Abstract
There are a large number of small-sized hardware such as nuts, washers and pins in power transmission equipment. The inspection image of power transmission has high resolution and large image size, which makes it difficult to detect defects distributed on such small-sized hardware. This is a major pain point in transmission line inspections. In response to this pain point, Ontology researches a defect detection model for small power transmission fittings based on improved SLIC (Simple Linear Iterative Clustering) and ViT (Vision Transformer). First, the improved SLIC is used to perform superpixel segmentation and clustering on the image, highlighting the position of small fittings in the entire image, and then using the visual Transformer deep learning network trains and learns the inspection images collected by drones at the power transmission inspection site, and obtains a model capable of stably and accurately identifying the defects of small power transmission fittings. The experimental results show that the method proposed in this paper can efficiently identify the defects of small power transmission fittings under the premise of ensuring stability, with an average recognition accuracy rate of 89.2%, which has high practicability and improves the detection and identification ability of small fittings defects.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Peng, X., Qian, J., Mai, X., et al.: Automatic power line inspection technology of large unmanned helicopter and its application. South. Power Syst. Technol. 10(2), 24–31, 76 (2016)
Liu, Z., Du, Y., Chen, Y., et al.: Simulation and experiment on the safety distance of typical ±500 kV DC transmission lines and towers for UAV inspection. High Voltage Eng. 45(2), 426–432 (2019)
Sun, Y.: Research on 3D imaging system of UAV line laser scanning. Harbin Institute of Technology, Harbin, China (2017)
Liu, Z., Miao, X., Chen, J., et al.: Review of visible image intelligent processing for transmission line inspection. Power Syst. Technol. 44(3), 1057–1069 (2020)
Xu, H., Yu, J., Liang, C., Zhang, X.: Detection method for small metal defects of improved RPN transmission line based on GAN. Chin. J. Electron Dev. 44(06), 1409–1416 (2021)
Fang, Z., Lin, W., Fan, S., et al.: A defects recognition method for small fittings in power transmission towers based on hierarchical recognition model. Electr. Power Inf. Commun. Technol. 18(9), 9 (2020)
Fu, J., Shao, G., Wu, L., et al.: Defect detection of line facility using hierarchical model with learning algorithm. High Voltage Eng. 43(1), 272–281 (2017)
Wang, K., Wang, J., Liu, G., et al.: Using improved strategies to improve the smart recognition rate of defects in pin on power fittings. Electr. Power Eng. Technol. 38(4), 80–85 (2019)
Song, X., Zhou, L., Li, Z., et al.: Review on superpixel methods in image segmentation. J. Image Graph. 5, 599–608 (2015)
Felzenswalb, P.F., Huttenloche, R.D.P.: Efficient graph-based images segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Achanta, R., Shaji, A., Smith, K., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Dong, Q., Yan, K., Sun, T., Zhang, S.: Improvement of grab cut algorithm based on SLIC superpixel algorithm. Huazhong Univ. Sci. Tech. (Nat. Sci. Edn.) 44, 43–47+66 (2016)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv:2006.03677 (2020)
Dosovitskiy, A., et al.: An image is worth 16 × 16 words: transformers for image recognition at scale. In: ICLR (2021)
Gao, X., Hoi, S.C.H., Zhang, Y., et al.: Sparse online learning of image similarity. ACM Trans. Intell. Syst. Technol. 8(5), 64:1–64:22 (2017)
Zhang, Y., Gao, X., Chen, Z., et al.: Mining spatial-temporal similarity for visual tracking. IEEE Trans. Image Process. 29, 8107–8119 (2020)
Li, W., Chen, Z., Gao, X., et al.: Multimodel framework for indoor localization under mobile edge computing environment. IEEE Internet Things J. 6(3), 4844–4853 (2019)
Gao, X., Xie, J., Chen, Z., et al.: Dilated convolution-based feature refinement network for crowd localization. In: ACM Transactions on Multimedia Computing, Communications, and Applications (2022)
Beal, J., Kim, E., Tzeng, E., et al.: Toward transformer based object detection [J/OL]. arXiv:2012.09958 [cs.CV] (2020). https://arxiv.org/abs/2012.09958
Acknowledgment
This work was funded by the “Research on the key technology of intelligent annotation of power image based on image self-learning” program of the Big Data Center, State Grid Corporation of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Z., Wang, L., Chen, S., Ren, J., Xue, M. (2023). A Defect Detection Method for Small Fittings of Power Transmission Based on Improved SLIC. In: Zhai, G., Zhou, J., Yang, H., Yang, X., An, P., Wang, J. (eds) Digital Multimedia Communications. IFTC 2022. Communications in Computer and Information Science, vol 1766. Springer, Singapore. https://doi.org/10.1007/978-981-99-0856-1_35
Download citation
DOI: https://doi.org/10.1007/978-981-99-0856-1_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0855-4
Online ISBN: 978-981-99-0856-1
eBook Packages: Computer ScienceComputer Science (R0)