Improving YOLOv5's domestic optical image radiation anomaly detection method

doi:10.13474/j.cnki.11-2246.2024.0811

Abstract

Abstract: With the continuous increase in the number of domestic optical satellites, the obtained satellite image data has shown a large-scale increase. There is a considerable proportion of image radiation anomalies in the images obtained by satellites and processed through sensor correction. Image radiation quality is an important factor determining the evaluation of image quality inspection level. Currently, its inspection mainly adopts human-computer interaction. In response to the current radiation problem in optical image quality inspection, an improved YOLOv5 deep learning network is proposed to identify targets in radiation abnormal areas. Integrate the improved light BiFPN feature fusion network and ShuffleNetV2 backbone network into YOLOv5s. By exploring the principle of image radiation anomalies, this network can accurately determine the range of targets in radiation anomaly images. The trained model can effectively detect the range of radiation issues through anchor frames, lay the foundation for further model deployment and application.

Key words: deep learning, light weight, remote sensing images, radiation anomaly, object detection

CLC Number:

P237

SHI Yijian, TAN Hai, ZHONG Xuhui. Improving YOLOv5's domestic optical image radiation anomaly detection method[J]. Bulletin of Surveying and Mapping, 2024, 0(8): 60-65,72.

References

[1] 马单丹. 高光谱遥感影像异常目标检测的关键问题研究[D]. 西安: 中国科学院大学(中国科学院西安光学精密机械研究所), 2019.
[2] 马晓晓. 基于表示学习的高光谱遥感影像异常检测[D]. 西安: 西安电子科技大学, 2021.
[3] 谭海,张荣军,樊文锋,等. 融合多尺度特征的国产光学影像辐射异常分类检测[J]. 自然资源遥感,2022,34(4): 97-104.
[4] 邵延华,张铎,楚红雨,等. 基于深度学习的YOLO目标检测综述[J]. 电子与信息学报,2022,44(10): 3697-3708.
[5] ZHANG Xiangyu,ZHOU Xinyu,LIN Mengxiao,et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE.2017.
[6] MA Ningning,ZHANG Xiangyu,ZHENG Haitao,et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[M]//Proceedings of Computer Vision-ECCV 2018. Cham: Springer International Publishing,2018: 122-138.
[7] SANDLER M,HOWARD A,ZHU Menglong,et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018.
[8] DENG Jia,DONG Wei,SOCHER R,et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,FL:IEEE,2009.
[9] LI,Z,PENG, C,YU,G,et al. Light-head R-CNN: in defense of two-stage object detector[J].Computer Science,2017:20405715.
[10] IOANNOU Y,ROBERTSON D,CIPOLLA R,et al.Deep roots: improving cnn efficiency with hierarchical filter groups[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,HI:IEEE,2017.
[11] 潘桂霞,赖惠成,王同官,等. 一种Yolov5颈部细化的小交通标志检测算法[J]. 现代电子技术,2023,46(14): 56-62.
[12] 许德刚,王露,李凡. 深度学习的典型目标检测算法研究综述[J]. 计算机工程与应用,2021,57(8): 10-25.
[13] 谈世磊,别雄波,卢功林,等. 基于YOLOv5网络模型的人员口罩佩戴实时检测[J]. 激光杂志,2021,42(2): 147-150.
[14] 马琳琳,马建新,韩佳芳,等. 基于YOLOv5s目标检测算法的研究[J]. 电脑知识与技术,2021,17(23): 100-103.
[15] 李阿娟. YOLOv5算法改进及其现实应用[D]. 太原: 中北大学,2021.
[16] 邱天衡,王玲,王鹏,等. 基于改进YOLOv5的目标检测算法研究[J]. 计算机工程与应用,2022,58(13): 63-73.
[17] 谭显东,彭辉. 改进YOLOv5的SAR图像舰船目标检测[J]. 计算机工程与应用,2022,58(4): 247-254.
[18] 李一鸣,王潇. 基于YOLOv5s模型的轧钢表面缺陷检测[J]. 制造业自动化,2021,43(11): 117-119.