基于多分支融合网络的遥感飞机检测算法

张顺; 赵倩; 赵琰

doi:doi:10.3969/j.issn.1671-637x.2023.03.019

电光与控制, 2023, 30 (3): 107, 网络出版: 2023-04-03

基于多分支融合网络的遥感飞机检测算法

A Remote Sensing Aircraft Detection Algorithm Based on Multi-Branch Fusion Network

论文大纲

张顺赵倩赵琰

作者单位

上海电力大学电子与信息工程学院, 上海 201000

遥感图像遥感飞机多分支残差网络 remote sensing image remote sensing aircraft Multi Branch-Residual Network(MBRNet) YOLOv4 YOLOv4 GhostNet GhostNet

摘要

针对目前遥感图像检测精度低、召回率低、实时性差等问题, 提出基于GhostNet和 CoT多分支残差网络(MBRNet)的遥感飞机检测算法。借鉴YOLOv4网络模型, 采用MBRNet作为新的主干网络, 从而减少梯度消失问题并弥补了CNN欠缺的全局特征计算能力; 为了减少小目标丢失问题, 同时在主干与PANet中引入多方位的特征提取与融合思路, 实现在高、低特征层之间和同尺度特征层之间的信息充分互补。提出的算法在具有背景复杂、过度曝光、目标密集等场景的RSOD 和LEVIR数据集上准确率达到了97.64%, 召回率达到了89.11%。

Abstract

Aiming at the problems of low detection accuracy, low recall rate, and poor real-time performance of remote sensing images, a remote sensing aircraft detection algorithm based on GhostNet and CoT(Contextual Transformer) Multi-Branch Residual Network (MBRNet) is proposed. Learning from the YOLOv4 network model, MBRNet is adopted as new backbone network to reduce the problem of gradient disappearance and makes up for the lack of global feature calculation capabilities of CNN. In order to reduce the problem of small target loss, multi-directional feature extraction and fusion are introduced into the backbone and PANet. The idea is to realize full complementation of information between high and low feature layers and between feature layers of the same scale.The proposed algorithm has an accuracy of 97.64% and a recall rate of 89.11% on RSOD and LEVIR data sets in the circumstance of complex background, overexposure and dense targets.

参考文献

[1] 谢梦, 刘伟, 杨梦圆, 等．深度卷积神经网络支持下的遥感影像飞机检测［J］．测绘通报, 2019(6):19-23.

[2] 张欣,张永强,何斌, 等.基于YOLOv4-tiny的遥感图像飞机目标检测技术研究［J］.光学技术,2021,47(3):344-351.

[3] 汪亚妮,汪西莉.基于注意力和特征融合的遥感图像目标检测模型［J］.激光与光电子学进展,2021,58(2):363-371.

[4] CARION N, MASSA F, SYNNAEVE G, et al.End-to-end object detection with transformers［R］.Los Alamos: arXiv Preprint, 2020:arXiv:2005.12872.

[5] REN S Q, HE K M, GIRSHICK R, et al.Faster R-CNN: towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.

[6] REDMON J, DIVVALA S K, GIRSHICK R, et al.You only look once:unified, real-time object detection［C］//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE, 2016:779-788.

[7] 于洋,李世杰,陈亮,等.基于改进YOLOv2的船舶目标检测方法［J］.计算机科学,2019,46(8):339-343.

[8] 公明, 刘妍妍, 李国宁．改进YOLO-v3的遥感图像舰船检测方法［J］.电光与控制, 2020, 27(5): 102-107.

[9] REDMON J, FARHADI A.YOLOv3:an incremental improvement［R］.Los Alamos: arXiv Preprint, 2018:arXiv1804.02767.

[10] 侯涛, 蒋瑜.改进YOLOv4在遥感飞机目标检测中的应用研究［J］.计算机工程与应用,2021,57(12):224-230.

[11] XU D Q, WU Y Q.Improved YOLO-V3 with DenseNet for multi-scale remote sensing target detection［J］.Sensors, 2020, 20(15):4276.

[12] HUANG G, LIU Z, LAURENS V D M, et al.Densely connected convolutional networks［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2017:4700-4708.

[13] BOCHKOVSKIY A, WANG C Y, LIAO H Y.YOLOv4:optimal speed and accuracy of object detection［R］.Los Alamos: arXiv Preprint, 2020:arXiv2004.10934.

[14] LIU S, QI L, QIN H F, et al.Path aggregation network for instance segmentation［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE, 2018:8759-8768.

[15] HU J, SHEN L, SUN G．Squeeze-and-excitation networks［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE, 2018:7132-7141.

[16] HAN K, WANG Y H, TIAN Q, et al.GhostNet:more features from cheap operations［C］//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle: IEEE, 2020:1577-1586.

[17] LI Y H, YAO T, PAN Y W, et al.Contextual transformer networks for visual recognitional［R］.Los Alamos: arXiv Preprint, 2021:arXiv:2107.12292.

[18] 田婷婷,杨军.基于多尺度特征融合网络的遥感影像目标检测［J］.激光与光电子学进展,2021,59(16):427-435.

[19] AGGARWAL S, SINGH P.Cuckoo, bat and krill herd based k-means++ clustering algorithms［J］.Cluster Computing, 2018, 22(6):14169-14180.

[20] 钟志峰,夏一帆,周冬平,等.基于改进YOLOv4的轻量化目标检测算法［J］.计算机应用,2022,42(7):2201-2209.

张顺, 赵倩, 赵琰. 基于多分支融合网络的遥感飞机检测算法[J]. 电光与控制, 2023, 30(3): 107. ZHANG Shun, ZHAO Qian, ZHAO Yan. A Remote Sensing Aircraft Detection Algorithm Based on Multi-Branch Fusion Network[J]. Electronics Optics & Control, 2023, 30(3): 107.

基于多分支融合网络的遥感飞机检测算法

关于本站 Cookie 的使用提示

全站搜索

基于多分支融合网络的遥感飞机检测算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索