A Novel Foreign Object Detection Method in Transmission Lines Based on Improved YOLOv8n
Source abstract
Abstract
The rapid pace of urban development has resulted in the widespread presence of construction equipment and increasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safe operation of the power grid. Machine vision technology, particularly object recognition technology, has been widely employed to identify foreign objects in transmission line images. Despite its wide application, the technique faces limitations due to the complex environmental background and other auxiliary factors. To address these challenges, this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replaced with a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizing low-resolution and small-size objects. The algorithm's feature extraction network is improved by using a Large Selective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally, the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate faster convergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves a detection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which is a significant enhancement compared to the unimproved algorithm. This improvement effectively enhances the accuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Power Line Inspection Robots · Advanced Data and IoT Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (37)
Show source-provided references
1. Automatic polyp detection by combining conditional generative adversarial network and modified you-only-look-once10.1109/JSEN.2022.3170034 ↗
2. A drone-based data management and optimization using metaheuristic algorithms and blockchain smart contracts in a secure fog environment10.1016/j.compeleceng.2022.108234 ↗
3. BIoMT: A state-of-the-art consortium serverless network architecture for healthcare system using blockchain smart contracts10.1109/ACCESS.2022.3194195 ↗
4. On definition of deep learning
5. Rich feature hierarchies for accurate object detection and semantic segmentation
6. Fast R-CNN
7. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
8. R–FCN: Object Detection via region-based fully convolutional networks
9. You only look once: Unified, real-time object detection
10. YOLO9000: Better, faster, stronger
11. J. Redmon and A. Farhadi, “YOlOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
12. A. Bochkovskiy, C. Y. Wang, and H. Y. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
13. SSD: Single shot MultiBox detector
14. C. Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg, “DSSD: Deconvo- lutional single shot detector,” arXiv preprint, arXiv:1701.06659, 2017.
15. Z. X. Li and F. Zhou, “FSSD: Feature fusion single shot multibox detector,” arXiv preprint arXiv:1712.00960, 2017.
16. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, “Overfeat: Integrated recognition, localization and detection using convolutional networks,” arXiv preprint arXiv:1312.6229, 2013.
17. Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles10.1109/TITS.2022.3158253 ↗
18. Recognition of insulators in grid inspection images,” (in Chinese)
19. Research on aerial insulator detection method of aerial transmission lines based on YOLOv3
20. Anchorless frame SAR image ship target detection based on YOLO framework
21. Transmission line detection based on YOLO target detection algorithm
22. S. H. Su, “Research and application of target recognition of transmission lines construction machinery based on improved faster R-CNN,” Ph.D. dissertation, Shandong Univ., China, 2021.
23. CBAM: Convolutional block attention Module
24. Detection and identification of engineering vehicles in transmission corridor based on improved YoloX
25. N. Shao, “Research on the key technology of deep learning-based transmission lines hazardous object identification,” Ph.D. dissertation, Shandong Univ., China, 2020.
26. Large selective kernel network for remote sensing object detection
27. Distance-IoU loss: Faster and better learning for bounding box regression
28. Detection and identification of fish in electronic monitoring data of commercial fishing vessels based on improved YOLOv8
29. An improved dense pedestrian detection algorithm for YOLOv8
30. Z. J. Tong, Y. H. Chen, Z. W. Xu, and R. Yu, “Wise-IoU: Bounding box regression loss with dynamic focusing mechanism,” arXiv preprint arXiv:2301.10051, 2023.
31. Low-altitude flying object target detection method based on improved YOLO v7
32. SPD-based improved YOLOv5 for crowd area density analysis of bus stops
33. Bounding box regression with uncertainty for accurate object detection
34. YOLO-SPD: Tiny objects localization on remote sensing based on You Only Look Once and Space-to-Depth Convolution
35. Squeeze-and-Excitation networks
36. Efficient multi-scale attention module with cross-spatial learning
37. Design and development of AR home decoration system based on Vuforia SDK development