, 2023, doi: 10.1080/15567036.2023.2206797.
G. Petrova E, “Natural factors of accidents at power transmission line,” IDRiM Journal, vol. 12, no. 1, pp. 39-55, 2022, doi: 10.5595/001c.38749.
N. Bhukya B, R. Chinda P, R. Rayapudi S, et al., “Congestion management of power transmission line with advanced interline power flow controller,” Journal of Mechatronics, Electrical Power, and Vehicular Technology, vol. 16, no. 1, pp. 52-68, 2025, doi: 10.55981/j.mev.2025.795.
W. Weerakkody, B. Rathnayaka, and C. Siriwardana, “Identifying and Prioritizing Critical Risk Factors in the Context of a High-Voltage Power Transmission Line Construction Project: A Case Study from Sri Lanka,” CivilEng, vol. 5, no. 4, pp. 1057-1088, 2024, doi: 10.3390/civileng5040052.
Y. Sevim, “Power Transmission Line Fault Detection and Classification,” Karadeniz Fen Bilimleri Dergisi, vol. 15, no. 1, pp. 470-487, 2025, doi: 10.31466/kfbd.1604790.
M. Wang, W. Chai, C. Xu, et al., “An edge computing method using a novel mode component for power transmission line fault diagnosis in distribution network,” Journal of Ambient Intelligence and Humanized Computing, vol. 13, no. 11, pp. 5163-5176, 2022, doi: 10.1007/s12652-020-02466-1.