面向梯田遥感识别的JAM-R-CNN深度网络模型

谢君洋; 林安琪; 吴浩; 吴紫薇; 吴文斌; 余强毅

doi:10.11834/jrs.20233126

浏览量 : 0 下载量: 124 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

面向梯田遥感识别的JAM-R-CNN深度网络模型
JAM-R-CNN deep learning network model for remote sensing recognition of terrace
2023年页码：1-12
网络出版日期： 2023-07-20 ，
DOI： 10.11834/jrs.20233126

扫描看全文

谢君洋，林安琪，吴浩，吴紫薇，吴文斌，余强毅.XXXX.面向梯田遥感识别的JAM-R-CNN深度网络模型.遥感学报，XX（XX）： 1-12

XIE Junyang，LIN Anqi，WU Hao，WU Ziwei，WU Wenbin，YU Qiangyi. XXXX. JAM-R-CNN deep learning network model for remote sensing recognition of terrace. National Remote Sensing Bulletin， XX（XX）：1-12
谢君洋，林安琪，吴浩，吴紫薇，吴文斌，余强毅.XXXX.面向梯田遥感识别的JAM-R-CNN深度网络模型.遥感学报，XX（XX）： 1-12 DOI： 10.11834/jrs.20233126.

XIE Junyang，LIN Anqi，WU Hao，WU Ziwei，WU Wenbin，YU Qiangyi. XXXX. JAM-R-CNN deep learning network model for remote sensing recognition of terrace. National Remote Sensing Bulletin， XX（XX）：1-12 DOI： 10.11834/jrs.20233126.

摘要

快速准确地掌握梯田的空间分布，不仅为水土保持提供重要的数据支撑，也提高了山区农业的监管水平。在利用深度学习方法进行梯田识别的过程中，形状狭长的梯田容易因卷积运算而造成漏提现象，并且在山区地物边界不清晰的复杂背景下，易产生大面积粘连的识别结果，导致最终的梯田识别精度不高。为此，本研究提出了一种面向梯田遥感识别的JAM-R-CNN深度网络模型，该模型以Mask R-CNN为基础，融合跳跃网络来维持高分辨率遥感影像的高语义信息，引入卷积注意力机制模块来加强梯田的特征表达能力，修改模型的锚框大小以适应梯田狭长的特性。在重庆市南川区的盐井梯田区域，使用国产高分二号（GF-2）卫星影像数据进行实验，结果表明，JAM-R-CNN网络模型的梯田识别结果精确率为90.81%，召回率为84.28%，F1为88.98%，IoU为83.15%。相较于经典的Mask R-CNN模型，JAM-R-CNN网络模型的梯田识别精度较高，4个评价指标依次提升了1.96%、5.26%、3.29%和5.19%。消融实验结果验证了模型改进的三个模块均对梯田识别有明显的促进作用。综上，本研究提出的JAM-R-CNN深度网络模型不仅能够有效减少梯田识别结果的粘连现象，而且明显提高了狭长型梯田的提取率，实现了梯田遥感识别整体精度的显著提升，具有较好的应用价值。

Abstract

Objective Efficiently and accurately grasping the spatial distribution of terraced fields not only provides important data support for soil and water conservation

but also improves the regulatory level of agriculture in mountainous areas. In the process of using deep learning methods for terrace recognition

narrow and elongated terraces are prone to missing extraction due to convolution operations

and in complex backgrounds with unclear terrain boundaries in mountainous areas

large areas of adhesive recognition results are easily generated

which leads to low accuracy in the final terrace recognition. Therefore

in order to further achieve accurate recognition of terrace information

the urgent technical problem to be solved is how to effectively maintain the high semantic information of high-resolution remote sensing images in the convolution operation process based on the characteristics of terraces

reduce the omission of narrow and long terraces and the adhesion of recognition results.Method To address the above problems

this paper proposes a JAM-R-CNN deep learning network terrace recognition method based on very high resolution remote sensing images. This network is based on the Mask R-CNN model

integrates the jumping network to maintain the high Semantic information of high resolution remote sensing images

introduces the convolutional block attention module (CBAM) to enhance the feature expression ability of terraces

and modifies the anchor size to adapt to the narrow and long characteristics of terraces

so as to achieve the purpose of improving the terrace recognition accuracy. To test the proposed method

the part of the salt well terraces in Nanchuan District

Chongqing

China was selected as the study area

and used four models in the domestic GF-2 satellite image data for experiments.Result The results show that the terrace parcel map derived from the JAM-R-CNN model achieved the precision of 90.81%

recall of 84.28%

the F1 score of 88.98% and the IoU of 83.15%. Compared with the results of the Mask R-CNN

the value of the precision

recall

F1 score and IoU in the results of the JAM-R-CNN model were increased by 1.96%

5.26%

3.29% and 5.19%

indicating that the JAM-R-CNN model can better identify the terraces. Most of the terraces identified by the Unet and DeepLab v3+ are connected together

and the terraced fields with small size fail to be distinguished. The JAM-R-CNN model identifies fewer missing areas on the periphery of terraces compared to the Mask R-CNN model

and the number of missing narrow and long terraces is significantly reduced. This is the effect of three improvement parts

which further proves that the JAM-R-CNN model proposed in this article has significant improvement effect and shows superior performance in remote sensing recognition of terraces.Conclusion To sum up

the JAM-R-CNN deep learning network model proposed in this article not only effectively reduces the adhesion phenomenon of terrace recognition results

but also significantly improves the extraction rate of narrow and long terraces

achieving a significant improvement in the overall accuracy of terrace remote sensing recognition

and has good application value.

关键词

遥感梯田识别高分辨率遥感影像深度学习跳跃网络JAM-R-CNN

Keywords

remote sensingterrace recognitionhigh resolution remote sensing imagedeep learningjump networkJAM-R-CNN

references

Cai Z W，He Z，Wang W J，Yang J Y，Wei H D，Wang C, and Xu B D. 2022. Mapping cropland at metric resolution using the spatiotemporal information from multi-source GF satellite data. National Remote Sensing Bulletin，26(7): 1368-1382

蔡志文, 何真, 王文静, 杨靖雅, 魏浩东, 王聪, 徐保东. 2022. 基于多源国产高分卫星时空信息的米级分辨率耕地提取. 遥感学报, 26(7): 1368-1382 [DOI: 10.11834/jrs.20221069http://dx.doi.org/10.11834/jrs.20221069]

Chen L L, Shi Z, Liao K T, Song Y J and Zhang H M. 2022. Cultivated land extraction from high resolution remote sensing image based on convolutional neural network. Transactions of the Chinese Society for Agricultural Machinery, 53(9): 168-177

陈玲玲, 施政, 廖凯涛, 宋月君, 张红梅. 2022. 基于卷积神经网络的高分遥感影像耕地提取研究. 农业机械学报, 53(9):168-177 [DOI: 10.6041/j.issn.1000-1298. 2022.09.017http://dx.doi.org/10.6041/j.issn.1000-1298.2022.09.017]

Dai W, Na J M, Huang N, Hu G H, Yang X, Tang G A, Xiong L Y, and Li F Y. 2020. Integrated edge detection and terrain analysis for agricultural terrace delineation from remote sensing images. International Journal of Geographical Information Science, 34(3):484-503. [DOI: 10.1080/13658816.2019.1650363http://dx.doi.org/10.1080/13658816.2019.1650363]

Dang T M, Mu X M, Sun W Y, Gao P, and Zhao G J. 2017. Review of quickly discriminating approaches of terrace information based on high resolution remote sensing images. Yellow River, 39(3): 85-89+94

党恬敏, 穆兴民, 孙文义, 高鹏, 赵广举. 2017. 高分辨率遥感影像梯田快速提取方法研究进展. 人民黄河, 39(3): 85-89+94 [DOI: 10.3969/j.issn.1000-1379. 2017.03.019http://dx.doi.org/10.3969/j.issn.1000-1379.2017.03.019]

Deng P F，Xu K J, and Huang H. 2021. CNN-GCN-based dual-stream network for scene classification of remote sensing images. National Remote Sensing Bulletin，25(11)：2270-2282

邓培芳, 徐科杰, 黄鸿. 2021. 基于CNN-GCN双流网络的高分辨率遥感影像场景分类. 遥感学报, 25 (11):2270-2282 [DOI: 10.11834/jrs.20210587http://dx.doi.org/10.11834/jrs.20210587]

Diaz-Varela R A, Zarco-Tejada P J, Angileri V, and Loudjani P. 2014. Automatic identification of agricultural terraces through object-oriented analysis of very high resolution DSMs and multispectral imagery obtained from an unmanned aerial vehicle. Journal of Environmental Management, 134 (15):117-126. [DOI: 10.1016/j.jenvman.2014.01.006http://dx.doi.org/10.1016/j.jenvman.2014.01.006]

Dong S J, Xin L J, Li S F, Xie H L, Zhao Y L, Wang X, Li X B, Song H F, and Lu Y H. 2023. The extent and spatial distribution of terrace abandonment in China. Acta Geographica Sinica, 78(1): 3-15

董世杰, 辛良杰, 李升发, 谢花林, 赵宇鸾, 王学, 李秀彬, 宋恒飞, 卢亚晗. 2023. 中国梯田撂荒程度及空间格局分异研究. 地理学报, 78(1): 3-15 [DOI: 10.11821/dlxb202301001http://dx.doi.org/10.11821/dlxb202301001]

Eckert S, Ghebremicael S T, Hurni H, and Kohler T. 2017. Identification and classification of structural soil conservation measures based on very high resolution stereo satellite data. Journal of Environmental Management, 193:592-606. [DOI: 10.1016/j.jenvman.2017.02.061http://dx.doi.org/10.1016/j.jenvman.2017.02.061]

He K M, Gkioxari G, Dollar P, and Girshick R. 2017. Mask R-CNN. the International Conference on Computer Vision, 2961-2969. [DOI: 10.48550/arXiv.1703.06870http://dx.doi.org/10.48550/arXiv.1703.06870]

Jong M, Guan K Y, Wang S B, Huang Y Z, and Peng B. 2022. Improving field boundary delineation in ResUNets via adversarial deep learning. International Journal of Applied Earth Observation and Geoinformation, 112:102877. [DOI: 10.1016/j.jag.2022.102877http://dx.doi.org/10.1016/j.jag.2022.102877]

Liu W, Wu Z P, Luo J C, Sun Y W, Wu T J, Zhou N, Hu X D, Wang L Y, and Zhou Z F. 2021. A divided and stratified extraction method of high-resolution remote sensing information for cropland in hilly and mountainous areas based on dep leaning. Acta Geodaetica et Cartographica Sinica, 50(1): 105-116

刘巍, 吴志峰, 骆剑承, 孙营伟, 吴田军, 周楠, 胡晓东, 王玲玉, 周忠发. 2021. 深度学习支持下的丘陵山区耕地高分辨率遥感信息分区分层提取方法. 测绘学报, 50(1): 105-116 [DOI: 10.11947/j.AGCS.2021.20190448http://dx.doi.org/10.11947/j.AGCS.2021.20190448]

Liu X Y, Yang S T, Wang F G, He Z X, Ma H B, and Luo Y. 2014. Analysis on sediment yield reduced by current terrace and shrubs-herbs-arbor vegetation in the Loess Plateau. Journal of Hydraulic Engineering, 45(11):1293-300

刘晓燕, 杨胜天, 王富贵, 何兴照, 马红斌, 罗娅. 2014. 黄土高原现状梯田和林草植被的减沙作用分析. 水利学报, 45(11):1293-1300 [DOI: 10.13243/j.cnki.slxb.2014.11.004http://dx.doi.org/10.13243/j.cnki.slxb.2014.11.004]

Long J, Li M M, Wang X Q, and Stein A. 2022. Delineation of agricultural fields using multi-task BsiNet from high-resolution satellite images. International Journal of Applied Earth Observation and Geoinformation, 112: 102871.[DOI: 10.1016/j.jag.2022.102871http://dx.doi.org/10.1016/j.jag.2022.102871]

Luo L H, Li F Y, Dai Z Y, Yang X, Liu W, and Fang X. 2020. Terrace extraction based on remote sensing images and digital elevation model in the loess plateau, China. Earth Science Informatics, 13:433-446. [DOI: 10.1007/s12145-020-00444-xhttp://dx.doi.org/10.1007/s12145-020-00444-x]

Mei W Y, Wang H Y, David F, Zhou W Q, Isabella H, Josh M G, Derek V B, and Jain M. 2022. Using Deep Learning and Very-High-Resolution Imagery to Map Smallholder Field Boundaries. Remote Sensing, 14(13): 3046. [DOI: 10.3390/rs14133046http://dx.doi.org/10.3390/rs14133046]

Sun W Y, Zhang Y Q, Mu X M, Li J Y, Gao P, Zhao G H, Dang T M, and Chiew F. 2019. Identifying terraces in the hilly and gully regions of the Loess Plateau in China. Land Degradation & Development, 30(17): 2126-2138. [DOI: 10.1002/ldr.3405http://dx.doi.org/10.1002/ldr.3405]

Waldner F, Diakogiannis F I. 2020. Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sensing of Environment, 245:111741. [DOI: 10.1016/j.rse.2020.111741http://dx.doi.org/10.1016/j.rse.2020.111741]

Wang J D, Sun K, Cheng T H, Jiang B R, Deng C R, Zhao Y, Liu D, Mu Y, Tan M K, Wang X G, Liu W Y, and Xiao B. 2021. Deep High-Resolution Representation Learning for Visual Recognition. IEEE transactions on pattern analysis and machine intelligence, 43(10): 3349 - 3364. [DOI: 10.1109/TPAMI.2020.2983686http://dx.doi.org/10.1109/TPAMI.2020.2983686]

Woo S, Park J C, Lee J Y, and Kweon I S. 2018. CBAM: Convolutional Block Attention Module. the European Conference on Computer Vision, 3-19. [DOI: 10.48550/arXiv.1807.06521http://dx.doi.org/10.48550/arXiv.1807.06521]

Xu Z Y，Shen Z F，Li Y，Zhao L F，Ke Y M，Li L L, and Wen Q. 2022. Classification of high-resolution remote sensing images based on enhanced DeepLab algorithm and adaptive loss function. National Remote Sensing Bulletin，26(2)：406-415

许泽宇, 沈占锋, 李杨, 赵丽芳, 柯映明, 李苓苓, 温奇. 2022. 增强型DeepLab算法和自适应损失函数的高分辨率遥感影像分类. 遥感学报, 26(2):406-415 [DOI: 10.11834/jrs.20209200http://dx.doi.org/10.11834/jrs.20209200]

Xue M D, Zhang H M, Yang J T, and Li X S. 2019. Extraction of terrace information based on UAV image and topographic index. Application Research of Computers, 36(8): 2527-2533+2538

薛牡丹, 张宏鸣, 杨江涛, 李星恕. 2019. 无人机影像与地形指数结合的梯田信息提取. 计算机应用研究, 36(8): 2527-2533+2538 [DOI: 10.19734/j.issn.1001-3695. 2018.01.0182http://dx.doi.org/10.19734/j.issn.1001-3695.2018.01.0182]

Yu M G, Rui X P, Xie W Y, Xu X J, and Wei W. 2022. Research on Automatic Identification Method of Terraces on the Loess Plateau Based on Deep Transfer Learning. Remote Sensing, 14 (10):2446. [DOI: 10.3390/rs14102446http://dx.doi.org/10.3390/rs14102446]

Yuan S, Tang H, and Guo Y. 2022. Segmentation method for plant leaves using an improved Mask R-CNN model. Transactions of the Chinese Society of Agricultural Engineering, 38(1): 212-220

袁山, 汤浩, 郭亚. 2022. 基于改进Mask R-CNN模型的植物叶片分割方法. 农业工程学报, 38 (1): 212-220 [doi: 10.11975/j.issn.1002-6819.2022.01.024http://dx.doi.org/10.11975/j.issn.1002-6819.2022.01.024]

Zhao F, Xiong L Y, Wang C, Wang H R, Wei H, and Tang G A. 2021. Terraces mapping by using deep learning approach from remote sensing images and digital elevation models. Transactions in GIS, 25(5): 2438-2454. [DOI: 10.1111/tgis.12824http://dx.doi.org/10.1111/tgis.12824]

Zhao X, Wang X J, Zhao Y, Luo Z D, Xu Y L, Guo H, and Zhang Y. 2016. Feasibility Analysis on Methodology of Terraced Extraction by Using Fourier Transformation Based on Domestic Hi-Resolution Remote Sensing Images of GF-1 Satellite. Soil and Water Conservation in China, (1): 63-65+73

赵欣, 王晓晶, 赵院, 罗志东, 许永利, 郭浩, 张羿. 2016. 国产高分一号卫星数据傅里叶变换提取梯田影像可行性分析. 中国水土保持, (1): 63-65+73 [DOI: 10.14123/j.cnki.swcc.2016.0050http://dx.doi.org/10.14123/j.cnki.swcc.2016.0050]

Zhou N, Yang P, Wei C S, Shen Z F, Yu J J, Ma X Y, and Luo J C. 2021. Accurate extraction method for cropland in mountainous areas based on field parcel. Transactions of the Chinese Society of Agricultural Engineering, 37(19):260-266

周楠, 杨鹏, 魏春山, 沈占锋, 余娟娟, 马晓宇, 骆剑承. 2021. 地块尺度的山区耕地精准提取方法. 农业工程学报, 37(19): 260-266 [DOI: 10.11975/j.issn.1002-6819.2021.19.030http://dx.doi.org/10.11975/j.issn.1002-6819.2021.19.030]

Zhou Y, Li M M, Wang X Q, Wu S Y, and Jin S L. 2022. Extraction of farming terraces using object-based convolutional neural networks from very high resolution satellite image. Remote Sensing Information, 37(2):138-144

周珏, 李蒙蒙, 汪小钦,吴思颖, 金时来. 2022. 面向对象卷积神经网络的耕作梯田提取. 遥感信息, 37(2): 138-144 [DOI: 10.3969/j.issn.1000-3177.2022.02.019http://dx.doi.org/10.3969/j.issn.1000-3177.2022.02.019]

文章被引用时，请邮件提醒。

提交

光学信号Token引导的异源遥感变化检测网络

高光谱遥感影像异常目标检测研究进展

基于多方向自适应感知网络的高光谱遥感图像分类

弱监督尺度自适应增强的高分辨率遥感影像场景分类

结合RGB-DSM图像和深度学习的城市樟树树冠检测