水土保持措施识别与提取方法的研究进展

田培; 任益伶; 陈妍

doi:10.13870/j.cnki.stbcxb.2024.05.025

您当前的位置：

首页 >

文章列表页 >

水土保持措施识别与提取方法的研究进展

更新时间：2025-02-18

- 水土保持措施识别与提取方法的研究进展
- Research Progress on Identification and Extraction Methods of Soil and Water Conservation Measures
- 水土保持学报 2024年38卷第5期页码：1-9
- 作者机构：
  
  华中师范大学城市与环境科学学院, 地理过程分析与模拟湖北省重点实验室,武汉,430079
- 作者简介：
  
  [ "田培(1988—),男,博士,副教授,硕士生导师,主要从事土壤侵蚀与水土保持、水文水资源研究。E-mail:tianpei@ccnu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金项目(42377354);湖北省自然科学基金面上项目(2024AFB951);教育部"春晖计划"合作科研项目(202200199);水利部水网工程与调度重点实验室开放研究基金项目(QTKS0034W2328)
- DOI：10.13870/j.cnki.stbcxb.2024.05.025
  中图分类号： S157.1
- 纸质出版：2024
- 稿件说明：
移动端阅览
田培, 任益伶, 陈妍. 水土保持措施识别与提取方法的研究进展[J]. 水土保持学报, 2024,38(5):1-9.

TIAN Pei, REN Yiling, CHEN Yan. Research Progress on Identification and Extraction Methods of Soil and Water Conservation Measures[J]. 2024, 38(5): 1-9.
田培, 任益伶, 陈妍. 水土保持措施识别与提取方法的研究进展[J]. 水土保持学报, 2024,38(5):1-9. DOI： 10.13870/j.cnki.stbcxb.2024.05.025.

TIAN Pei, REN Yiling, CHEN Yan. Research Progress on Identification and Extraction Methods of Soil and Water Conservation Measures[J]. 2024, 38(5): 1-9. DOI： 10.13870/j.cnki.stbcxb.2024.05.025.

摘要

[目的] 水土保持措施类型及其配置模式复杂繁多

准确识别与精细化提取水土保持措施详细配置信息是获取水土保持措施因子值的基础。[方法] 水土保持措施信息获取方式主要有传统的野外调查、卫星遥感影像和无人机近景摄影等

其识别与提取方法主要包括目视解译、传统的机器学习、面向对象分类方法及深度学习模型。通过梳理国内外水土保持措施识别与提取方法的研究成果

总结存在的不足并提出研究展望。[结果] 在语义分割中未来的特征融合与多模态学习、弱监督与半监督学习、集成学习和元学习等均可被运用到水土保持措施提取中。[结论] 当前对于水土保持耕作措施识别与提取的成果鲜见报道

而农业实践中耕作措施较常见

后续应加强耕作措施识别提取的研究;人工智能结合大数据技术是未来水土保持措施信息高效精准识别与提取的发展方向

需要进一步研究采用半监督、弱监督学习方法

结合多模态学习、小样本标签等方法

获取高质量的标记样本数据

进行水土保持点、线状工程措施的提取;将多模态学习、实例分割方法等深度学习算法与面向对象分类方法相结合应用到水土保持植物措施的识别提取中

提高不同水土保持植物措施的分类提取精度

从而完善各类水土保持措施的信息提取方法

为准确获取水土保持措施因子值及核算水土保持碳汇能力提供支撑。

Abstract

[Objective] The types of soil and water conservation measures and their configuration modes are complicated. Accurate identification and fine extraction of detailed configuration information of soil and water conservation measures are the basis for obtaining the factor values of soil and water conservation measures. [Methods] The information acquisition methods of soil and water conservation measures mainly include traditional field surveys

satellite remote sensing images

and UAV close-range photography. The identification and extraction methods mainly include visual interpretation

traditional machine learning

object-oriented classification methods

and deep learning models. By combing the research results of identification and extraction methods of soil and water conservation measures at home and abroad

the existing shortcomings are summarized and the research prospects are put forward. [Results] In semantic segmentation

future feature fusion and multimodal learning

weak supervision and semi-supervised learning

integrated learning and meta-learning can be applied to the extraction of soil and water conservation measures. [Conclusion] At present

there are few reports on the results of identification and extraction of soil and water conservation tillage measures. However

tillage measures are common in agricultural practice

and the research on identification and extraction of tillage measures should be strengthened in the future. Artificial intelligence combined with big data technology is the development direction of efficient and accurate identification and extraction of soil and water conservation measures in the future. It is necessary to further study the use of semi-supervised and weakly supervised learning methods

combined with multi-modal learning

small sample labels and other methods to obtain high-quality labeled sample data for soil and water conservation. Extraction of point and linear engineering measures; the combination of deep learning algorithms such as multimodal learning and instance segmentation methods with object-oriented classification methods is applied to the identification and extraction of soil and water conservation plant measures to improve the classification and extraction accuracy of different soil and water conservation plant measures. So as to improve the information extraction method of various soil and water conservation measures

and provide support for accurately obtaining the factor value of soil and water conservation measures and calculating the carbon sink capacity of soil and water conservation.

关键词

Keywords

references

赵蒙恩,闫庆武,刘政婷,等.鄂尔多斯市土壤侵蚀时空演变及影响因子分析[J].干旱区研究,2022,39(6):1819-1831. ZHAO M E, YAN Q W, LIU Z T, et al. Analysis of temporal and spatial evolution and influencing factors of soil erosion in Ordos City[J].Arid Zone Research,2022,39(6):1819-1831.

汪言在,董一帆,苏正安.基于土地利用与植被恢复情景的土壤侵蚀演变特征[J].自然资源学报,2020,35(6):1369-1380. WANG Y Z, DONG Y F, SU Z A. Assessment of soil erosion change under land use and reforestation scenarios[J].Journal of Natural Resources,2020,35(6):1369-1380.

郭兴月,王添,程圣东,等.近30年土壤侵蚀模型研究进展[J].泥沙研究,2023,48(1):65-72. GUO X Y, WANG T, CHENG S D, et al. Progress of soil erosion models in recent 30 years[J].Journal of Sediment Research,2023,48(1):65-72.

TAYE G, VANMAERCKE M, POESEN J, et al. Determining RUSLE P- and C-factors for stone bunds and trenches in rangeland and cropland, North Ethiopia[J].Land Degradation and Development,2018,29(3):812-824.

FRAZIER P S, PAGE K J. Water body detection and delineation with Landsat TM data[J].Photogrammetric Engineering and Remote Sensing,2000,66(12):1461-1467.

WANG Y B, HU X D, YU S X, et al. Soil conservation of sloping farmland in China: History, present, and future[J].Earth Science Reviews,2024,249:e104655.

杨润泽,肖辉杰,冯天骄,等.密云水库周边板栗林下不同水土保持措施效益评价[J].水土保持研究,2022,29(6):28-35. YANG R Z, XIAO H J, FENG T J, et al. Evaluation on benefits of different soil and water conservation measures under

Castanea mollissima

bl. forest around Miyun Reservoir[J].Research of Soil and Water Conservation,2022,29(6):28-35.

PING Y D, TIAN P, LUO L, et al. Soil erosion sensitivity and prediction for hilly areas of Hubei Province, China, using combined RUSLE and LSTM models[J].Journal of Soils and Sediments,2024,24(2):829-846.

季富华,刘佳,王利民.农作物类型遥感识别算法及国产高分卫星应用示例[J].中国农业资源与区划,2021,42(7):254-268. JI F H, LIU J, WANG L M. Summary of remote sensing algorithm in crop type identification and its application based on gaofen satellites[J].Chinese Journal of Agricultural Resources and Regional Planning, 2021,42(7):254-268.

张雅文,许文盛,韩培,等.无人机遥感技术在生产建设项目水土保持监测中的应用:以鄂北水资源配置工程为例[J].中国水土保持科学,2017,15(2):132-139. ZHANG Y W, XU W S, HAN P, et al. Application of the UAV remote sensing technology in soil and water conservation monitoring in construction projects: A case study of water resources allocation for the region of North Hubei[J].Scienceof Soil and Water Conservation,2017,15(2):132-139.

赵兴实,田中雨,刘岩,等.卫片目视解译在土壤侵蚀现状调查中的应用[J].水土保持通报,1996,16(1):149-152. ZHAO X S, TIAN Z Y, LIU Y, et al. Application of visual interpretation of satellite photos in investigation of soil erosion status[J].Bulletin of Soil and Water Conservation,1996,16(1):149-152.

杨蕾.基于Spot5遥感影像提取水土保持信息的研究[D].西安:西北大学,2006. YANG L. A research on extraction soil and water conservation information based on Spot5 images[D].Xi’an: North West University,2006.

赵东波.基于高分辨率遥感影像的水土保持措施信息提取和分析[D].陕西杨凌:西北农林科技大学,2007. ZHAO D B. The analysis and extraction of soil conservation practices information based on hi-resolution remote sensing images[D].Yangling, Shaanxi: Northwest A&F University,2007.

吴卿.基于高分辨率遥感影像的水土保持生态建设监测方法研究[D].北京:北京林业大学,2007. WU Q. Study on monitoring method for ecological construction of water and soil conservation based on high-resolution remote sensing images[D].Beijing: Beijing Forestry University,2007.

赵帮元,马宁,杨娟,等.基于不同分辨率遥感影像提取的水土保持措施精度分析[J].水土保持通报,2012,32(4):154-157. ZHAO B Y, MA N, YANG J, et al. Extracting features of soil and water conservation measures from remote sensing images of different resolution levels: Accuracy analysis[J].Bulletin of Soil and Water Conservation,2012,32(4):154-157.

施明新.无人机技术在生产建设项目水土保持监测中的应用[J].水土保持通报,2018,38(2):236-240. SHI M X. Application of UAV remote sensing technology to monitoring of soil and water conservation for construction projects[J].Bulletin of Soil and Water Conservation,2018,38(2):236-240.

LI L L, QIAO J W, YAO J, et al. Automatic freezing-tolerant rapeseed material recognition using UAV images and deep learning[J].Plant Methods,2022,18:e5.

KONG H, WU D. Research on land use classification method of high resolution remote sensing image based on SVM[J].Academic Journal of Science and Technology,2023,7(2):111-114.

XU Z H, SONG H Y, WU Z M, et al. Research on crop information extraction of agricultural uav images based on blind image deblurring technology andsvm[J].INMATEH Agricultural Engineering,2021,64:33-42.

XU A A, WANG F, LI L. Vegetation information extraction in Karst area based on UAV remote sensing in visible light band[J].Optik,2023,272:e170355.

FENG C, ZHANG W J, DENG H, et al. A combination of OBIA and random forest based on visible UAV remote sensing for accurately extracted information about weeds in areas with different weed densitiesin farmland[J].Remote Sensing,2023,15(19):e4696.

KESHTKAR H, VOIGT W, ALIZADEH E. Land-cover classification and analysis of change using machine-learning classifiers and multi-temporal remote sensing imagery[J].Arabian Journal of Geosciences,2017,10(6):e154.

李煜.基于高分辨影像机器学习算法的落叶松人工林提取研究[D].西安:西安科技大学,2021. LI Y. Extraction of Larch plantations machine learning within high spatial resolution images[D].Xi’an: Xi’an University of Science and Technology,2021.

李志铭,赵静,兰玉彬,等.基于无人机可见光图像的作物分类研究[J].西北农林科技大学学报(自然科学版),2020,48(6):137-144. LI Z M, ZHAO J, LAN Y B, et al. Crop classificationbased on UAV visible image[J].Journal of Northwest A&F University (Natural Science Edition),2020,48(6):137-144.

NIU Y C, YIN J Q. Weakly supervised point cloud semantic segmentation with the fusion of heterogeneous network features[J].Image and Vision Computing,2024,142:e104916.

GAO Z J, ZHANG Y J, LI Y K. Extracting features from infrared images using convolutional neural networks and transfer learning[J].Infrared Physics and Technology,2020,105:e103237.

夏晨真,张月.基于厘米级无人机影像的水土保持措施精准识别[J].水土保持学报,2020,34(5):111-118. XIA C Z, ZHANG Y. Accurate identification of soil and water conservation measures based on centimeter-resolution UAV images[J].Journal of Soil and Water Conservation,2020,34(5):111-118.

张艳超,杨海龙,信忠保,等.基于面向对象和无人机影像的黄土高原丘陵区小流域梯田提取研究[J].水土保持学报,2023,37(3):139-146. ZHANG Y C, YANG H L, XIN Z B, et al. Extraction of small watershed terraces in the hilly areas of Loess Plateau through UAV images with object-oriented approach[J].Journal of Soil and Water Conservation,2023,37(3):139-146.

侯群群. 面向对象的遥感影像水土保持措施信息提取研究[D].陕西杨凌:西北农林科技大学,2013. HOU Q Q. Soil conservation practices information extraction from remote sensing images using object-oriented method[D].Yangling, Shaanxi: Northwest A&F University,2013.

YANG K L, ZHANG H X, WANG F, et al. Extraction of broad-leaved tree crown based on UAV visible images and OBIA-RF model: A case study for Chinese olive trees[J].Remote Sensing,2022,14(10):e2469.

LI H T, GU H Y, HAN Y S, et al. Object-oriented classification of high-resolution remote sensing imagery based on an improved colour structure code and a support vector machine[J].International Journal of Remote Sensing,2010,31(6):1453-1470.

GUO Q, ZHANG J, GUO S J, et al. Urban tree classification based on object-oriented approach and random forest algorithm using unmanned aerial vehicle(UAV) multispectral imagery[J].Remote Sensing,2022,14(16):e3885.

XU Q, JIN M T, GUO P. A high-precision crop classification method based on time-series UAV images[J].Agriculture,2022,13(1):e97.

赵搏华,王秀茹,阎世煜,等.面向对象分类方法在水土保持措施提取中的应用[J].中国水土保持科学(中英文),2022,20(1):122-127. ZHAO B H, WANG X R, YAN S Y, et al. Application of object-oriented classification method in the extraction of soil and water conservation measures[J].Science of Soil and Water Conservation,2022,20(1):122-127.

邬宁珊.基于无人机遥感提取黄土区林地植被参数的方法研究[D].北京:北京林业大学,2021. WU N S. Determining vegetation parameters from UAV imagery in loess region[D].Beijing: Beijing Forestry University,2021.

钱伟,王春,代文,等.基于深度学习融合OBIA的黄土高原小流域淤地坝系提取[J].干旱区地理,2023,46(11):1803-1812. QIAN W, WANG C, DAI W, et al. Extraction of check dam system in small watershed of Loess Plateau based on deep learning and OBIA[J].Arid Land Geography,2023,46(11):1803-1812.

ZHAO F C, WU X M, WANG S. Object-oriented vegetation classification method based on UAV and satellite image fusion[J].Procedia Computer Science,2020,174:609-615.

王杰.基于面向对象分类和CNN的土地覆盖遥感提取[D].合肥:安徽大学,2020. WANG J. Remote sensing based extraction of land cover using object-oriented classification and CNN[D].Hefei: Anhui University,2020.

ARUN S A, AKILA A S. Land-cover classification with hyperspectral remote sensing image using CNN and spectral band selection[J].Remote Sensing Applications: Society and Environment, 2023,31:e100986.

LI Q J, TIAN J, TIAN Q J. Deep learning application for crop classification via multi-temporal remote sensing images[J].Agriculture,2023,13(4):e906.

LIN N, QUAN H L, HE J, et al. Urban vegetation extraction from high-resolution remote sensing imagery on SD-UNet and vegetation spectral features[J].Remote Sensing,2023,15(18):e4488.

LUO L H, LI F Y, DAI Z Y, et al. Terrace extraction based on remote sensing images and digital elevation model in the Loess Plateau, China[J].Earth Science Informatics,2020,13(2):433-446.

ZHAO F, XIONG L Y, WANG C, et al. Terraces mapping by using deep learning approach from remote sensing images and digital elevation models[J].Transactions in GIS,2021,25(5):2438-2454.

WANG Y N, KONG X B, GUO K, et al. Intelligent extraction of terracing using the ASPP ArrU-net deeplearning model for soil and water conservation on the Loess Plateau[J].Agriculture,2023,13(7):e1283.

朱默研.基于深度学习的遥感影像淤地坝语义分割[D].银川:宁夏大学,2022. ZHU M Y. Semantic segmentation of warping dams in remote sensing image based on deep learning[D].Yinchuan: Ningxia University,2022.

YU M G, RUI X P, XIE W Y, et al. Research on automatic identification method of terraces on the Loess Plateau based on deep transfer learning[J].Remote Sensing,2022,14(10):e2446.

LU H, FU X, LIU C, et al. Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning[J].Journal of Mountain Science,2017,14(4):731-741.

YANG B, ZHAO M C, XING Y, et al. VEDAM: Urban vegetation extraction based on deep attention model from high-resolution satellite images[J].Electronics,2023,12(5):e1215.

TANG T Y, FU B L, LOU P Q, et al. Segnet-based extraction of wetland vegetation information from uav images[J].ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences,2020,4210:375-380.

杨亚男,张宏鸣,李杭昊,等.结合FCN和DenseCRF模型的无人机梯田识别方法研究[J].计算机工程与应用,2021(3):222-230. YANG Y N, ZHANG H M, LI H H, et al. Research on UAV terrace recognition method based on FCN and Dense CRF model[J].Computer Engineering and Applications,2021(3):222-230.

邓泓,杨滢婷,刘兆朋,等.基于深度学习的无人机水田图像语义分割方法[J].中国农机化学报,2021,42(10):165-172. DENG H, YANG Y T, LIU Z P, et al. Semantic segmentation of paddy image by UAV based on deep learning[J].Journal of Chinese Agricultural Mechanization,2021,42(10):165-172.

杨蜀秦,宋志双,尹瀚平,等.基于深度语义分割的无人机多光谱遥感作物分类方法[J].农业机械学报,2021,52(3):185-192. YANG S Q, SONG Z S, YIN H P, et al. Crop classification method of UVA multispectral remote sensing based on deep semantic segmentation[J].Transactions of the Chinese Society for Agricultural Machinery,2021,52(3):185-192.

王启宏.民和县淤地坝遥感解译及其运行状况分析[J].中国水土保持,2023(2):54-58. WANG Q H. Remote sensing interpretation and operation of warping dams in Minhe County[J].Soil and Water Conservation in China,2023(2):54-58.

刘茜,易诗,李立,等.基于轻量级CNN-Transformer混合网络的梯田图像语义分割[J].农业工程学报,2023,39(13):171-181. LIU X, YI S, LI L, et al. Semantic segmentation of terrace image regions based on lightweight CNN-Transformer hybrid networks[J].Transactions of the Chinese Society of Agricultural Engineering,2023,39(13):171-181.

浏览量

573

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

海南屯昌砂质壤土橡胶林水土保持措施生态产品能值分析

黄土丘陵区不同水土保持措施坡面小区侵蚀性降雨标准

淮北平原砂姜黑土区典型作物根区土壤水分的来源及其量化

黄土坡面溶解性碳流失特征及其对水土保持措施的响应

基于径流小区实测的干热河谷土壤侵蚀荟萃分析