Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection

YU Jiu-yang; HU Tian-hao; DAI Yao-nan; ZHANG De-an; XIA Wen-feng

doi:10.12263/DZXB.20220612

您当前的位置：

首页 >

文章列表页 >

Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection

PAPERS | 更新时间：2025-12-08

- Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection
- ACTA ELECTRONICA SINICA Vol. 51, Issue 11, Pages: 3238-3247(2023)
- 作者机构：
  
  武汉工程大学机电工程学院湖北省绿色化工装备工程技术研究中心，湖北武汉 430205
- 作者简介：
- 基金信息：
  
  Hubei Provincial Key R&D Project(2020BAB030);Natural Science Foundation of Hubei Province(2023AFC010)
- DOI：10.12263/DZXB.20220612
  CLC： TP391;TP183
- Received：27 May 2022，
  
  Revised：2022-09-02，
  
  Published：25 November 2023
- 稿件说明：
移动端阅览
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 Jiu-yang,HU Tian-hao,DAI Yao-nan,et al.Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection[J].ACTA ELECTRONICA SINICA,2023,51(11):3238-3247.
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. DOI： 10.12263/DZXB.20220612.

YU Jiu-yang,HU Tian-hao,DAI Yao-nan,et al.Anchor-Free Transformer Algorithm for Aerial Remote Sensing Target Detection[J].ACTA ELECTRONICA SINICA,2023,51(11):3238-3247. DOI： 10.12263/DZXB.20220612.

摘要

遥感图像目标具有多方向排布、小且密集等特性，使基于深度学习的旋转目标检测算法存在检测精度不佳的问题.针对这一问题，本文提出了一种面向遥感目标检测的无锚框Transformer算法.首先，采用层次化Transformer采集不同分辨率的特征信息以扩大特征信息的采集范围.其次，构建一种新的前馈网络（Spacial-FeedForward Neural network，SFFN）.SFFN将

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=62797459&type=

2.28600001

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=62797471&type=

6.01133299

深度可分离卷积的局部空间特性和多层感知机（MultiLayer Perce

ptron，MLP）的全局通道特性融合在一起，以解决前馈网络（Feed Forward Neural network，FFN）在局部空间建模上的不足.最后，基于SFFN架构搭建了无锚框检测器，将预测框回归问题分为水平框与旋转框，缓解了旋转框的损失不连续性问题.在DOTA数据集上的测试结果表明，此方法的平均精度达到了75.83%，同时在NWPU VHR-10数据集上5类小目标检测结果达到了92.47%，在遥感目标检测精度上更具竞争力.

Abstract

Aerial remote sensing image targets have the characteristics of multi-directional arrangement

small

and dense. The rotating target detection algorithm based on deep learning has the problem of poor detection accuracy. To solve this problem

the article proposes a novel anchor-free Transformer algorithm for aerial remote sensing target detection. Firstly

hierarchical Transformer is used to collect feature information of different resolutions to improve the range of feature information collection. Secondly

a new feedforward network (Spacial-FeedForward Neural network

SFFN) is constructed. SFFN combines the local space characteristics of 3×3 depth separable convolution with the global channel characteristics of multi-layer perceptron (MLP) to solve the shortcomings of feed forward neural network (FFN) in local space modeling. Finally

an anchor-free detector is built based on SFFN architecture

and the regression problem of prediction frame is divided into horizontal frame and rotating frame

which alleviates the loss discontinuity problem of rotating frame. The test results on DOTA dataset show that the average accuracy of this method has reached 75.83%

respectively

while achieving 92.47% of 5 small targets on NWPU VHR-10 dataset

which is more competitive in remote sensing target detection accuracy.

关键词

Keywords

references

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 . Piscataway : IEEE , 2020 : 6568 - 6577 .

刘颖 , 刘红燕 , 范九伦 , 等 . 基于深度学习的小目标检测研究与应用综述 [J ] . 电子学报 , 2020 , 48 ( 3 ): 590 - 601 .

LIU Y , LIU H Y , FAN J L , et al . A survey of research and application of small object detection based on deep learning [J ] . Acta Electronica Sinica , 2020 , 48 ( 3 ): 590 - 601 . (in Chinese)

方青云 , 王兆魁 . 基于改进YOLOv3网络的遥感目标快速检测方法 [J ] . 上海航天 , 2019 , 36 ( 5 ): 21 - 27, 34 .

FANG Q Y , WANG Z K . Remote sensing target rapid detection method based on improved YOLOv3 network [J ] . Aerospace Shanghai , 2019 , 36 ( 5 ): 21 - 27, 34 . (in Chinese)

DAI J F , QI H Z , XIONG Y W , et al . Deformable convolutional networks [C ] // Proceedings of the IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 764 - 773 .

CARION N , MASSA F , SYNNAEVE G , et al . End-to-end object detection with transformers [C ] // European Conference on Computer Vision . Cham : Springer , 2020 : 213 - 229 .

CAO J , CHEN Q , GUO J , et al . Attention-guided context feature pyramid network for object detection [EB/OL ] . ( 2020-05-23 )[ 2022-05-27 ] . https://arxiv.org/abs/2005.11475v1 https://arxiv.org/abs/2005.11475v1 .

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 .

JIANG Y , ZHU X , WANG X , et al . R 2 CNN: Rotational region CNN for orientation robust scene text detection [EB/OL ] . ( 2017-06-29 )[ 2022-05-27 ] . https://arxiv.org/abs/1706.09579 https://arxiv.org/abs/1706.09579 .

DING J , XUE N , LONG Y , et al . Learning RoI Transformer for oriented object detection in aerial images [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 2849 - 2858 .

YANG X , YANG J , YAN J , et al . Scrdet: Towards more robust detection for small, cluttered and rotated objects [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 8232 - 8241 .

YANG X , YAN J C , FENG Z M , et al . R3Det: Refined single-stage detector with feature refinement for rotating object [EB/OL ] . ( 2019-08-15 )[ 2022-05-27 ] . https://arxiv.org/abs/1908.05612 https://arxiv.org/abs/1908.05612 .

肖进胜 , 张舒豪 , 陈云华 , 等 . 双向特征融合与特征选择的遥感影像目标检测 [J ] . 电子学报 , 2022 , 50 ( 2 ): 267 - 272 .

XIAO J S , ZHANG S H , CHEN Y H , et al . Remote sensing image object detection based on bidirectional feature fusion and feature selection [J ] . Acta Electronica Sinica , 2022 , 50 ( 2 ): 267 - 272 . (in Chinese)

LI W T , CHEN Y J , HU K X , et al . Oriented reppoints for aerial object detection [EB/OL ] . ( 2021-05-24 )[ 2022-05-27 ] . https://arxiv.org/abs/2105.11111 https://arxiv.org/abs/2105.11111 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 6000 - 6010 .

何林远 , 白俊强 , 贺旭 , 等 . 基于稀疏Transformer的遥感旋转目标检测 [J ] . 激光与光电子学进展 , 2022 , 59 ( 18 ): 1810003 .

HE L , BAI J Q , HE X , et al . Remote sensing rotation object detection based on sparse Transformer [J ] . Laser & Optoelectronics Progress , 2022 , 59 ( 18 ): 1810003 . (in Chinese)

祝星馗 , 蒋球伟 . 基于CNN与Transformer的无人机图像目标检测研究 [J ] . 武汉理工大学学报(信息与管理工程版) , 2022 , 44 ( 2 ): 323 - 331 .

ZHU X K , JIANG Q W . Research on object detection for UAV images based on CNN and transformer [J ] . Journal of Wuhan University of Technology (Information & Management Engineering) , 2022 , 44 ( 2 ): 323 - 331 . (in Chinese)

LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [C ] // Proceedings of the IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2999 - 3007 .

CHEN Z Y , ZHU Y S , ZHAO C Y , et al . DPT: Deformable patch-based transformer for visual recognition [C ] // Proceedings of the 29th ACM International Conference on Multimedia . New York : ACM , 2021 : 2899 - 2907 .

WU P , GONG S Q , PAN K K , et al . Reduced order model using convolutional auto-encoder with self-attention [J ] . Physics of Fluids , 2021 , 33 ( 7 ): 077107 .

CHOLLET F . Xception: Deep learning with depthwise separable convolutions [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 1251 - 1258 .

CHU X X , TIAN Z , WANG Y Q , et al . Twins: Revisiting the design of spatial attention in vision transformers [C ] // 35th Conference on Neural Information Processing Systems . Virtual Event : NeurlPS , 2021 : 1 - 12 .

戴耀南 . 基于障碍物图像感知的油气管道机器人路径规划策略研究 [D ] . 武汉 : 武汉工程大学 , 2022 .

DAI Y N . A Dissertation Submitted in Partial Fulfillment of the Requirements forthe Degree of Doctor of Philosophy in Engineering [D ] . Wuhan : Wuhan Institute of Technology , 2022 . (in Chinese)

WANG W H , XIE E Z , LI X , et al . Pyramid vision transformer: A versatile backbone for dense prediction without convolutions [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 568 - 578 .

PAN X J , REN Y Q , SHENG K K , et al . Dynamic refinement network for oriented and densely packed object detection [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 11204 - 11213 .

AZIMI S M , VIG E , BAHMANYAR R , et al . Towards multi-class object detection in unconstrained remote sensing imagery [C ] // Asian Conference on Computer Vision . Cham : Springer , 2019 : 150 - 165 .

RAFFEL C , SHAZEER N , ROBERTS A , et al . Exploring the limits of transfer learning with a unified text-to-text transformer [EB/OL ] . ( 2019-10-23 )[ 2022-05-27 ] . https://arxiv.org/abs/1910.10683 https://arxiv.org/abs/1910.10683 .

SHANG R H , HE J H , WANG J M , et al . Dense connection and depthwise separable convolution based CNN for polarimetric SAR image classification [J ] . Knowledge-Based Systems , 2020 , 194 : 105542 .

SHI P F , ZHAO Z X , FAN X N , et al . Remote sensing image object detection based on angle classification [J ] . IEEE Access , 2021 , 9 : 118696 - 118707 .

SANDLER M , HOWARD A , ZHU M L , et al . Mobilenetv2: Inverted residuals and linear bottlenecks [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 4510 - 4520 .

GAO J F , CHEN Y , WEI Y M , et al . Detection of specific building in remote sensing images using a novel YOLO-S-CIOU model. Case: Gas station identification [J ] . Sensors , 2021 , 21 ( 4 ): 1375 .

BOCHKOVSKIY A , WANG C Y , LIAO H Y M . Yolov4: Optimal speed and accuracy of object detection [EB/OL ] . ( 2020-04-23 )[ 2022-05-27 ] . https://arxiv.org/abs/2004.10934 https://arxiv.org/abs/2004.10934 .

QIAN W , YANG X , PENG S L , et al . Learning modulated loss for rotated object detection [EB/OL ] . ( 2019-11-19 )[ 2022-05-27 ] . https://arxiv.org/abs/1911.08299 https://arxiv.org/abs/1911.08299 .

赵玉卿 , 贾金露 , 公维军 , 等 . 基于pro-YOLOv4的多尺度航拍图像目标检测算法 [J ] . 计算机应用研究 , 2021 , 38 ( 11 ): 3466 - 3471 .

ZHAO Y Q , JIA J L , GONG W J , et al . Multi-scale aerial image target detection algorithm based on pro-YOLOv4 [J ] . Application Research of Computers , 2021 , 38 ( 11 ): 3466 - 3471 . (in Chinese)

肖振久 , 杨玥莹 , 孔祥旭 . 基于改进YOLOv4的遥感图像目标检测方法 [J ] . 激光与光电子学进展 , 2023 , 60 ( 6 ): 0628009 .

XIAO Z J , YANG Y Y , KONG X X . Remote sensing image target detection based on improved YOLOv4 [J ] . Laser & Optoelectronics Progress , 2023 , 60 ( 6 ): 0628009 . (in Chinese)

ZHAO P , QU Z , BU Y , et al . PolarDet: A fast, more precise detector for rotated target in aerial images [J ] . International Journal of Remote Sensing , 2021 , 42 ( 15 ): 5831 - 5835 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cross-Modal SAR Target Detection via Progressive Knowledge Transfer

Shared Super-Resolution Dual-Branch Network for Spatiotemporal Fusion of Remote Sensing Images

Multi-Stage Feature Fusion Object Detection Method for Remote Sensing Image

Cascaded Inverse Residual Network for Lightweight Object Detection Model in Remote Sensing Image

Application of Improved Cascade R-CNN Algorithm in Target Detection

Related Author

ZHAO Guo-wei

JIANG Jia-qing

DONG Gang-gang

FANG Shuai

ZHANG Xiao-xi

ZHANG Jing

CHEN Li

ZHANG Fan

Related Institution

National Key Laboratory of Radar Signal Processing, Xidian University

School of Computer and Information, Hefei University of Technology

Anhui Province Key Laboratory of Industry Safety and Emergency Technology

Information Engineering University

National Digital Switching System Engineering Technology Research Center

⁰