测绘学报 ›› 2024, Vol. 53 ›› Issue (7): 1384-1400.doi: 10.11947/j.AGCS.2024.20230455
收稿日期:
2023-10-07
发布日期:
2024-08-12
作者简介:
杨军(1973—),男,博士,教授,博士生导师,主要研究方向为三维模型空间分析、遥感大数据智能解译、深度学习。E-mail:yangj@mail.lzjtu.cn
基金资助:
Jun YANG1,2(), Hengjing XIE1, Hongchao FAN3, Haowen YAN1
Received:
2023-10-07
Published:
2024-08-12
About author:
YANG Jun (1973—), male, PhD, professor, PhD supervisor, majors in 3D model spatial analysis, intelligent interpretation of remotely sensed big data, deep learning. E-mail: yangj@mail.lzjtu.cn
Supported by:
摘要:
针对传统神经网络架构搜索需要耗费大量时间用于超网训练,搜索效率较低,搜索得到的模型无法高效解决遥感影像中多尺度目标检测困难、背景复杂度高的问题,本文提出采用多尺度熵神经网络架构搜索的方法进行遥感影像目标检测。首先,在搜索空间的基础模块中加入特征分离卷积以代替残差模块中的常规卷积,减少遥感影像中由于背景复杂度高而造成的信息间干扰,提高网络模型在复杂背景下的检测性能;然后,引入最大熵原理,计算搜索空间中每个候选网络的多尺度熵,将多尺度熵与特征金字塔网络相结合,以兼顾遥感影像大、中、小目标的检测;最后,在不进行参数训练的情况下利用渐进式进化算法搜索得到多尺度熵最大的网络模型用于目标检测任务,在保证模型检测精度的同时,提升网络搜索效率。本文方法在RSOD、DIOR和DOTA数据集上的平均检测精度均值分别达到93.1%、75.5%和73.6%,网络搜索时间为8.1 h。试验结果表明,与当前基准方法相比,本文方法能够显著提升网络的搜索效率,在目标检测任务中更好地结合了不同尺度下的特征并解决了影像背景复杂度高的问题。
中图分类号:
杨军, 解恒静, 范红超, 闫浩文. 遥感影像目标检测多尺度熵神经网络架构搜索[J]. 测绘学报, 2024, 53(7): 1384-1400.
Jun YANG, Hengjing XIE, Hongchao FAN, Haowen YAN. Multi-scale entropy neural architecture search for object detection in remote sensing images[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(7): 1384-1400.
表1
数据预处理前后结果的对比"
不同数据集的预处理 | 浮点运算数 | 参数量 | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|
未经过数据预处理(RSOD) | 207.63×109 | 30.29×106 | 92.4 | 99.2 | 98.5 | 67.6 | 89.8 | 94.7 |
经过数据预处理(RSOD) | 207.63×109 | 30.29×106 | 93.1 | 99.2 | 98.7 | 68.6 | 89.9 | 95.4 |
未经过数据预处理(DIOR) | 144.41×109 | 30.04×106 | 72.1 | 90.8 | 80.7 | 38.5 | 68.0 | 84.8 |
经过数据预处理(DIOR) | 144.41×109 | 30.04×106 | 75.5 | 92.6 | 84.4 | 44.3 | 72.1 | 87.0 |
未经过数据预处理(DOTA) | 208.15×109 | 30.31×106 | 70.8 | 87.5 | 81.6 | 50.0 | 76.6 | 82.5 |
经过数据预处理(DOTA) | 208.15×109 | 30.31×106 | 73.6 | 89.2 | 83.9 | 53.4 | 80.5 | 85.0 |
表3
在RSOD数据集上不同网络模型的对比"
网络模型 | 浮点运算数 | 参数量 | 网络搜索时间/h | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|---|
Faster R-CNN | 841.40×109 | 41.14×106 | — | 84.9 | 99.5 | 96.4 | 61.0 | 83.0 | 88.0 |
ResNet-SB | 298.57×109 | 46.89×106 | — | 77.4 | 97.5 | 90.5 | 23.3 | 66.4 | 82.3 |
VarifocalNet | 218.57×109 | 32.49×106 | — | 87.8 | 99.1 | 96.9 | 56.0 | 82.9 | 91.3 |
NAS-FCOS | 216.31×109 | 38.67×106 | 11.4 | 77.3 | 98.0 | 89.2 | 26.9 | 75.0 | 83.1 |
DetNAS | 201.67×109 | 32.79×106 | 12.6 | 85.5 | 99.5 | 97.9 | 63.2 | 83.2 | 88.6 |
本文方法 | 207.63×109 | 30.29×106 | 8.1 | 93.1 | 99.2 | 98.7 | 68.6 | 89.9 | 95.4 |
表5
在DIOR数据集上不同网络模型的对比"
网络模型 | 浮点运算数 | 参数量 | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|
Faster R-CNN | 798.04×109 | 32.95×106 | 66.1 | 88.8 | 74.2 | 12.2 | 50.8 | 76.2 |
ResNet-SB | 216.40×109 | 41.22×106 | 52.0 | 76.4 | 57.5 | 9.7 | 31.2 | 62.1 |
VarifocalNet | 159.35×109 | 32.49×106 | 70.1 | 89.6 | 78.3 | 35.2 | 64.6 | 83.0 |
NAS-FCOS | 230.62×109 | 38.15×106 | 55.7 | 80.4 | 60.6 | 10.4 | 35.8 | 65.5 |
DetNAS | 208.47×109 | 25.38×106 | 67.8 | 91.3 | 78.3 | 36.1 | 60.6 | 74.4 |
本文方法 | 144.41×109 | 30.04×106 | 75.5 | 92.6 | 84.4 | 44.3 | 72.1 | 87.0 |
表6
在DIOR数据集上不同目标类别的检测精度对比"
类别 | Faster R-CNN | ResNet-SB | VarifocalNet | NAS-FCOS | DetNAS | 本文方法 |
---|---|---|---|---|---|---|
飞机 | 81.5 | 67.8 | 72.7 | 75.5 | 80.6 | 81.3 |
机场 | 66.0 | 42.2 | 79.9 | 52.2 | 58.2 | 81.6 |
棒球场 | 86.5 | 77.6 | 83.2 | 83.5 | 85.4 | 86.0 |
篮球场 | 81.0 | 63.9 | 85.5 | 68.7 | 81.9 | 90.4 |
桥梁 | 43.7 | 31.8 | 48.8 | 27.5 | 55.3 | 60.0 |
烟囱 | 81.7 | 74.7 | 84.0 | 80.0 | 82.0 | 83.6 |
水坝 | 55.0 | 36.5 | 73.3 | 35.4 | 58.5 | 77.1 |
高速公路服务区 | 70.1 | 44.0 | 80.4 | 53.1 | 68.7 | 85.6 |
高速公路收费站 | 74.3 | 63.3 | 76.0 | 57.4 | 76.4 | 81.0 |
高尔夫球场 | 61.8 | 43.9 | 80.9 | 56.3 | 62.2 | 86.8 |
田径场 | 82.2 | 65.6 | 81.6 | 65.5 | 81.4 | 86.7 |
港口 | 41.7 | 26.3 | 41.7 | 34.0 | 51.4 | 52.4 |
立交桥 | 57.0 | 44.3 | 61.1 | 38.9 | 61.9 | 68.2 |
船舶 | 47.0 | 43.1 | 49.8 | 48.6 | 48.7 | 54.5 |
体育场 | 77.9 | 69.2 | 86.4 | 67.9 | 81.2 | 89.0 |
储油罐 | 67.3 | 62.5 | 58.7 | 71.3 | 71.0 | 64.6 |
网球场 | 90.4 | 79.9 | 86.0 | 82.0 | 89.5 | 89.1 |
火车站 | 49.2 | 19.2 | 71.1 | 25.4 | 52.1 | 76.2 |
车辆 | 46.7 | 42.0 | 43.4 | 47.0 | 53.0 | 53.2 |
风车 | 56.1 | 43.2 | 61.2 | 43.3 | 56.5 | 66.4 |
表7
在DOTA数据集上不同网络模型的对比"
网络模型 | 浮点运算数 | 参数量 | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|
Faster R-CNN | 264.11×109 | 41.53×106 | 57.3 | 81.6 | 66.3 | 35.5 | 62.3 | 68.7 |
ResNet-SB | 263.78×109 | 41.19×106 | 61.2 | 85.3 | 72.1 | 38.5 | 66.5 | 75.0 |
VarifocalNet | 245.69×109 | 32.52×106 | 66.1 | 86.7 | 77.1 | 45.5 | 70.0 | 79.0 |
NAS-FCOS | 249.36×109 | 38.69×106 | 54.5 | 80.6 | 62.2 | 27.3 | 58.8 | 69.0 |
DetNAS | 270.02×109 | 29.20×106 | 58.4 | 84.0 | 68.5 | 42.6 | 62.2 | 65.9 |
本文方法 | 208.15×109 | 30.31×106 | 73.6 | 89.2 | 83.9 | 53.4 | 80.5 | 85.0 |
表8
在DOTA数据集上不同目标类别的检测精度对比"
类别 | FasterR-CNN | ResNet-SB | VarifocalNet | FCOSNAS- | DetNAS | 本文方法 |
---|---|---|---|---|---|---|
飞机 | 74.5 | 74.9 | 81.0 | 73.8 | 75.1 | 83.7 |
船舶 | 43.8 | 43.2 | 56.6 | 42.5 | 53.5 | 58.0 |
储油罐 | 46.3 | 47.5 | 60.6 | 46.6 | 52.6 | 60.5 |
棒球场 | 59.4 | 65.4 | 65.9 | 63.0 | 55.9 | 78.2 |
网球场 | 87.9 | 88.3 | 93.1 | 85.3 | 88.8 | 94.5 |
篮球场 | 76.5 | 77.2 | 79.8 | 71.7 | 71.0 | 89.9 |
操场 | 64.0 | 70.0 | 71.6 | 36.8 | 59.9 | 83.3 |
港口 | 59.3 | 62.9 | 67.7 | 56.5 | 61.3 | 74.5 |
桥梁 | 43.8 | 50.5 | 56.6 | 39.6 | 54.8 | 77.3 |
大型车辆 | 63.6 | 64.7 | 73.7 | 61.8 | 66.7 | 76.4 |
小型车辆 | 37.1 | 38.8 | 47.9 | 36.4 | 42.2 | 52.3 |
直升机 | 53.8 | 67.6 | 67.0 | 58.4 | 62.0 | 77.1 |
环形交叉路口 | 54.1 | 58.6 | 65.3 | 54.7 | 51.0 | 79.1 |
足球场 | 58.7 | 66.7 | 47.1 | 51.8 | 47.0 | 60.3 |
游泳池 | 37.6 | 42.4 | 48.4 | 38.8 | 34.4 | 55.3 |
表10
主干网络各尺度在不同权重比下的比较"
α3:α4:α5 | 浮点运算数 | 参数量 | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|
1∶1∶1 | 206.28×109 | 28.60×106 | 91.3 | 99.2 | 98.1 | 65.0 | 88.0 | 94.0 |
1∶1∶2 | 206.31×109 | 29.84×106 | 92.1 | 99.2 | 98.5 | 67.7 | 87.7 | 94.5 |
1∶1∶3 | 207.92×109 | 29.93×106 | 92.8 | 99.2 | 98.6 | 68.5 | 9.5 | 95.2 |
1∶1∶4 | 207.63×109 | 30.29×106 | 93.1 | 99.2 | 98.7 | 68.6 | 89.9 | 95.4 |
1∶1∶5 | 207.18×109 | 30.60×106 | 92.9 | 99.2 | 98.7 | 68.4 | 89.8 | 95.2 |
1∶1∶6 | 208.39×109 | 30.12×106 | 93.0 | 99.2 | 98.7 | 68.3 | 90.3 | 95.3 |
1∶1∶7 | 207.95×109 | 30.91×106 | 92.8 | 99.2 | 98.5 | 66.9 | 90.2 | 95.4 |
1∶1∶8 | 208.01×109 | 29.96×106 | 92.2 | 99.2 | 98.3 | 64.8 | 89.6 | 94.8 |
表11
RSOD数据集上的消融试验"
模型 | 说明 | 浮点运算数 | 参数量 | 网络搜索时间/h | mAP/(%) | AP50/(%) | AP75/(%) | APs/(%) | APm/(%) | APl/(%) |
---|---|---|---|---|---|---|---|---|---|---|
Model-1 | Baseline | 203.83×109 | 28.86×106 | 7.5 | 88.9 | 99.0 | 97.9 | 57.3 | 86.0 | 92.0 |
Model-2 | Baseline+渐进式进化算法 | 199.84×109 | 26.85×106 | 6.2 | 89.0 | 98.9 | 97.9 | 56.8 | 86.2 | 92.3 |
Model-3 | Baseline+FSResBlock | 209.61×109 | 30.33×106 | 9.2 | 92.9 | 99.2 | 98.6 | 68.3 | 90.1 | 95.4 |
Model-4 | Baseline+渐进式进化算法+FSResBlock | 207.63×109 | 30.29×106 | 8.1 | 93.1 | 99.2 | 98.7 | 68.6 | 89.9 | 95.4 |
[1] | 周鹏, 杨军. 采用神经网络架构搜索的遥感影像分割方法[J]. 西安电子科技大学学报, 2021, 48(5):47-57. |
ZHOU Peng, YANG Jun. Semantic segmentation of remote sensing images based on neural architecture search[J]. Journal of Xidian University, 2021, 48(5):47-57. | |
[2] | 陈丁, 万刚, 李科. 多层特征与上下文信息相结合的光学遥感影像目标检测[J]. 测绘学报, 2019, 48(10):1275-1284. DOI: 10.11947/j.AGCS.2019.20180431. |
CHEN Ding, WAN Gang, LI Ke. Object detection in optical remote sensing images based on combination of multi-layer feature and context information[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(10):1275-1284. DOI: 10.11947/j.AGCS.2019.20180431. | |
[3] | CHEN Zhanlong, LI Shuangjiang, XU Yongyang, et al. Correg-YOLOv3: a method for dense buildings detection in high-resolution remote sensing images[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(2):51-61. DOI: 10.11947/j.JGGS.2023.0206. |
[4] | 杨军, 韩鹏飞. 采用神经网络架构搜索的高分遥感影像目标检测 [J/OL]. 吉林大学学报 (工学版): 1-12 [2023-07-01]. DOI: 10.13229/j.cnki.jdxbgxb20221472. |
YANG Jun, HAN Pengfei. Object detection of high-resolution remote sensing images by neural architecture search [J/OL]. Journal of Jilin University (Engineering Edition): 1-12 [2023-07-01]. DOI: 10.13229/j.cnki.jdxbgxb20221472. | |
[5] | GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE, 2014: 580-587. |
[6] | ZOPH B, LE Q V. Neural architecture search with reinforcement learning [EB/OL]. [2023-08-01]. https://openreview.net/pdf?id=r1Ue8Hcxg. |
[7] | PHAM H, GUAN M, ZOPH B, et al. Efficient neural architecture search via parameters sharing [C]//Proceedings of 2018 International Conference on Machine Learning. Stockholm: Springer, 2018: 4095-4104. |
[8] | REAL E, AGGARWAL A, HUANG Y, et al. Regularized evolution for image classifier architecture search [C]//Proceedings of 2019 AAAI Conference on Artificial Intelligence. Hawaii: AAAI, 2019: 4780-4789. |
[9] | LIU H, SIMONYAN K, YANG Y. DARTS: differentiable architecture search [EB/OL]. [2023-08-01]. https://arxiv.org/pdf/1806.09055v2. |
[10] | GHIASI G, LIN T Y, LE Q V. NAS-FPN: learning scalable feature pyramid architecture for object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 7036-7045. |
[11] | LIANG Tingting, WANG Yongtao, TANG Zhi, et al. OPANAS: one-shot path aggregation network architecture search for object detection[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 10195-10203. |
[12] | WANG Ning, GAO Yang, CHEN Hao, et al. NAS-FCOS: fast neural architecture search for object detection[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11940-11948. |
[13] | CHEN Yukang, YANG Tong, ZHANG Xiangyu, et al. DetNAS: backbone search for object detection[J]. Advances in Neural Information Processing Systems, 2019, 32:6638-6648. |
[14] | PENG Cheng, LI Yangyang, SHANG Ronghua, et al. RSBNet: one-shot neural architecture search for a backbone network in remote sensing image recognition[J]. Neurocomputing, 2023, 537:110-127. |
[15] | HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778. |
[16] | WU Yuxin, HE Kaiming. Group normalization [C]//Proceedings of 2018 European Conference on Computer Vision. Cham: Springer, 2018: 3-19. |
[17] | CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2014: 1724-1734. |
[18] | WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11534-11542. |
[19] | HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141. |
[20] | KESAVAN H K, KAPUR J N. The generalized maximum entropy principle[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1989, 19(5):1042-1052. |
[21] | NIELSEN F, NOCK R. MaxEnt upper bounds for the differential entropy of univariate continuous distributions[J]. IEEE Signal Processing Letters, 2017, 24(4):402-406. |
[22] | CHEN Qiang, WANG Yingming, YANG Tong, et al. You only look one-level feature[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13039-13048. |
[23] | NOH H, HONG S, HAN B. Learning deconvolution network for semantic segmentation[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1520-1528. |
[24] | REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 15:1125-1131. |
[25] | TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 9627-9636. |
[26] | LI Xiang, WANG Wenhai, WU Lijun, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection [J]. Advances in Neural Information Processing Systems, 2020, 33:21002-21012. |
[27] | LONG Yang, GONG Yiping, XIAO Zhifeng, et al. Accurate object localization in remote sensing images based on convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5):2486-2498. |
[28] | LI Ke, WAN Gang, CHENG Gong, et al. Object detection in optical remote sensing images: a survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159:296-307. |
[29] | XIA Guisong, BAI Xiang, DING Jian, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3974-3983. |
[30] | XIAO Bin, TANG Han, JIANG Yanjun, et al. Brightness and contrast controllable image enhancement based on histogram specification[J]. Neurocomputing, 2018, 275:2798-2809. |
[31] | HE Zhezhi, RAKIN A S, FAN Deliang. Parametric noise injection: trainable randomness to improve deep neural network robustness against adversarial attack[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 588-597. |
[32] | REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. |
[33] | WIGHTMAN R, TOUVRON H, JÉGOU H. ResNet strikes back: an improved training procedure in timm [EB/OL]. [2023-08-01]. https://openreview.net/pdf?id=NG6MJnVl6M5. |
[34] | ZHANG Haoyang, WANG Ying, DAYOUB F, et al. VarifocalNet: an IoU-aware dense object detector[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 8514-8523. |
[1] | 殷吉崇, 武芳, 翟仁健, 邱越, 巩现勇, 行瑞星. 面向建筑物轮廓规则化的双路径边界约束与相对论生成对抗网络[J]. 测绘学报, 2024, 53(7): 1444-1457. |
[2] | 宁晓刚, 张翰超, 张瑞倩. 遥感影像高可信智能不变检测技术框架与方法实践[J]. 测绘学报, 2024, 53(6): 1098-1112. |
[3] | 顾海燕, 杨懿, 李海涛, 孙立坚, 丁少鹏, 刘世琦. 高分辨率遥感影像样本库动态构建与智能解译应用[J]. 测绘学报, 2024, 53(6): 1165-1179. |
[4] | 彭代锋, 翟晨晨, 周顶蔚, 张永军, 管海燕, 臧玉府. 基于金字塔语义token全局信息增强的高分光学遥感影像变化检测[J]. 测绘学报, 2024, 53(6): 1195-1211. |
[5] | 王继成, 郭安嵋, 慎利, 蓝天, 徐柱, 李志林. 多级对比学习下的弱监督高分遥感影像城市固废堆场提取[J]. 测绘学报, 2024, 53(6): 1212-1223. |
[6] | 丁少鹏, 卢秀山, 刘如飞, 杨懿, 顾海燕, 李海涛. 联合目标特征引导与多重注意力的建筑物变化检测[J]. 测绘学报, 2024, 53(6): 1224-1235. |
[7] | 李彦胜, 吴敏郎, 张永军. 知识图谱约束深度网络的高分辨率遥感影像场景分类[J]. 测绘学报, 2024, 53(4): 677-688. |
[8] | 黄启灏, 靳国旺, 熊新, 王丽美, 李佳豪. 通道剪枝与知识蒸馏相结合的轻量化SAR目标检测[J]. 测绘学报, 2024, 53(4): 712-723. |
[9] | 廖钊宏, 张依晨, 杨飚, 林明春, 孙文博, 高智. 基于Swin Transformer-CNN的单目遥感影像高程估计方法及其在公路建设场景中的应用[J]. 测绘学报, 2024, 53(2): 344-352. |
[10] | 林云浩, 王艳军, 李少春, 蔡恒藩. 一种耦合DeepLab与Transformer的农作物种植类型遥感精细分类方法[J]. 测绘学报, 2024, 53(2): 353-366. |
[11] | 江宝得, 黄威, 许少芬, 巫勇. 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. |
[12] | 顾小虎, 李正军, 缪健豪, 李星华, 沈焕锋. 高分遥感影像双通道并行混合卷积分类方法[J]. 测绘学报, 2023, 52(5): 798-807. |
[13] | 胡明洪, 李佳田, 姚彦吉, 阿晓荟, 陆美, 李文. 结合多路径的高分辨率遥感影像建筑物提取SER-UNet算法[J]. 测绘学报, 2023, 52(5): 808-817. |
[14] | 余东行, 徐青, 赵传, 郭海涛, 卢俊, 林雨准, 刘相云. 注意力引导特征融合与联合学习的遥感影像场景分类[J]. 测绘学报, 2023, 52(4): 624-637. |
[15] | 胡安娜, 刘睿, 吴亮, 张进, 徐永洋, 陈思琼. 顾及全局特征和纹理特征的遥感影像超分辨率重建方法[J]. 测绘学报, 2023, 52(4): 648-659. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||