基于多尺度感知增强的旋转目标检测

doi:10.11896/jsjkx.240300076

摘要/Abstract

摘要： 遥感图像中的旋转目标检测由于存在背景复杂、目标在任意方向分布且密集排列、尺度变化剧烈、高长宽比等问题而具有挑战性。针对这些问题,提出基于多尺度感知增强的旋转目标检测框架。首先,在特征提取阶段,提出多尺度感知增强模块,针对不同层级的特征图采用不同的卷积块来提取特征,确保低层特征图能保留足够的细节信息,高层特征图能提取足够的语义信息,使得提取的多级特征图对不同尺度具有自适应的特征学习能力。同时,利用自适应通道注意力模块来学习通道权重,缓解复杂背景带来的影响。其次,提出尺寸敏感的旋转交并比损失,通过在旋转交并比损失中增加目标长宽比和面积的损失项,来监督网络学习目标的尺寸信息,增加对高长宽比目标的敏感性。在公开的遥感图像数据集DOTA,HRSC2016和DIOR-R上,所提方法分别取得77.64%,98.32%和66.14%的mAP,检测精度优于现有的先进遥感图像检测网络。

关键词: 遥感图像, 旋转目标检测, 多尺度感知增强, 自适应特征学习, 旋转交并比损失

Abstract: Oriented object detection in remote sensing images is more challenging due to the issues of complex background,dense distribution and with arbitrary direction,large-scale variation,high aspect-ratio of objects.To address these issues,this paper proposes a framework for oriented object detection in remote sensing images based on multi-scale perception enhancemen.Firstly,a multi-scale perceptual enhancement module is proposed in the feature extraction stage,which employs different convolutional blocks for extracting features for different levels of feature maps to ensure that the low-level feature maps retain enough detail information and the high-level feature maps extract enough semantic information.So that the extracted multilevel feature maps have the ability of adaptive feature learning for different scales.Meanwhile,an adaptive channel attention module is used to adaptively learn the channel weights to mitigate the effects of the complex background.Secondly,a size-sensitive rotated Itersection over Union(IoU) loss is proposed to supervise the network to learn the size information of the target and increase the sensitivity to high aspect ratio targets by adding the loss terms of objects' aspect ratio and area in the loss.The proposed method achieves 77.64%,98.32%,and 66.14% mAP on the publicly available remote sensing image datasets DOTA,HRSC2016,and DIOR-R,respectively.The detection accuracies of the proposed framework outperform existing state-of-the-art remote sensing image detection networks.

Key words: Remote sensing image, Oriented object detection, Multi-scale perceptual enhancement, Adaptive feature learning, Rotated IoU loss

中图分类号:

TP751

张达斌, 吴秦, 周浩杰. 基于多尺度感知增强的旋转目标检测[J]. 计算机科学, 2025, 52(6): 247-255. https://doi.org/10.11896/jsjkx.240300076

ZHANG Dabin, WU Qin, ZHOU Haojie. Oriented Object Detection Based on Multi-scale Perceptual Enhancement[J]. Computer Science, 2025, 52(6): 247-255. https://doi.org/10.11896/jsjkx.240300076

参考文献

[1]YU Z,CHU H,BO S,et al.Multrlayer Feature Selection Based Hierarchal Component Model for Aero-planeDetection on Remote Sensing Image [J].Geomatics and Information Science of Wuhan University,2014,39(12):1406-1411.
[2]TANG F,WANG W,LI J,et al.Aircraft rotation detection inremote sensing image based on multi-feature fusion and rotation-aware anchor [J].Applied Sciences,2022,12(3):1291.
[3]JI H,GAO Z,MEI T,et al.Improved faster R-CNN with multiscale feature fusion and homography augmentation for vehicle detection in remote sensing images [J].IEEE Geoscience and Remote Sensing Letters,2019,16(11):1761-1765.
[4]ZHANG Y_Z,GUO W,LI W_B.Omnidirectional accurate detection algorithm for dense small objects in remote sensing images[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(4):1105-1113.
[5]WANG F_S,BAO P.Intelligent Recognition of sensitive small targets with fine grains in complex background remote sensing images[J].Journal of Jilin University(Engineering and Techno-logy Edition),2024,54(11):3289-3295.
[6]LIU Z,WANG H,WENG L,et al.Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds [J].IEEE Geoscience and Remote Sensing Letters,2016,13(8):1074-1078.
[7]RAN B,YOU Y,LI Z,et al.Arbitrary-Oriented Ship Detection Method Based on Improved Regression Model for Target Direction Detection Network[C]//IGARSS 2020－2020 IEEE International Geoscience and Remote Sensing Symposium.IEEE,2020:964-967.
[8]CHEN L,WENG T,XING J,et al.A new deep learning net-work for automatic bridge detection from SAR images based on balanced and attention mechanism [J].Remote Sensing,2020,12(3):441.
[9]LIN T Y,DOLLáR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125.
[10]WANG J,WANG Y,WU Y,et al.FRPNet:A feature-reflowing pyramid network for object detection of remote sensing images [J].IEEE Geoscience and Remote Sensing Letters,2020,19:1-5.
[11]ZHANG W,JIAO L,LI Y,et al.Laplacian feature pyramid network for object detection in VHR optical remote sensing images [J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-14.
[12]GU L,EUGENE P,DONG G.Fast Fourier Convolution Based Remote Sensor Image Object Detection for Earth Observation [J].arXiv:2209.00551,2022.
[13]HUANG Z,LI W,XIA X G,et al.A novel nonlocal-aware pyramid and multiscale multitask refinement detector for object detection in remote sensing images [J].IEEE Transactions on Geo-science and Remote Sensing,2021,60:1-20.
[14]LIU Y,LI Q,YUAN Y,et al.ABNet:Adaptive balanced network for multiscale object detection in remote sensing imagery [J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-14.
[15]ZHOU Y,CHEN S,ZHAO J,et al.CLT-Det:Correlation lear-ning based on transformer for detecting dense objects in remote sensing images [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-15.
[16]YU J,JIANG Y,WANG Z,et al.Unitbox:An advanced object detection network [C]//Proceedings of the 24th ACM International Conference on Multimedia.2016:516-520.
[17]REZATOFIGHI H,TSOI N,GWAK J,et al.Generalized intersection over union:A metric and a loss for bounding box regression [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:658-666.
[18]ZHENG Z,WANG P,LIU W,et al.Distance-IoU loss:Fasterand better learning for bounding box regression[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2020:12993-13000.
[19]ZHANG Y F,REN W,ZHANG Z,et al.Focal and efficient IOU loss for accurate bounding box regression [J].Neurocomputing,2022,506:146-157.
[20]GUO Z,LIU C,ZHANG X,et al.Beyond bounding-box:Con-vex-hull feature adaptation for oriented and densely packed object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:8792-8801.
[21]XIE E,SUN P,SONG X,et al.Polarmask:Single shot instance segmentation with polar representation [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:12193-12202.
[22]YANG X,YANG J,YAN J,et al.Scrdet:Towards more robust detection for small,cluttered and rotated objects[C]//Procee-dings of the IEEE/CVF International Conference on Computer Vision.2019:8232-8241.
[23]CHEN Z,CHEN K,LIN W,et al.Piou loss:Towards accurate oriented object detection in complex environments [C]//European Conference on Computer Vision.Springer,2020:195-211.
[24]YANG X,YAN J,MING Q,et al.Rethinking rotated object detection with gaussian wasserstein distance loss [C]//International Conference on Machine Learning.PMLR,2021:11830-11841.
[25]YANG X,YANG X,YANG J,et al.Learning high-precisionbounding box for rotated object detection via kullback-leibler divergence [J].Advances in Neural Information Processing Systems,2021,34:18381-18394.
[26]YANG X,ZHOU Y,ZHANG G,et al.The KFIoU loss for rotated object detection [J].arXiv:2201.12558,2022.
[27]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[28]YU F,KOLTUN V,FUNKHOUSER T.Dilated residual net-works [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:472-480.
[29]LI H,LI J,WEI H,et al.Slim-neck by GSConv:A better design paradigm of detector architectures for autonomous vehicles [J].arXiv:2206.02424,2022.
[30]XIE X,CHENG G,WANG J,et al.Oriented R-CNN for object detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:3520-3529.
[31]XIA G S,BAI X,DING J,et al.DOTA:A large-scale dataset for object detection in aerial images [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3974-3983.
[32]CHENG G,WANG J,LI K,et al.Anchor-free oriented proposal generator for object detection [J].arXiv:2110.01931,2022.
[33]DENG J,DONG W,SOCHER R,et al.Imagenet:A large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:248-255.
[34]CHEN K,WANG J,PANG J,et al.MMDetection:Open mmlab detection toolbox and benchmark [J].arXiv:1906.07155,2019.
[35]LIN TY,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection [C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988.
[36]TIAN Z,SHEN C,CHEN H,et al.Fcos:Fully convolutional one-stage object detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:9627-9636.
[37]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.2019:2849-2858.
[38]LI C,XU C,CUI Z,et al.Feature-attentioned object detection in remote sensing imagery[C]//IEEE International Conference on Image Processing.IEEE,2019:3886-3890.
[39]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):5831-5861.
[40]FU K,CHANG Z,ZHANG Y,et al.Rotation-aware and multi-scale convolutional neural network for object detection in remote sensing images [J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,161:294-308.
[41]CHENG G,YAO Y,LI S,et al.Dual-aligned oriented detector [J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-11.
[42]LU D,LI D,LI Y,et al.OSKDet:Orientation-sensitive keypoint localization for rotated object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:1182-1192.
[43]MING Q,ZHOU Z,MIAO L,et al.Dynamic anchor learning for arbitrary-oriented object detection [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:2355-2363.
[44]MA J,SHAO W,YE H,et al.Arbitrary-oriented scene text detection via rotation proposals [J].IEEE Transactions on Multimedia,2018,20(11):3111-3122.
[45]XU Y,FU M,WANG Q,et al.Gliding vertex on the horizontal bounding box for multi-oriented object detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(4):1452-1459.
[46]WANG J,YANG W,LI H C,et al.Learning center probability map for detecting objects in aerial images [J].IEEE Transactions on Geoscience and Remote Sensing,2020,59(5):4307-4323.
[47]HOU L,LU K,XUE J,et al.Shape-adaptive selection and mea-surement for oriented object detection [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:923-932.
[48]YANG X,YAN J,FENG Z,et al.R3det:Refined single-stagedetector with feature refinement for rotating object[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:3163-3171.
[49]HAN J,DING J,XUE N,et al.Redet:A rotation-equivariant detector for aerial object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:2786-2795.
[50]HAN J,DING J,LI J,et al.Align deep features for oriented object detection [J].IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-11.
[51]ZENG Y,YANG X,LI Q,et al.Ars-detr:Aspect ratio sensitive oriented object detection with transformer [J].arXiv:2303.04989,2023.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed