昆明理工大学 民航与航空学院,云南 昆明 650500
[ "陈思睿(1999-),男,黑龙江大庆人,硕士研究生,2022年于昆明理工大学获得学士学位,主要从事遥感影像及机器视觉方面的研究。E-mail: 1113251813@qq.com" ]
[ "谢 涛(1974-),男,云南昭通人,副教授,硕士生导师,2000年于云南大学获得硕士学位,主要研究方向包括图像处理,人工智能技术和新型传感器研制。E-mail: 77183118@qq.com" ]
收稿:2025-07-01,
修回:2025-07-28,
纸质出版:2025-10-10
移动端阅览
陈思睿,胡方敏,王洪亮等.全向矩形校准的高分辨遥感影像细节分割[J].光学精密工程,2025,33(19):3121-3134.
CHEN Sirui,HU Fangmin,WANG Hongliang,et al.Detailed segmentation of high-resolution remote sensing images calibrated with omnidirectional rectangle[J].Optics and Precision Engineering,2025,33(19):3121-3134.
陈思睿,胡方敏,王洪亮等.全向矩形校准的高分辨遥感影像细节分割[J].光学精密工程,2025,33(19):3121-3134. DOI: 10.37188/OPE.20253319.3121. CSTR: 32169.14.OPE.20253319.3121.
CHEN Sirui,HU Fangmin,WANG Hongliang,et al.Detailed segmentation of high-resolution remote sensing images calibrated with omnidirectional rectangle[J].Optics and Precision Engineering,2025,33(19):3121-3134. DOI: 10.37188/OPE.20253319.3121. CSTR: 32169.14.OPE.20253319.3121.
针对高分辨率遥感影像分割中特征提取不全、边缘模糊及小目标漏检等难题,提出一种基于全向矩形校准的高分辨遥感影像细节分割方法,构建全向矩形校准网络(Omnidirectional Rectangular Calibration Network, ORCNet)。首先,设计全向矩形校准状态空间模块(Omnidirectional Rectangular Calibration State Space Module, ORSM),通过八向扫描与几何敏感权重校准,提升特征几何适应性与目标保留能力。随后,构建互补滤波混合特征融合模块(Complementary Filtering Hybrid Attention Fusion Module, CFHAF)融合通道、空间与像素级注意力机制,实现多尺度特征的自适应融合,增强语义感知。最后,融合动态点上采样技术(Dynamic Point Upsampling, DySample)优化边界细节恢复能力,结合Focal-Dice混合损失函数进行训练优化。实验结果表明,ORCNet在Massachusetts buildings数据集上F1score达到84.64%,mIoU达到77.07%,在deepglobe-road-dataset上,F1score达到85.32%,较RSMamba提升3.51%。该方法有效克服了遥感分割中存在的问题,具备显著的高精度、强稳定性和优秀的实际应用潜力。
To address incomplete feature extraction, blurred boundaries, and omission of small targets in high-resolution remote sensing image segmentation, a detail-preserving segmentation method based on omnidirectional rectangular calibration, termed the Omnidirectional Rectangular Calibration Network (ORCNet), is proposed. First, an Omnidirectional Rectangular Calibration State Space Module (ORSM) is introduced to enhance geometric adaptability and target retention via octagonal scanning and geometry-sensitive weight calibration. Next, a Complementary Filtering Hybrid Attention Fusion Module (CFHAF) is developed, integrating channel-, spatial-, and pixel-level attention mechanisms to enable adaptive multi-scale feature fusion and improved semantic discrimination. Finally, Dynamic Point Upsampling (DySample) is incorporated to refine boundary detail recovery. The model is trained with a Focal-Dice hybrid loss. On the Massachusetts Buildings dataset, the method achieves an F1 score of 84.64% and an mIoU of 77.07%. On the DeepGlobe Road dataset, an F1 score of 85.32% is obtained, representing a 3.51% improvement over RSMamba. Experimental results indicate that the proposed approach effectively addresses the three primary challenges in remote sensing segmentation, delivering high precision, robust performance, and strong potential for practical application.
ZHANG G Z , JIANG W Y . Remote sensing image semantic segmentation method based on a deep convolutional neural network and multiscale feature fusion [J]. International Journal on Semantic Web and Information Systems , 2023 , 19 ( 1 ): 1 - 16 . doi: 10.4018/ijswis.333712 http://dx.doi.org/10.4018/ijswis.333712
CHENG J , DENG C J , SU Y Z , et al . Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: a review [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2024 , 211 : 1 - 34 . doi: 10.1016/j.isprsjprs.2024.03.012 http://dx.doi.org/10.1016/j.isprsjprs.2024.03.012
ZHU Q W , LI K , ZHANG G J , et al . GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution [J/OL]. Arxiv , preprint Arxiv: 2501 . 01460 , 2024 . https://arxiv.org/html/ 2501. 01460 https://arxiv.org/html/2501.01460 .
朱长青 , 王耀革 , 马秋禾 , 等 . 基于形态分割的高分辨率遥感影像道路提取 [J]. 测绘学报 , 2004 , 33 ( 4 ): 347 - 351 .
ZHU CH Q , WANG Y G , MA Q H , et al . Road extraction from high-resolution remotely sensed image based on morphological segmentation [J]. Acta Geodaetica et Cartographic Sinica , 2004 , 33 ( 4 ): 347 - 351 . (in Chinese)
汪闽 , 骆剑承 , 周成虎 , 等 . 结合高斯马尔可夫随机场纹理模型与支撑向量机在高分辨率遥感图像上提取道路网 [J]. 遥感学报 , 2005 , 9 ( 3 ): 271 - 276 . doi: 10.11834/jrs.20050340 http://dx.doi.org/10.11834/jrs.20050340
WANG M , LUO J CH , ZHOU CH H , et al . Extraction of road network from high resolution remote sensed imagery with the combination of Gaussian Markov random field texture model and support vector machine [J]. Journal of Remote Sensing , 2005 , 9 ( 3 ): 271 - 276 . (in Chinese) . doi: 10.11834/jrs.20050340 http://dx.doi.org/10.11834/jrs.20050340
SHI J B , MALIK J . Normalized cuts and image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2000 , 22 ( 8 ): 888 - 905 . doi: 10.1109/34.868688 http://dx.doi.org/10.1109/34.868688
KASS M , WITKIN A , TERZOPOULOS D . Snakes: active contour models [J]. International Journal of Computer Vision , 1988 , 1 ( 4 ): 321 - 331 . doi: 10.1007/bf00133570 http://dx.doi.org/10.1007/bf00133570
CHEN L C , ZHU Y K , PAPANDREOU G , et al . Encoder-decoder with atrous separable convolution for semantic image segmentation [C]. Computer Vision-ECCV 2018. Cham : Springer , 2018 : 833 - 851 . doi: 10.1007/978-3-030-01234-2_49 http://dx.doi.org/10.1007/978-3-030-01234-2_49
RONNEBERGER O , FISCHER P , BROX T . U - Net : Convolutional Networks for Biomedical Image Segmentation [M]. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham : Springer International Publishing , 2015 : 234 - 241 . doi: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28
CAO H , WANG Y Y , CHEN J , et al . Swin - unet : Unet - like Pure Transformer for Medical Image Segmentation [M]. Computer Vision-ECCV 2022 Workshops. Cham : Springer Nature Switzerland , 2023 : 205 - 218 . doi: 10.1007/978-3-031-25066-8_9 http://dx.doi.org/10.1007/978-3-031-25066-8_9
LIU Y , TIAN Y , ZHAO Y , et al . Vmamba: Visual state space model [J/OL]. Arxiv , preprint Arxiv: 2401 . 10166 , 2024 . https://arxiv.org/abs/2401.10166 https://arxiv.org/abs/2401.10166 .
李智杰 , 惠爱婷 , 李昌华 , 等 . 面向遥感图像道路提取的多尺度上下文感知网络 [J]. 光学 精密工程 , 2025 , 33 ( 4 ): 610 - 623 . doi: 10.37188/ope.20253304.0610 http://dx.doi.org/10.37188/ope.20253304.0610
LI ZH J , HUI A T , LI CH H , et al . Multi-scale context-aware network for road extraction in remote sensing images [J]. Opt. Precision Eng. , 2025 , 33 ( 4 ): 610 - 623 . (in Chinese) . doi: 10.37188/ope.20253304.0610 http://dx.doi.org/10.37188/ope.20253304.0610
刘帅 , 李笑迎 , 于梦 , 等 . 高分辨率遥感图像双解耦语义分割网络模型 [J]. 测绘学报 , 2023 , 52 ( 4 ): 638 - 647 .
LIU SH , LI X Y , YU M , et al . Dual decoupling semantic segmentation model for high-resolution remote sensing images [J]. Acta Geodaetica et Cartographica Sinica , 2023 , 52 ( 4 ): 638 - 647 . (in Chinese)
ZHANG W H , JIAO L C , LIU X , et al . Multi-scale feature fusion network for object detection in VHR optical remote sensing images [C]. IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium . 28-2,2019 , Yokohama , Japan . IEEE , 2019 : 330 - 333 . doi: 10.1109/igarss.2019.8897842 http://dx.doi.org/10.1109/igarss.2019.8897842
CHEN Z X , HE Z W , LU Z M . DEA-net: single image dehazing based on detail-enhanced convolution and content-guided attention [J]. IEEE Transactions on Image Processing , 2024 , 33 : 1002 - 1015 . doi: 10.1109/tip.2024.3354108 http://dx.doi.org/10.1109/tip.2024.3354108
江宝得 , 黄威 , 许少芬 , 等 . 融合分散自适应注意力机制的多尺度遥感影像建筑物实例细化提取 [J]. 测绘学报 , 2023 , 52 ( 9 ): 1504 - 1514 .
JIANG B D , HUANG W , XU SH F , et al . Multi-scale building instance refinement extraction from remote sensing images by fusing with decentralized adaptive attention mechanism [J]. Acta Geodaetica et Cartographica Sinica , 2023 , 52 ( 9 ): 1504 - 1514 . (in Chinese)
ZHU H , ZHU Y , XIAO J Y , et al . Exact: exploring space-time perceptive clues for weakly supervised satellite image time series semantic segmentation [C]. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 10-17,2025 , Nashville, TN, USA. IEEE , 2025 : 14036 - 14045 . doi: 10.1109/cvpr52734.2025.01310 http://dx.doi.org/10.1109/cvpr52734.2025.01310
LI K Y , LIU R X , CAO X Y , et al . SegEarth-OV: towards training-free open-vocabulary segmentation for remote sensing images [C]. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 10-17,2025 , Nashville, TN, USA. IEEE , 2025 : 10545 - 10556 . doi: 10.1109/cvpr52734.2025.00986 http://dx.doi.org/10.1109/cvpr52734.2025.00986
ZHAO S , CHEN H , ZHANG X , et al . Rs-mamba for large remote sensing image dense prediction [J/OL]. Arxiv , preprint Arxiv: 2404 . 02668 , 2024 . https://arxiv.org/abs/2404.02668 https://arxiv.org/abs/2404.02668 .
NI Z , CHEN X , ZHAI Y , et al . Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation [J/OL]. Arxiv , preprint Arxiv: 2405 . 06228 , 2024 . https://arxiv.org/abs/2405.06228 https://arxiv.org/abs/2405.06228 .
CHEN K Y , CHEN B W , LIU C Y , et al . RSMamba: remote sensing image classification with state space model [J]. IEEE Geoscience and Remote Sensing Letters , 2024 , 21 : 8002605 . doi: 10.1109/lgrs.2024.3407111 http://dx.doi.org/10.1109/lgrs.2024.3407111
DING Z , LI Y , HE Y , et al . Dygmamba: Efficiently modeling long-term temporal dependency on continuous-time dynamic graphs with state space models [J/OL]. Arxiv , preprint Arxiv: 2408 . 04713 , 2024 . https://arxiv.org/abs/2408.04713 https://arxiv.org/abs/2408.04713 .
LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 21-26,2017 , Honolulu, HI, USA. IEEE , 2017 : 936 - 944 . doi: 10.1109/cvpr.2017.106 http://dx.doi.org/10.1109/cvpr.2017.106
TARG S , ALMEIDA D , LYMAN K . Resnet in resnet: Generalizing residual architectures [J/OL]. Arxiv , preprint Arxiv: 1603 . 08029 , 2016 . https://arxiv.org /abs /1603.08029 https://arxiv.org/abs/1603.08029 .
NHI N T U , LE T M , VAN T T . A model of semantic-based image retrieval using C-tree and neighbor graph [J]. International Journal on Semantic Web and Information Systems , 2022 , 18 ( 1 ): 1 - 23 . doi: 10.4018/ijswis.295551 http://dx.doi.org/10.4018/ijswis.295551
LIU W Z , LU H , FU H T , et al . Learning to upsample by learning to sample [C]. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). 1-6,2023 , Paris, France. IEEE , 2023 : 6004 - 6014 . doi: 10.1109/iccv51070.2023.00554 http://dx.doi.org/10.1109/iccv51070.2023.00554
胡功明 , 杨春成 , 徐立 , 等 . 改进U-Net的遥感图像语义分割方法 [J]. 测绘学报 , 2023 , 52 ( 6 ): 980 - 989 .
HU G M , YANG CH CH , XU L , et al . Improved U-Net remote sensing image semantic segmentation method [J]. Acta Geodaetica et Cartographica Sinica , 2023 , 52 ( 6 ): 980 - 989 . (in Chinese)
LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [C]. 2017 IEEE International Conference on Computer Vision (ICCV). 22-29,2017 , Venice, Italy. IEEE , 2017 : 2999 - 3007 . doi: 10.1109/iccv.2017.324 http://dx.doi.org/10.1109/iccv.2017.324
LI X , SUN X , MENG Y , et al . Dice loss for data-imbalanced NLP tasks [J/OL]. Arxiv , preprint Arxiv: 1911 . 02855 , 2019 . https://arxiv.org/abs/1911. 02855 https://arxiv.org/abs/1911.02855 .
MNIH V . Machine Learning for Aerial image Labeling [M]. University of Toronto , Canada , 2013 .
DEMIR I , KOPERSKI K , LINDENBAUM D , et al . DeepGlobe 2018: a challenge to parse the Earth through satellite images [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 18-22,2018 , Salt Lake City, UT, USA. IEEE , 2018 : 172 - 17209 . doi: 10.1109/cvprw.2018.00031 http://dx.doi.org/10.1109/cvprw.2018.00031
LU Y , CHEN Y R , ZHAO D B , et al . Graph - FCN for Image Semantic Segmentation [M]. Advances in Neural Networks-ISNN 2019. Cham : Springer International Publishing , 2019 : 97 - 105 . doi: 10.1007/978-3-030-22796-8_11 http://dx.doi.org/10.1007/978-3-030-22796-8_11
FU J , LIU J , TIAN H J , et al . Dual attention network for scene segmentation [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 15-20,2019 , Long Beach, CA, USA. IEEE , 2019 : 3141 - 3149 . doi: 10.1109/cvpr.2019.00326 http://dx.doi.org/10.1109/cvpr.2019.00326
POUDEL R P K , LIWICKI S , CIPOLLA R . Fast-scnn: Fast semantic segmentation network [J/OL]. Arxiv , preprint Arxiv: 1902 . 04502 , 2019 . https://arxiv.org/abs /1902.04502 https://arxiv.org/abs/1902.04502 .
WANG P , HU Y S , PENG S Y , et al . EMANet: an ancient text detection method based on enhanced-EfficientNet and multidimensional scale fusion [J]. IEEE Internet of Things Journal , 2024 , 11 ( 19 ): 32105 - 32116 . doi: 10.1109/jiot.2024.3423667 http://dx.doi.org/10.1109/jiot.2024.3423667
BENAYAS A , HASHEMPOUR R , RUMBLE D , et al . Unified transformer multi-task learning for intent classification with entity recognition [J]. IEEE Access , 2021 , 9 : 147306 - 147314 . doi: 10.1109/access.2021.3124268 http://dx.doi.org/10.1109/access.2021.3124268
CHEN J , LU Y , YU Q , et al . Transunet: Transformers make strong encoders for medical image segmentation [J/OL]. Arxiv , preprint Arxiv: 2102 . 04306 , 2021 . https://arxiv.org/abs /2102.04306 https://arxiv.org/abs/2102.04306 .
XIE E Z , WANG W H , YU Z D , et al . SegFormer: Simple and efficient design for semantic segmentation with transformers [J/OL]. Arxiv , preprint Arxiv: 2105 . 15203 , 2021 . https://arxiv.org /abs/2105.15203 https://arxiv.org/abs/2105.15203 .
WANG D P , DONG X H , HUANG L Y , et al . Information entropy uncertainty estimation based domain adaptation for land cover classification from multi-source remote sensing images [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 10 ): 1940 - 1952 .
0
浏览量
2
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
