{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:54:35Z","timestamp":1779134075843,"version":"3.51.4"},"reference-count":41,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Overhead transmission lines are important lifelines in power systems, and the research and application of their intelligent patrol technology is one of the key technologies for building smart grids. The main reason for the low detection performance of fittings is the wide range of some fittings\u2019 scale and large geometric changes. In this paper, we propose a fittings detection method based on multi-scale geometric transformation and attention-masking mechanism. Firstly, we design a multi-view geometric transformation enhancement strategy, which models geometric transformation as a combination of multiple homomorphic images to obtain image features from multiple views. Then, we introduce an efficient multiscale feature fusion method to improve the detection performance of the model for targets with different scales. Finally, we introduce an attention-masking mechanism to reduce the computational burden of model-learning multiscale features, thereby further improving model performance. In this paper, experiments have been conducted on different datasets, and the experimental results show that the proposed method greatly improves the detection accuracy of transmission line fittings.<\/jats:p>","DOI":"10.3390\/s23104923","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T02:00:27Z","timestamp":1684720827000},"page":"4923","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fittings Detection Method Based on Multi-Scale Geometric Transformation and Attention-Masking Mechanism"],"prefix":"10.3390","volume":"23","author":[{"given":"Ning","family":"Wang","sequence":"first","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3271-3585","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenlin","family":"Huang","sequence":"additional","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Wen","sequence":"additional","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Operation and Maintenance Center of Information and Communication, CSG EHV Power Transmission Company, Guangzhou 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7509-5222","authenticated-orcid":false,"given":"Wenshuo","family":"Lou","sequence":"additional","affiliation":[{"name":"Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,19]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"From Smart Grid to Energy Internet: Basic Concept and Research Framework","volume":"15","author":"Dong","year":"2014","journal-title":"Autom. Electr. Power Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ijepes.2017.12.016","article-title":"Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning","volume":"99","author":"Nguyen","year":"2018","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_3","first-page":"57","article-title":"Concept, Research Status and Prospect of Electric Power Vision Technology","volume":"57","author":"Zhao","year":"2020","journal-title":"Electr. Power Sci. Eng."},{"key":"ref_4","first-page":"57","article-title":"Review on Semantic Segmentation of UAV Aerial Images","volume":"57","author":"Cheng","year":"2021","journal-title":"Comput. Eng. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"687","DOI":"10.12720\/jcm.9.9.687-692","article-title":"Unmanned aerial vehicles for power line inspection: A cooperative way in platforms and communications","volume":"9","author":"Deng","year":"2014","journal-title":"J. Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s11633-019-1194-7","article-title":"Deep learning based on hand gesture recognition and UAV flight controls","volume":"17","author":"Hu","year":"2020","journal-title":"Int. J. Autom. Comput."},{"key":"ref_7","first-page":"1","article-title":"Research progress of visual detection methods for transmission line key components based on deep learning","volume":"34","author":"Zhao","year":"2018","journal-title":"Electr. Power Sci. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., and Darrell, T. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., and Jiang, Y. (2021, January 19\u201325). Sparse r-cnn: End-to-end object detection with learnable proposals. Proceedings of the Conference on Computer Vision and Pattern Recognition, Online.","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., and Erhan, D. (2016, January 10\u201316). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_13","unstructured":"Redmon, J., Divvala, S., and Girshick, R. (July, January 26). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_14","unstructured":"Ge, Z., Liu, S., and Wang, F. (2021). Yolox: Exceeding Yolo Series in 2021. arXiv."},{"key":"ref_15","first-page":"1","article-title":"Transformers in Vision: A Survey","volume":"54","author":"Salman","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., and Synnaeve, G. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Online.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_17","unstructured":"Zhu, X., Su, W., and Lu, L. (2021). Deformable DETR: Deformable Transformers for End-to-End Object Detection. arXiv."},{"key":"ref_18","unstructured":"Roh, B., Shin, J., and Shin, W. (2021). Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity. arXiv."},{"key":"ref_19","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume":"34","author":"Fang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_20","unstructured":"Song, H., Sun, D., and Chun, S. (2021). ViDT: An Efficient and Effective Fully Transformerbased Object Detector. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., and Chen, M. (2021, January 10\u201317). Rethinking and improving relative position encoding for vision transformer. Proceedings of the International Conference on Computer Vision, Montreal, Canada.","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.11834\/jig.200793","article-title":"Bolt defect detection for aerial transmission lines using Faster R-CNN with an embedded dual attention mechanism","volume":"26","author":"Qi","year":"2021","journal-title":"J. Image Graph."},{"key":"ref_23","first-page":"2821","article-title":"Bolt Detection Technology of Transmission Lines Based on Deep Learning","volume":"45","author":"Zhang","year":"2020","journal-title":"Power Syst. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2849","DOI":"10.1109\/TIM.2018.2871353","article-title":"A CNN-based defect inspection method for catenary split pins in high-speed railway","volume":"68","author":"Zhong","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","first-page":"98","article-title":"Construction and Application of Bolt and Nut Pair Knowledge Graph Based on GGNN","volume":"56","author":"Zhao","year":"2021","journal-title":"Power Syst. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xu, G., and Qi, Y. (2016, January 24\u201329). Multi-patch deep features for power line insulator status classification from aerial images. Proceedings of the International Joint Conference on Neural Networks, Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727606"},{"key":"ref_27","unstructured":"Zhao, Z., Ma, D., and Ding, J. (2023). Weakly Supervised Detection Method for Pin-missing Bolt of Transmission Line Based on SAW-PCL. J. Beijing Univ. Aeronaut. Astronaut., 1\u201310."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhao, K., and Guo, X. (2021, January 17\u201320). HRM-CenterNet: A High-Resolution Real-time Fittings Detection Method. Proceedings of the International Conference on Systems, Man, and Cybernetics, Melbourne, Australia.","DOI":"10.1109\/SMC52423.2021.9658920"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2582","DOI":"10.11834\/jig.200703","article-title":"Multi Label Classification of Bolt Attributes based on Deformable NTS-Net Network","volume":"26","author":"Zhang","year":"2021","journal-title":"J. Image Graph."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lou, W., Zhang, K., and Guo, X. (2022, January 7\u201310). PAformer: Visually Indistinguishable Bolt Defect Recognition Based on Bolt Position and Attributes. Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Chiang Mai, Thailand.","DOI":"10.23919\/APSIPAASC55919.2022.9979954"},{"key":"ref_31","first-page":"64","article-title":"Relativistic GAN for bolts image generation with attention mechanism","volume":"56","author":"Qi","year":"2019","journal-title":"Electr. Meas. Instrum."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yu, Y., Gong, Z., and Zhong, P. (2017, January 28\u201330). Unsupervised representation learning with deep convolutional neural network for remote sensing images. Proceedings of the Image and Graphics: 9th International Conference, Los Angeles, CA, USA.","DOI":"10.1007\/978-3-319-71589-6_9"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., and Huszar, F. (2017, January 21\u201326). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Proceedings of the IEEE Conference Computer Vision and Pattern Recognition, Hawaii, HI, USA.","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref_34","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_35","unstructured":"He, J., Chen, J., and Liu, S. (2021). TransFG: A Transformer Architecture for Fine-Grained Recognition. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wei, X., Wang, P., and Guo, Y. (2019, January 16\u201320). Multi-Label Image Recognition with Graph Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lin, T., Dollar, P., and Girshick, R. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., and Qin, H. (2018, January 18\u201322). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q. (2020, January 14\u201319). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_40","first-page":"13937","article-title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","unstructured":"Loshchilov, I., and Hutter, F. (2018). Decoupled Weight Decay Regularization. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/10\/4923\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:38:55Z","timestamp":1760125135000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/10\/4923"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":41,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23104923"],"URL":"https:\/\/doi.org\/10.3390\/s23104923","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,19]]}}}