[1]周为,吴涛,吴锡,等.特征融合和相移编码的遥感图像旋转目标检测[J].计算机技术与发展,2025,(04):22-28.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0361]
　ZHOU Wei,WU Tao,WU Xi,et al.Rotating Object Detection in Remote Sensing Images via Feature Fusion and Phase Shifting Coder[J].,2025,(04):22-28.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0361]
点击复制

特征融合和相移编码的遥感图像旋转目标检测

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年04期
页码:
22-28
栏目:
媒体计算
出版日期:
2025-04-10

文章信息/Info

Title:
Rotating Object Detection in Remote Sensing Images via Feature Fusion and Phase Shifting Coder
文章编号:
1673-629X(2025)04-0022-07
作者:
周为; 吴涛; 吴锡; 符颖
成都信息工程大学 计算机学院,四川 成都 610200
Author(s):
ZHOU Wei; WU Tao; WU Xi; FU Ying
School of Computer Science,Chengdu University of Information Technology,Chengdu 610200,China
关键词:
遥感图像; 目标检测; 相移编码; 边界不连续; 旋转框
Keywords:
remote sensing images; object detection; phase-shifting coder; boundary discontinuity; rotated box
分类号:
TP751/P2
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0361
摘要:
针对现有的旋转目标检测模型对目标朝向任意、排列密集的遥感图像检测精度较低的问题,该文提出了一种基于多尺度特征融合和两倍步长相移编码的遥感图像旋转目标检测算法。 首先利用不同大小和深度的卷积进行特征提取,有效地捕获上下文特征;然后,通过自上而下和自下而上的特征融合策略以获取更加精细和丰富的语义特征图;同时引入了两倍步长相移编码模块(Double Stepsize Phase-Shifting Coder,DSPSC)对于角度进行编码后再求损失,解决了基准模型存在的边界不连续问题,从而进一步提高了模型的检测精度;最后,在大规模数据集 DOTA 和 HRSC2016 上的实验结果表明,平均检测精度分别为 72. 97% 和 90. 10% ,较基准网络分别提升了 2. 89 百分点和 2. 70 百分点。 与其它对比方法相比,该方法在精度上取得最好结果,证明了其在遥感图像旋转目标检测上的有效性。
Abstract:
The existing rotating target detection modals suffer from low inference accuracy when detecting targets with arbitrary orientations and dense arrangements in remote sensing images. We propose a remote sensing image rotation target detection algorithm based on multi-scale feature fusion and double stepsize phase-shifting coder. Firstly,we use convolutional layers of different sizes and depths to extract features,effectively capturing contextual features. Then,a top-down and bottom-up feature fusion strategy is employed to obtain finer and richer semantic feature maps. Meanwhile,we introduce a DSPSC (Double Stepsize Phase-Shifting Coder) module to encode angles and compute losses,addressing the discontinuity issue in the baseline modal and further improving the detection accuracy.Finally,experimental results on large-scale datasets DOTA and HRSC2016 demonstrate the average detection accuracy is 72. 97% and 90. 10% ,respectively,which is 2. 89 percentage points and 2. 70 percentage points higher than that of the baseline network. Compared with other comparative methods,the proposed method exhibits advantages in accuracy,demonstrating its effectiveness in remote sensing image rotation target detection.

相似文献/References:

[1]蒋璐璐 王适 王宝成 李慧敏 李鑫慧.一种改进的标记分水岭遥感图像分割方法[J].计算机技术与发展,2010,(01):36.
　JIANG Lu-lu,WANG Shi,WANG Bao-cheng,et al.Segmentation of Remote Sensing Image Based on an Improved Labeling Watershed Algorithm[J].,2010,(04):36.
[2]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(04):29.
[3]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(04):179.
[4]赵艳飞 高清维 卢一相.基于多尺度Retinex算法的遥感图像增强[J].计算机技术与发展,2008,(02):70.
　ZHAO Yan-fei,GAO Qing-wei,LU Yi-xiang.Remote Sensing Image Enhancement Based on Multi- Scale Retinex Algorithm[J].,2008,(04):70.
[5]陈昌生 许文波 赵健.基于ArcSDE的卫星遥感影像数据库研究[J].计算机技术与发展,2010,(07):80.
　CHEN Chang-sheng,XU Wen-bo,ZHAO Jian.Research on Remote Sensing Image Database Based on ArcSDE[J].,2010,(04):80.
[6]李晓飞 马大玮 范小麟 胡焰智.基于数学形态学的遥感图像多感兴趣区域提取[J].计算机技术与发展,2007,(12):56.
　LI Xiao-fei,MA Da-wei,FAN Xiao-lin,et al.Extraction of ROIs Based on Mathematical Morphology toward Applications on Remote Sense Image Processing[J].,2007,(04):56.
[7]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(04):60.
[8]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(04):181.
[9]董敏[],阎镇.基于CUDA的航天遥感图像实时快视系统的研究[J].计算机技术与发展,2014,24(06):32.
　DONG Min[][][],YAN Zhen[].Research on Aerospace Remote Sensing Images Real-time Quick-view System Based on CUDA[J].,2014,24(04):32.
[10]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(04):37.
[11]张永福,宋海林,班 越,等.融合特征的深度学习遥感图像目标检测模型[J].计算机技术与发展,2021,31(09):48.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 009]
　ZHANG Yong-fu,SONG Hai-lin,BAN Yue,et al.Fusion Features Based Deep Learning Remote Sensing Image Target Detection Model[J].,2021,31(04):48.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 009]
[12]张永福,宋海林.基于跳跃特征金字塔的域适应目标检测模型[J].计算机技术与发展,2022,32(09):28.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 005]
　ZHANG Yong-fu,SONG Hai-lin.Skip Feature Pyramid Based Domain Adapted Model for Object Detection[J].,2022,32(04):28.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 005]
[13]薛继伟,孙宇锐.基于改进 YOLOv5 的光学遥感图像水坝检测研究[J].计算机技术与发展,2023,33(05):69.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 011]
　XUE Ji-wei,SUN Yu-rui.Research on Dam Detection of Optical Remote Sensing Image Based on Improved YOLOv5[J].,2023,33(04):69.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 011]
[14]彭芳,贺智明.信息收集和分发机制的遥感图像目标检测算法[J].计算机技术与发展,2025,(01):46.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0293]
　PENG Fang,HE Zhi-ming.Remote Sensing Image Object Detection Algorithm Based on Information Gather-and-distribute Mechanism[J].,2025,(04):46.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0293]

更新日期/Last Update: 2025-04-10