| 2,596 | 17 | 100 |
| 下载次数 | 被引频次 | 阅读次数 |
针对目前遥感图像目标检测算法中存在的误检、漏检和检测精度低等问题，提出了一种改进YOLOv8的遥感图像检测算法。在主干网络中引入注意力机制EMA到C2f模块，以提高模型对多尺度目标的特征提取能力；在颈部网络中提出Slim-PAN结构，以减少模型计算量；使用WIOU损失函数代替CIOU损失函数，以提升模型的检测精度。通过在DIOR和RSOD遥感数据集上的实验结果表明，改进后的算法与原YOLOv8算法相比，mAP分别提升了1.5%和2.3%,计算量降低了0.3 GFLOPs,改进算法在不增加计算量的同时能提高检测精度，证明了改进算法的有效性和先进性。
Abstract：An improved YOLOv8 remote sensing image detection algorithm is proposed to address the issues of false detection, missed detection, and low detection accuracy in current remote sensing image object detection algorithms.Attention mechanism EMA is introduced into the C2f module in the backbone network to improve the model's feature extraction ability for multi-scale objects.A Slim-PAN structure is proposed in the neck network to reduce the model computational complexity.WIOU loss function is used instead of CIOU loss function to improve the detection accuracy of the model.The experimental results on DIOR and RSOD remote sensing datasets show that compared with the original YOLOv8 algorithm, the mAP of the improved algorithm is increased by 1.5% and 2.3% respectively, and the calculation amount is reduced by 0.3 GFLOPs, which reflects that the improved algorithm can improve the detection accuracy without increasing the calculation amount, and the effectiveness and advancement of the improved algorithm is proved.
[1] 李阿标，郭浩，戚畅，等.复杂背景下遥感图像密集目标检测[J].计算机工程与应用，2023,59(8):247-253.
[2] 余俊宇，刘孙俊，许桃.融合注意力机制的YOLOv7遥感小目标检测算法研究[J].计算机工程与应用，2023,59(20):167-175.
[3] 付涵，范湘涛，严珍珍，等.基于深度学习的遥感图像目标检测技术研究进展[J].遥感技术与应用，2022,37(2):290-305.
[4] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:580-587.
[5] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1440-1448.
[6] CAI Z W,VASCONCELOS N.Cascade R-CNN:Delving into High Quality Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:6154-6162.
[7] REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-time Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:779-788.
[8] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[EB/OL].(2018-04-08)[2023-09-04].https://arxiv.org/abs/1804.02767.
[9] LI C Y,LI L L,JIANG H L,et al.YOLOv6:A Single-stage Object Detection Framework for Industrial Applications[J].(2022-09-07)[2023-12-04].https://arxiv.org/abs/2209.02976.
[10] LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot Multibox Detector[C]//Computer Vision-ECCV 2016:14th European Conference.Amsterdam:ECCV,2016:21-37.
[11] ZHANG H K,CHANG H,MA B P,et al.Cascade Retinanet:Maintaining Consistency for Single-stage Object Detection[J].(2019-07-16)[2023-09-04].https://arxiv.org/abs/1907.06881.
[12] DUAN K W,BAI S,XIE L X,et al.Centernet:Keypoint Triplets for Object Detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Seoul:IEEE,2019:6568-6577.
[13] HOU Y J,SHI G,ZHAO Y X,et al.R-YOLO:A YOLO-based Method for Arbitrary-oriented Target Detection in High-resolution Remote Sensing Images[J].Sensors,2022,22(15):5716.
[14] 张上，张岳，王恒涛，等.轻量化无人机遥感图像小目标检测算法[J].无线电工程，2023,53(10):2329-2336.
[15] WAN D H,LU R S,WANG S L,et al.YOLO-HR:Improved YOLOv5 for Object Detection in High-resolution Optical Remote Sensing Images[J].Remote Sensing,2023,15(3):614.
[16] 梁秀满，贾梓涵，于海峰，等.基于改进YOLOv7的无人机图像目标检测算法[J/OL].(2023-10-17)[2023-12-04].http://kns.cnki.net/kcms/detail/13.1097.TN.20231013.1804.010.html.
[17] OUYANG D L,HE S,ZHANG G Z,et al.Efficient Multi-scale Attention Module with Cross-spatial Learning[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).Rhodes Island:IEEE,2023:1-5.
[18] TONG Z J,CHEN Y H,XU Z W,et al.Wise-IoU:Bounding Box Regression Loss with Dynamic Focusing Mechanism[EB/OL].(2023-01-24)[2023-12-04].https://arxiv.org/abs/2301.10051.
[19] ZHENG Z H,WANG P,REN D W,et al.Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation[J].IEEE Transactions on Cybernetics,2021,52(8):8574-8586.
[20] LI K,WAN G,CHENG G,et al.Object Detection in Optical Remote Sensing Images:A Survey and a New Benchmark[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,159:296-307.
[21] LONG Y,GONG Y P,XIAO Z F,et al.Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(5):2486-2498.
[22] LI H L,LI J,WEI H B,et al.Slim-neck by GSConv:A Better Design Paradigm of Detector Architectures for Autonomous Vehicles[EB/OLJ].(2022-08-17)[2023-12-04].https://arxiv.org/abs/2206.02424.
基本信息:
中图分类号:TP751
引用信息:
[1]程换新,矫立浩,骆晓玲,等.改进YOLOv8的遥感图像检测算法[J].无线电工程,2024,54(05):1155-1161.
基金信息:
国家自然科学基金(62273192)~~
2024-01-18
2024-01-18
2024-01-18