Semi-supervised Network for Remote Sensing Crop Mapping Based on Improved AdvSemiSeg

ZHAI Xuedong, HAN Wenting, HAN Wenting, MA Weitong, CUI Xin, LI Guang, HUANG Shenjin

Abstract

Crop precision remote sensing mapping holds significant importance for agricultural resource surveys and management. Deep learning provides technical support for achieving accurate and efficient crop mapping.To alleviate the dependency of deep learning on labeled samples, an improved semisupervised remote sensing crop mapping method was proposed based on AdvSemiSeg. The proposed method introduced STMF-DeepLabv3+ as the generator in the adversarial learning framework, enhancing the feature encoding and semantic expression capabilities of the generator through Swin Transformer (ST) and multi-scale fusion (MF) modules, thus improving the segmentation performance of remote sensing crop images. Additionally, the efficient channel attention (ECA) module was introduced after each convolutional layer of the discriminator to adaptively learn the representation information of different channel feature maps, enhancing the discriminator’s perception of different channel features. During the training process, the discriminator provided high-quality pseudo-labels and adversarial losses to the generator, effectively improving the generalization ability of the generator. Compared with several advanced semi-supervised semantic segmentation methods, the proposed method achieved optimal performance in extracting planting information from remote sensing images in the Hetao Irrigation District of Inner Mongolia.

 

Keywords: remote sensing;crop mapping;semi-supervised learning;generative adversarial network;multi-scale features fusion;channel attention

 

Download Full Text:

PDF


References


CHEN Shuisen, LIU Qinhuo, CHEN Liangfu, et al. Review of research advances in remote sensing monitoring of grain crop area[J]. Transactions of the CSAE, 2005, 21(6): 166 -171. (in Chinese)

LIU Zhe, LIU Diyou, ZIIU Dehai, et al. Review on crop type fine identification and automatic mapping using remote sensing [J] . Transactions of the Chinese Society for Agricultural Machinery, 2018, 49( 12): 1 - 12. (in Chinese)

KYERE I, ASTOR T, GRAB R, et al. Agricultural crop discrimination in a heterogeneous low-mountain range region based on multi-temporal and multi-sensor satellite data[J]. Computers and Electronics in Agriculture, 2020, 179: 105864.

CASTELO-CABAY M, PIEDRA-FERNANDEZ J A, AYALA R. Deep learning for land use and land cover classification from the Ecuadorian Paramo [ J], International Journal of Digital Earth, 2022, 15( 1 ) : 1001 - 1017.

ZHAO Longcai, LI Fenling, CHANG Qingrui. Review on crop type identification and yield forecasting using remote sensing [J] . Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2) : 1 - 19. (in Chinese)

DONG Xiuchun, LIU Zhongyou, JIANG Yi, et al. Winter wheat extraction of WorldView — 2 image based on semantic segmentation method[J]. Remote Sensing Technology and Application, 2022, 37(3) ; 564 -570. (in Chinese)

COSTA II, FOODY G M, BOYD D S. Supervised methods of image segmentation accuracy assessment in land cover mapping [J] . Remote Sensing of Environment, 2018 , 205 ; 338 - 351.

WANG Zhimin, W ANG Jiasheng, YANG Kun, et al. Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3 + [J]. Computers and Geosciences, 2022, 158; 104969.

REDDY Y, VISWANATH P, REDDY В E. Semi-supervised learning: a brief review [J ]. International Journal of Engineering and Technology, 2018, 7(1.8): 81 -85.

CHEN Jifa, SUN Buvang, WANG Lizhe, et al. Semi-supervised semantic segmentation framework with pseudo supervisions for land-use/land-cover mapping in coastal areas [ J ]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102881.

CHEN Li, HAN Yi, YANG Guang, et al. Spatially heterogeneous cropland characteristic extraction based on improved semi¬supervised models[J ]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54 (12 ); 173 - 185. (in Chinese)

ZHANG Mingmei, XUE Yongan, ZHAN Yuanyuan, et al. Semi-supervised semantic segmentation-based remote sensing identification method for winter wheat planting area extraction[ J ]. Agronomy, 2023, 13 ( 12) ; 2868.

OLSSON V, TRANHEDEN W, PINTO J, et al. Class.Mix; segmentation-based data augmentation for semi-supervised learning С //Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021 ; 1369 - 1378.

YUN S, HAN D, OH S J, et al. CutMix; regularization strategy to train strong classifiers with localizable features [C] // Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 6023 -6032.

WANG Jiaqi, LIU Bing, ZHOU Yong, et al. Semisupervised multiscale generative adversarial network for semantic segmentation of remote sensing image[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 19; 1-5.

GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems, 2014: 2672 -2680.

HAN Wei, FENG Ruyi, WANG Lizhe, et al. A semi-supervised generative framework with deep learning features for high- resolution remote sensing image scene classification[ J ]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 145: 23 -43.

HUNG W C, TSAI H, LIOU Y T, et al. Adversarial learning for semi-supervised semantic segmentation [ J] . arXiv Preprint, arXiv: 1802. 07934 , 2018.

GENG Yanlei, ZOU Zhengrong, HE Shuaishuai. Semantic segmentation of objects in remote sensing images based on semi¬supervised generative adversarial nets [ J ]. Geomatics and Spatial Information Technology, 2020, 43 (4 ): 36 - 39. (in Chinese)

CHEN Hao, LI Zhenghong, WU Jiangjiang, et al. SemiRoadExNet: a semi-supervised network for road extraction from remote sensing imagery via adversarial learning [J ]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 198: 169 - 183.

LU Huanyu, ZHANG Yonghong, MA Guangyi, et al. Semi-supervised adversarial learning based water body extraction from remote sensing images[ j]. Computer Engineering, 2024, 50(7) ; 251 -263. (in Chinese)

LI Guang, GUI Jiawei, HAN Wenting, et al. Crop type mapping using time-series Sentinel — 2 imagery and U-Net in early growth periods in the Hetao irrigation district in China [J]. Computers and Electronics in Agriculture, 2022, 203: 107478.


Refbacks

  • There are currently no refbacks.