基于形状自适应标签分配的遥感有向目标检测网络

任王; 吴斌; 余长宏; 曾文捷

doi:10.11959/j.issn.1000-0801.2026035

您当前的位置：

首页 >

文章列表页 >

基于形状自适应标签分配的遥感有向目标检测网络

研究与开发 | 更新时间：2026-03-05

- 基于形状自适应标签分配的遥感有向目标检测网络
- Shape-adaptive label assignment for oriented object detection network
- 电信科学 2026年42卷第2期页码：148-160
- 作者机构：
  
  浙江工商大学信息与电子工程学院，浙江杭州 310018
- 作者简介：
  
  [ "任王（1981- ），男，博士，浙江工商大学信息与电子工程学院副教授，主要研究方向为无线通信和信号处理。" ]
  [ "吴斌（2000- ），男，浙江工商大学信息与电子工程学院硕士生，主要研究方向为数字图像处理。" ]
  [ "余长宏（1978- ），男，博士，浙江工商大学信息与电子工程学院副教授，主要研究方向为智能计算和大数据应用。" ]
  [ "曾文捷（2001- ），男，浙江工商大学信息与电子工程学院硕士生，主要研究方向为遥感图像目标检测。" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2026035
  中图分类号： TN957;TP751
- 收稿：2025-03-13，
  
  修回：2025-09-27，
  
  录用：2025-10-17，
  
  纸质出版：2026-02-20
- 稿件说明：
移动端阅览
任王,吴斌,余长宏等.基于形状自适应标签分配的遥感有向目标检测网络[J].电信科学,2026,42(02):148-160.

Ren Wang,Wu Bin,Yu Changhong,et al.Shape-adaptive label assignment for oriented object detection network[J].Telecommunications Science,2026,42(02):148-160.
任王,吴斌,余长宏等.基于形状自适应标签分配的遥感有向目标检测网络[J].电信科学,2026,42(02):148-160. DOI： 10.11959/j.issn.1000-0801.2026035.

Ren Wang,Wu Bin,Yu Changhong,et al.Shape-adaptive label assignment for oriented object detection network[J].Telecommunications Science,2026,42(02):148-160. DOI： 10.11959/j.issn.1000-0801.2026035.

摘要

针对遥感图像中大纵横比目标因正样本不足而出现的学习不充分问题，提出一种基于形状自适应标签分配的遥感有向目标检测网络（shape-adaptive label assignment for oriented object detection network，SALANet）。首先，引入纵横比敏感系数建立目标几何特征与正样本数量的动态映射关系，缓解传统方法中固定分配规则引发的样本分布不平衡问题；其次，设计自适应标签分配策略，通过对交并比（intersection over union，IoU）进行排名实现高质量正样本选择；最后，提出中心轴先验，将圆形中心先验区扩展为目标中心轴的矩形区域，增强大纵横比目标的几何特征表征能力。在DOTAv1.0和HRSC2016数据集上的对比实验表明，SALANet分别取得0.777 1和0.932 3的平均精度均值（mean average precision，mAP），较基线方法RoI Transformer分别提升8.15%和2.87%。

Abstract

To address the issue of insufficient learning caused by the lack of positive samples for large aspect ratio targets in remote sensing images

a shape-adaptive label assignment network for oriented object detection (SALANet) was proposed. Firstly

an aspect ratio sensitivity coefficient was introduced to establish a dynamic mapping relationship between target geometric features and the number of positive samples

alleviating the sample distribution imbalance caused by fixed allocation rules in traditional methods. Secondly

an adaptive label assignment strategy was designed to prioritize high-quality positive samples through intersection over union (IoU) ranking. Finally

a central axis prior was proposed

extending the circular central prior region to a rectangular region along the target’s central axis

thereby enhancing the geometric feature representation capability for large aspect ratio targets. Comparative experiments on the DOTAv1.0 and HRSC2016 datasets demonstrated that SALANet achieved mAP scores of 0.777 1 and 0.932 3

respectively

representing improvements of 8.15% and 2.87% over the baseline method RoI Transformer.

关键词

Keywords

references

Ren S Q , He K M , Girshick R , et al . Faster R-CNN: towards real-time object detection with region proposal networks [C ] // Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence . Piscataway : IEEE Press , 2016 : 1137 - 1149 .

Redmon J , Divvala S , Girshick R , et al . You only look once: unified, real-time object detection [C ] // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2016 : 779 - 788 .

姚婷婷 , 肇恒鑫 , 冯子豪 , 等 . 上下文感知多感受野融合网络的定向遥感目标检测 [J ] . 电子与信息学报 , 2025 , 47 ( 1 ): 233 - 243 .

Yao T T , Zhao H X , Feng Z H , et al . A context-aware multiple receptive field fusion network for oriented object detection in remote sensing images [J ] . Journal of Electronics & Information Technology , 2025 , 47 ( 1 ): 233 - 243 .

Ma J Q , Shao W Y , Ye H , et al . Arbitrary-oriented scene text detection via rotation proposals [J ] . IEEE Transactions on Multimedia , 2018 , 20 ( 11 ): 3111 - 3122 .

Ding J , Xue N , Long Y , et al . Learning RoI transformer for oriented object detection in aerial images [C ] // Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2020 : 2844 - 2853 .

Xu Y C , Fu M T , Wang Q M , et al . Gliding vertex on the horizontal bounding box for multi-oriented object detection [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 43 ( 4 ): 1452 - 1459 .

胡齐 . 基于特征回归和双中点向量表示的遥感目标检测算法研究 [D ] . 开封 : 河南大学 , 2024 .

Hu Q . Research on remote sensing object detection algorithm based on feature regression and double midpoint vector representation [D ] . Kaifeng : Henan University , 2024 .

Yu L B , Zhou Y , Li X L , et al . A rotating object detector with convolutional dynamic adaptive matching [J ] . Applied Sciences , 2024 , 14 ( 2 ): 633 .

谢明杰 . 基于自适应标签分配策略的遥感目标检测方法研究 [D ] . 哈尔滨 : 哈尔滨工程大学 , 2024 .

Xie M J . Research on remote sensing object detection method based on adaptive label assignment strategy [D ] . Harbin : Harbin Engineering University , 2024 .

徐丹青 , 吴一全 . 光学遥感图像目标检测的深度学习算法研究进展 [J ] . 遥感学报 , 2024 , 28 ( 12 ): 3045 - 3073 .

Xu D Q , Wu Y Q . Progress of research on deep learning algorithms for object detection in optical remote sensing images [J ] . National Remote Sensing Bulletin , 2024 , 28 ( 12 ): 3045 - 3073 .

Lin Y T , Feng P M , Guan J , et al . IENet: interacting embranchment one stage anchor free detector for orientation aerial object detection [PP ] . arXiv ( 2019-12-02 )[ 2021-03-29 ] . arXiv: arXiv. 1912 . 00969 .

Xiao Z F , Qian L J , Shao W P , et al . Axis learning for orientated objects detection in aerial images [J ] . Remote Sensing , 2020 , 12 ( 6 ): 908 .

李士博 , 肖振久 , 曲海成 , 等 . 面向SAR图像舰船检测的多粒度特征与形位相似度量方法 [J ] . 光电工程 , 2025 , 52 ( 2 ): 44 - 58 .

Li S B , Xiao Z J , Qu H C , et al . Multi-granularity feature and shape-position similarity metric method for ship detection in SAR images [J ] . Opto-Electronic Engineering , 2025 , 52 ( 2 ): 44 - 58 .

Zhang S F , Chi C , Yao Y Q , et al . Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection [C ] // Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2020 : 9756 - 9765 .

余颖 . 复杂场景下遥感图像任意方向目标检测方法研究 [D ] . 西安 : 西安电子科技大学 , 2023 .

Yu Y . Research on arbitrary-oriented object detection methods in remote sensing images under complex scenes [D ] . Xi’an : Xidian University , 2023 .

Ming Q , Zhou Z Q , Miao L J , et al . Dynamic anchor learning for arbitrary-oriented object detection [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 3 ): 2355 - 2363 .

董燕 , 魏铭宏 , 高广帅 , 等 . 基于双重标签分配的遥感有向目标检测方法 [J ] . 计算机科学 , 2024 , 51 ( S2 ): 496 - 504 .

Dong Y , Wei M H , Gao G S , et al . Remote sensing orineted object detection method based on dual-label assignment [J ] . Computer Science , 2024 , 51 ( S2 ): 496 - 504 .

Zhang D W , Xiao X , Zheng Z L , et al . Probabilistic assignment with decoupled IoU prediction for visual tracking [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 7 ): 5776 - 5789 .

Huang Q Q , Yao R L , Lu X Q , et al . Oriented object detector with Gaussian distribution cost label assignment and task-decoupled head [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 5621916 .

Ma Q H , Jin S H , Bian G , et al . S3DR-det: a rotating target detection model for high aspect ratio shipwreck targets in side-scan sonar images [J ] . Remote Sensing , 2025 , 17 ( 2 ): 312 .

Ge Z , Liu S T , Wang F , et al . YOLOX: exceeding YOLO series in 2021 [PP ] . V2 arXiv ( 2021-07-18 )[ 2021-08-06 ] . arXiv: arXiv. 2107.08430.

党思航 , 李晓哲 , 夏召强 , 等 . 采用自适应预筛选的遥感图像目标开集检测研究 [J ] . 电子与信息学报 , 2024 , 46 ( 10 ): 3908 - 3917 .

Dang S H , Li X Z , Xia Z Q , et al . Research on open-set object detection in remote sensing images based on adaptive pre-screening [J ] . Journal of Electronics & Information Technology , 2024 , 46 ( 10 ): 3908 - 3917 .

喻九阳 , 胡天豪 , 戴耀南 , 等 . 面向遥感目标检测的无锚框Transformer算法 [J ] . 电子学报 , 2023 , 51 ( 11 ): 3238 - 3247 .

Yu J Y , Hu T H , Dai Y N , et al . Anchor-free Transformer algorithm for aerial remote sensing target detection [J ] . Acta Electronica Sinica , 2023 , 51 ( 11 ): 3238 - 3247 .

Xia G S , Bai X , Ding J , et al . DOTA: a large-scale dataset for object detection in aerial images [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE Press , 2018 : 3974 - 3983 .

Liu Z K , Yuan L , Weng L B , et al . A high resolution optical satellite image dataset for ship recognition and some new baselines [C ] // Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods . Portugal : SCITEPRESS-Science and Technology Publications , 2017 : 324 - 331 .

浏览量

186

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据