Bird Detection on Power Transmission Lines Based on Improved YOLOv7
Abstract
:1. Introduction
1.1. Motivation
1.2. Related Work
2. YOLOv7 Model
3. Enhanced YOLO v7 Model
3.1. Our Work
- We introduce the ODConv in the backbone of YOLOv7. This method retains a substantial portion of spatial information, thereby enhancing the network’s sensitivity to small-scale targets without inflating the model’s parameter size. The ODConv module also helps mitigate the impact of noise.
- Additionally, to address the issue of unstable loss function convergence during small object detection, this paper adopts the Alpha_GIoU function, thereby improving the network’s robustness concerning target sizes.
- Finally, a series of data augmentation such as mixup and multi-angle rotation are added to the dataset for model training to mitigate the impact of insufficient data.
3.2. A New Dynamic Convolutional Kernels of ODConv
3.3. Alpha_GIoU Loss Function
- -
- quantifies the relationship between the predicted bounding box and the target bounding box by typically representing the ratio of the intersection area of these bounding boxes to their union area.
- -
- represents the area of the smallest convex polygon encompassing both bounding boxes.
- -
- denotes the area encompassed by the union of the two bounding boxes.
- -
- signifies the value of the loss function.
4. Experimentation and Analysis
4.1. Experimental Environment and Hyperparameters
4.2. Experimental Dataset
4.3. Evaluation Metrics
- -
- [email protected] signifies the average detection accuracy at an Intersection over Union (IOU) [13] threshold of 0.5 for all object categories. It reflects the algorithm’s accuracy in detecting various object categories.
- -
- [email protected]:0.95 represents the mean average precision over a range of 10 IOU thresholds, spanning from 0.5 to 0.95, with intervals of 0.05. This metric provides a comprehensive assessment of detection accuracy across various IOU thresholds.
- -
- Precision (P) represents the ratio of true positive detections to the total number of detections, indicating the algorithm’s precision in correctly identifying bird objects.
4.4. Introduce the ODConv in the Backbone of YOLOv7
4.5. Evaluate the Impact of ODConv on Model Accuracy
4.5.1. Comparing Results from Experiments Introducing Attention Mechanism
4.5.2. Contrast Experiment Results of IoU
5. Ablation Experiment
5.1. Experimental Comparison between YOLOv7 and the Improved Network Model
5.2. Comparative Analysis of the Improved YOLOv7 Network Model with Other Network Models
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Billings, K.; Morey, T. Switchmode Power Supply Handbook, 3rd ed.; McGraw-Hill Education: New York, NY, USA, 2011. [Google Scholar]
- Lie, J.; Yu, J.; E, M.; Wang, L.; Yang, Z.J.; Wang, H. Research on application and effect of anti-bird facilities on high voltage transmission lines. J. Northeast. Norm. Univ. Nat. Sci. Ed. 2013, 45, 118–121. (In Chinese) [Google Scholar]
- Wu, B.; Wu, X.; Liu, S.; Yan, Z.; Chang, B.; Jia, Z.; Jiang, J.; Ouyang, X. Simulation study on bird streamer flashover of 330 kV transmission line. High Volt. Appar. 2018, 54, 120–127. (In Chinese) [Google Scholar]
- Tang, Z.; Yuan, X.; Liao, Z.; Ye, B.; Wang, R.; Wu, Z. Statistics analysis and protection of bird fault of Guangdong Shaoguan power grid. Insul. Surge Arresters 2018, 20–24. (In Chinese) [Google Scholar]
- Ou, S.; Wang, Y.; Yang, W. Failure analysis and its precaution measure on bird damage to inner Mongolia power grid. Inn. Mong. Electr. Power Technol. 2007, 25, 1–3. (In Chinese) [Google Scholar]
- Ma, Z. Importance of habitat protection for bird protection. Bull. Biol. 2017, 52, 6–8. (In Chinese) [Google Scholar]
- Huang, X.; Cao, W. Review of the disaster mechanism of transmission lines. J. Xi’an Polytech. Univ. 2017, 31, 589–605. (In Chinese) [Google Scholar]
- Lu, M.; Tan, F.; He, Z.; Liu, Z.; Song, S.; Fan, W.; Wang, W. Research on the mechanism of guano flashover in 110 kV transmission lines. Insul. Surge Arresters 2015, 1–7. [Google Scholar] [CrossRef]
- IEEE Std 1651-2010; IEEE Guide for Reducing Bird-Related Outages. IEEE: New York, NY, USA, 2011; pp. 1–32.
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1137–1149. [Google Scholar] [CrossRef]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single shot MultiBox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016; Proceedings, Part I 14; Springer International Publishing: Berlin/Heidelberg, Germany, 2016. [Google Scholar]
- Chen, Y.; Sun, L.; Zhang, Y.; Fu, Q.; Lu, Y.; Li, Y.; Sun, J. Research on Transmission Line Bird Detection Technology based on YOLO v3. Comput. Eng. 2020, 46, 294–300. [Google Scholar]
- Bochkovskiy, A.; Wang, C.Y.; Liao, H.Y.M. Yolov4: Optimal Speed and Accuracy of Object Detection. arXiv 2020, arXiv:2004.10934. [Google Scholar]
- Zou, C.; Liang, Y. Bird Detection on Transmission Line Based on YOLO V3 Algorithm. Comput. Appl. Softw. 2021, 38, 164–167. (In Chinese) [Google Scholar]
- Chen, C.; Xiong, Y.; Yan, B.P. Wild birds target detection and tracking technology in video system. E-Sci. Technol. Appl. 2014, 5, 53–58. [Google Scholar]
- Wang, C.-Y.; Bochkovskiy, A.; Liao, H.-Y.M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv 2023, arXiv:2207.02696v1. [Google Scholar]
- Li, S.; Wang, Z.; Liu, Z.; Tan, C.; Lin, H.; Wu, D.; Chen, Z.; Zheng, J.; Li, S.Z. Efficient Multi-order Gated Aggregation Network. arXiv 2022, arXiv:2211.03295. [Google Scholar] [CrossRef]
- Wang, C.Y.; Bochkovskiy, A.; Liao, H.Y.M. Scaled-YOLOv4: Scaling cross stage partial network. In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; IEEE Press: New York, NY, USA, 2021; pp. 13024–13033. [Google Scholar]
- Ding, X.H.; Zhang, X.Y.; Ma, N.N.; Han, J.G.; Ding, G.G.; Sun, J. RepVGG: Making VGG-style ConvNets great again. In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20–25 June 2021; IEEE Press: New York, NY, USA, 2021; pp. 13728–13737. [Google Scholar]
- Jiang, T.T.; Cheng, J.Y. Target recognition based on CNN with LeakyReLU and PReLU activation functions. In Proceedings of the 2019 IEEE Conference on Sensing, Diagnostics, Prognostics, and Control, Beijing, China, 15–17 August 2019; IEEE Press: New York, NY, USA, 2019; pp. 718–722. [Google Scholar]
- Ge, Z.; Liu, S.T.; Wang, F.; Li, Z.; Sun, J. YOLOX: Exceeding YOLO Series in 2021[EB/OL]. Available online: https://arxiv.org/abs/2107.08430 (accessed on 23 August 2022).
- Yang, B.; Bender, G.; Le, Q.V.; Ngiam, J. Condconv: Conditionally parameterized convolutions for efficient inference. Adv. Neural Inf. Process. Syst. 2019, 32. [Google Scholar] [CrossRef]
- Chen, Y.; Dai, X.; Liu, M.; Chen, D.; Yuan, L.; Liu, Z. Dynamic convolution: Attention over convolution kernels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020. [Google Scholar]
- Li, C.; Zhou, A.; Yao, A. Omni-Dimensional Dynamic Convolution. arXiv 2022, arXiv:2209.07947. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention Is All You Need. arXiv 2017, arXiv:1706.03762. [Google Scholar] [CrossRef]
- He, J.; Erfani, S.; Ma, X.; Bailey, J.; Chi, Y.; Hua, X.-S. Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression. arXiv 2021, arXiv:2110.13675. [Google Scholar] [CrossRef]
Method | [email protected] | [email protected]:0.95 | Precision |
---|---|---|---|
YOLOv7 | 75.84 | 45.42 | 71.22 |
SE-YOLOv7 | 73.36 | 43.56 | 68.23 |
ECA -YOLOv7 | 75.42 | 44.3 | 69.96 |
ODConv-YOLOV7 | 77.15 | 45.76 | 72.35 |
ODConv | Alpha_GIoU | [email protected] | [email protected]:0.95 | Precision |
---|---|---|---|---|
x | x | 75.84 | 45.42 | 71.22 |
√ | x | 77.15 | 45.76 | 72.35 |
x | √ | 76.84 | 45.56 | 72.22 |
√ | √ | 78.42 | 46.14 | 73.56 |
Comparative Models | mAP0.5 | mAP0.5:0.95 | Precision |
---|---|---|---|
YOLOv7 | 75.84 | 45.42 | 71.22 |
YOLOv8 | 75.13 | 43.27 | 71.87 |
YOLOv5 | 74.3 | 43.41 | 70.69 |
YOLOx | 77.5 | 44.56 | 72.35 |
The algorithm in this paper | 78.42 | 46.14 | 73.56 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jiang, T.; Zhao, J.; Wang, M. Bird Detection on Power Transmission Lines Based on Improved YOLOv7. Appl. Sci. 2023, 13, 11940. https://doi.org/10.3390/app132111940
Jiang T, Zhao J, Wang M. Bird Detection on Power Transmission Lines Based on Improved YOLOv7. Applied Sciences. 2023; 13(21):11940. https://doi.org/10.3390/app132111940
Chicago/Turabian StyleJiang, Tingyao, Jian Zhao, and Min Wang. 2023. "Bird Detection on Power Transmission Lines Based on Improved YOLOv7" Applied Sciences 13, no. 21: 11940. https://doi.org/10.3390/app132111940
APA StyleJiang, T., Zhao, J., & Wang, M. (2023). Bird Detection on Power Transmission Lines Based on Improved YOLOv7. Applied Sciences, 13(21), 11940. https://doi.org/10.3390/app132111940