协同多源国产高分影像和面向对象方法的南方农作物遥感识别

doi:10.3864/j.issn.0578-1752.2023.13.004

中国农业科学 ›› 2023, Vol. 56 ›› Issue (13): 2474-2490.doi: 10.3864/j.issn.0578-1752.2023.13.004

• 耕作栽培·生理生化·农业信息技术 • 上一篇下一篇

协同多源国产高分影像和面向对象方法的南方农作物遥感识别

王佳玥¹(), 蔡志文², 王文静¹, 魏浩东³, 王聪¹(), 李泽萱¹, 李秀妮¹, 胡琼¹()

¹ 华中师范大学城市与环境科学学院，武汉 430079
² 华中农业大学资源与环境学院/华中农业大学宏观农业研究院，武汉 430070
³ 华中农业大学植物科学技术学院/华中农业大学宏观农业研究院，武汉 430070

收稿日期:2022-12-04 接受日期:2022-02-06 出版日期:2023-07-01 发布日期:2023-07-06
通信作者:
王聪，E-mail：wangcong@ccnu.edu.cn。
王聪，E-mail：wangcong@ccnu.edu.cn。
胡琼，E-mail：huqiong@ccnu.edu.cn
联系方式: 王佳玥，E-mail：wangjiayue@mails.ccnu.edu.cn。
基金资助:
湖北省自然科学基金面上项目(2022CFB377); 国家自然科学基金面上项目(42271399); 中国科协青年人才托举工程项目(2020QNRC001); 中央高校基本科研业务费资助(CCNU22QN018); 中央高校基本科研业务费资助(CCNU22JC013)

Integrating Multi-Source Gaofen Images and Object-Based Methods for Crop Type Identification in South China

WANG JiaYue¹(), CAI ZhiWen², WANG WenJing¹, WEI HaoDong³, WANG Cong¹(), LI ZeXuan¹, LI XiuNi¹, HU Qiong¹()

¹ College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079
² College of Resources and Environment/Macro Agriculture Research Institute, Huazhong Agricultural University, Wuhan 430070
³ College of Plant Science and Technology/Macro Agriculture Research Institute, Huazhong Agricultural University, Wuhan 430070

Received:2022-12-04 Accepted:2022-02-06 Published:2023-07-01 Online:2023-07-06

摘要/Abstract

摘要：

【目的】中国南方地区云雨频繁且农业景观破碎，是我国农作物遥感监测最具挑战的区域之一。我国自主研发的高分系列卫星具有高时空分辨率和高质量成像的特点。本研究挖掘多源高分系列卫星的时间和空间双重优势，实现多云雨及景观异质区作物精细化识别。【方法】基于国产高空间分辨率高分二号（GF-2）影像表征农田空间几何特征，协同中空间分辨率高分一号（GF-1）和高分六号（GF-6）加密影像观测时间序列，充分表征农作物光谱季相节律。通过构建光谱-时相-空间三维分类特征，基于随机森林进行农作物分类并计算不同特征的重要性。同时，设置不同影像组合和不同分类单元下的多种分类场景，进一步分析不同高分数据协同利用在农作物识别上的表现差异。【结果】基于GF-1、GF-2和GF-6影像和面向对象的农作物分类在湖北省潜江市研究区的总体精度为95.49%，Kappa系数为0.94；在枣阳市的总体精度为93.78%，Kappa系数为0.92。协同GF-2和GF-6进行农作物分类精度优于协同GF-2和GF-1。此外，基于GF-2进行面向对象的农作物分类效果优于面向像元，其中潜江总体精度提升了1.4%，枣阳提升了1.32%。相比GF-1和GF-2对应的光谱和空间特征，GF-6光谱波段对农作物遥感识别的贡献度最大，累计重要性得分占全部光谱波段的82%（潜江）、77%（枣阳）。其中GF-6新增的红边Ⅰ波段（B5）、红边Ⅱ波段（B6）、紫波段（B7）和黄波段（B8）4个光谱波段对作物识别的贡献度分别为47%（潜江）和33%（枣阳）。【结论】协同发挥不同国产高分数据各自光谱-时间-空间优势，不仅缓解了农业景观破碎导致的“混合像元”问题，同时一定程度上降低了多云多雨气候对农作物识别影响的不确定性，为我国南方地区农作物精准识别提供了巨大潜能。

关键词: 国产高分数据, 面向对象, 随机森林, 遥感识别, 作物分类

Abstract:

【Objective】 Due to frequent cloudy and rainy weather, it is challenging to map crop types over South China with fragmented agricultural landscapes. The Gaofen (GF) series satellites developed by China have high spatial-temporal resolution and good image quality. This study exploited the spatial and temporal advantages of multi-source GF images for fine crop classification in heterogeneous agricultural areas with frequent clouds and rain. 【Method】This study characterized the spatial geometry of agricultural fields based on GF-2 data with high spatial resolution, and cooperated with the encrypted observations from GF-1 and GF-6 time series to fully characterize the spectral seasonal variations of crops. By constructing three-dimensional classification features of spectrum-time-space, the crop classification based on random forest classifier were conducted, and the importance scores of different features were calculated. Furthermore, several classification scenarios were set based on different satellite combinations and different classification units, for further analyzing the performances of integrating different GF datasets on crop type mapping. 【Result】The overall accuracy of synergistic GF-1, GF-2 and GF-6 by object-oriented crop classification was 95.49% with Kappa of 0.94 in Qianjiang city; the overall accuracy in Zaoyang city was 93.78% with Kappa of 0.92. The accuracy of crop classification by integrating GF-2 and GF-6 was higher than that by GF-2 and GF-1. In addition, the object-oriented crop classification based on GF-2 outperformed the pixel-oriented one, in which the overall accuracy improved by 1.4% and 1.32% in Qianjiang and Zaoyang, respectively. Compared with the spectral and spatial features of GF-1 and GF-2, the GF-6 spectral bands had the largest contribution to crop type identification, and the cumulative importance score accounted for 82% (Qianjiang) and 77% (Zaoyang) of all spectral bands. Among them, the four new spectral bands of GF-6, namely, red-edge I band (B5), red-edge Ⅱ band (B6), purple band (B7) and yellow band (B8), accounted for 47% (Qianjiang) and 33% (Zaoyang) of all spectral bands for crop type identification. 【Conclusion】Integrating multi-source GF images by taking advantages of their spectral, spatial and temporal features could not only alleviate the "mixed pixel" problem caused by the fragmented agricultural landscape, but also reduce the uncertainty of crop type identification in cloudy and rainy areas, providing great potential for accurate crop mapping in South China.

Key words: GF data, object-oriented, random forest, remote sensing identification, crop classification

王佳玥, 蔡志文, 王文静, 魏浩东, 王聪, 李泽萱, 李秀妮, 胡琼. 协同多源国产高分影像和面向对象方法的南方农作物遥感识别[J]. 中国农业科学, 2023, 56(13): 2474-2490.

WANG JiaYue, CAI ZhiWen, WANG WenJing, WEI HaoDong, WANG Cong, LI ZeXuan, LI XiuNi, HU Qiong. Integrating Multi-Source Gaofen Images and Object-Based Methods for Crop Type Identification in South China[J]. Scientia Agricultura Sinica, 2023, 56(13): 2474-2490.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2023.13.004

https://www.chinaagrisci.com/CN/Y2023/V56/I13/2474

图/表 14

图1

图2

表1

表2

图3

图4

图5

图6

表3

表4

图7

图8

图9

图10

参考文献 55

[1]	唐华俊, 吴文斌, 杨鹏, 周清波, 陈仲新. 农作物空间格局遥感监测研究进展. 中国农业科学, 2010, 43(14): 2879-2888.
	TANG H J, WU W B, YANG P, ZHOU Q B, CHEN Z X. Recent progresses in monitoring crop spatial patterns by using remote sensing technologies. Scientia Agricultura Sinica, 2010, 43(14): 2879-2888. (in Chinese)
[2]	宋茜, 胡琼, 陆苗, 余强毅, 杨鹏, 史云, 段玉林, 吴文斌. 农作物空间分布遥感制图发展方向探讨. 中国农业资源与区划, 2020, 41(6): 57-65.
	SONG Q, HU Q, LU M, YU Q Y, YANG P, SHI Y, DUAN Y L, WU W B. Prospect of crop mapping. Chinese Journal of Agricultural Resources and Regional Planning, 2020, 41(6): 57-65. (in Chinese)
[3]	唐华俊. 农业遥感研究进展与展望. 农学学报, 2018, 8(1): 167-171.
	TANG H J. Progress and prospect of agricultural remote sensing research. Journal of Agriculture, 2018, 8(1): 167-171. (in Chinese)
[4]	HU Q, WU W B, SONG Q, LU M, CHEN D, YU Q Y, TANG H J. How do temporal and spectral features matter in crop classification in Heilongjiang Province, China?. Journal of Integrative Agriculture, 2017, 16(2): 324-336. doi: 10.1016/S2095-3119(15)61321-1
[5]	LIU Y F, XIAO D Q, YANG W T. An algorithm for early rice area mapping from satellite remote sensing data in southwestern Guangdong in China based on feature optimization and random Forest. Ecological Informatics, 2022, 72: 101853. doi: 10.1016/j.ecoinf.2022.101853
[6]	胡琼, 吴文斌, 宋茜, 余强毅, 杨鹏, 唐华俊. 农作物种植结构遥感提取研究进展. 中国农业科学, 2015, 48(10): 1900-1914. doi: 10.3864/j.issn.0578-1752.2015.10.004
	HU Q, WU W B, SONG Q, YU Q Y, YANG P, TANG H J. Recent progresses in research of crop patterns mapping by using remote sensing. Scientia Agricultura Sinica, 2015, 48(10): 1900-1914. (in Chinese) doi: 10.3864/j.issn.0578-1752.2015.10.004
[7]	HU Q, SULLA-MENASHE D, XU B D, YIN H, TANG H J, YANG P, WU W B. A phenology-based spectral and temporal feature selection method for crop mapping from satellite time series. International Journal of Applied Earth Observation and Geoinformation, 2019, 80: 218-229. doi: 10.1016/j.jag.2019.04.014
[8]	OZDARICI-OK A, OK A, SCHINDLER K. Mapping of agricultural crops from single high-resolution multispectral images—Data-driven smoothing vs.parcel-based smoothing. Remote Sensing, 2015, 7(5): 5611-5638. doi: 10.3390/rs70505611
[9]	LI M Y, ZHANG R, LUO H X, GU S W, QIN Z L. Crop mapping in the Sanjiang plain using an improved object-oriented method based on google earth engine and combined growth period attributes. Remote Sensing, 2022, 14(2): 273. doi: 10.3390/rs14020273
[10]	BLICKENSDÖRFER L, SCHWIEDER M, PFLUGMACHER D, NENDEL C, ERASMI S, HOSTERT P. Mapping of crop types and crop sequences with combined time series of Sentinel-1, Sentinel-2 and Landsat 8 data for Germany. Remote Sensing of Environment, 2022, 269: 112831. doi: 10.1016/j.rse.2021.112831
[11]	周珂, 柳乐, 张俨娜, 苗茹, 杨阳. GEE支持下的河南省冬小麦面积提取及长势监测. 中国农业科学, 2021, 54(11): 2302-2318. doi: 10.3864/j.issn.0578-1752.2021.11.005
	ZHOU K, LIU L, ZHANG Y N, MIAO R, YANG Y. Area extraction and growth monitoring of winter wheat in Henan Province supported by google earth engine. Scientia Agricultura Sinica, 2021, 54(11): 2302-2318. (in Chinese) doi: 10.3864/j.issn.0578-1752.2021.11.005
[12]	HU Q, MA Y X, XU B D, SONG Q, TANG H J, WU W B. Estimating sub-pixel soybean fraction from time-series MODIS data using an optimized geographically weighted regression model. Remote Sensing, 2018, 10(4): 491. doi: 10.3390/rs10040491
[13]	SONG X P, HUANG W L, HANSEN M C, POTAPOV P. An evaluation of Landsat, Sentinel-2, Sentinel-1 and MODIS data for crop type mapping. Science of Remote Sensing, 2021, 3: 100018. doi: 10.1016/j.srs.2021.100018
[14]	SKAKUN S, FRANCH B, VERMOTE E, ROGER J C, BECKER-RESHEF I, JUSTICE C, KUSSUL N. Early season large-area winter crop mapping using MODIS NDVI data, growing degree days information and a Gaussian mixture model. Remote Sensing of Environment, 2017, 195: 244-258. doi: 10.1016/j.rse.2017.04.026
[15]	WEI H D, HU Q, CAI Z W, YANG J Y, SONG Q, YIN G F, XU B D. An object- and topology-based analysis (OTBA) method for mapping rice-crayfish fields in South China. Remote Sensing, 2021, 13(22): 4666. doi: 10.3390/rs13224666
[16]	BELGIU M, CSILLIK O. Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sensing of Environment, 2018, 204: 509-523. doi: 10.1016/j.rse.2017.10.005
[17]	LIU L, XIAO X M, QIN Y W, WANG J, XU X L, HU Y M, QIAO Z. Mapping cropping intensity in China using time series Landsat and Sentinel-2 images and Google Earth Engine. Remote Sensing of Environment, 2020, 239: 111624. doi: 10.1016/j.rse.2019.111624
[18]	HAO P Y, TANG H J, CHEN Z X, YU L, WU M Q. High resolution crop intensity mapping using harmonized Landsat-8 and Sentinel-2 data. Journal of Integrative Agriculture, 2019, 18(12): 2883-2897. doi: 10.1016/S2095-3119(19)62599-2
[19]	HU Q, YIN H, FRIEDL M A, YOU L Z, LI Z L, TANG H J, WU W B. Integrating coarse-resolution images and agricultural statistics to generate sub-pixel crop type maps and reconciled area estimates. Remote Sensing of Environment, 2021, 258: 112365. doi: 10.1016/j.rse.2021.112365
[20]	杨靖雅, 胡琼, 魏浩东, 蔡志文, 张馨予, 宋茜, 徐保东. 基于Sentinel-1/2数据的中国南方单双季稻识别结果一致性分析. 中国农业科学, 2022, 55(16): 3093-3109. doi: 10.3864/j.issn.0578-1752.2022.16.003
	YANG J Y, HU Q, WEI H D, CAI Z W, ZHANG X Y, SONG Q, XU B D. Consistency analysis of classification results for single and double cropping rice in Southern China based on sentinel-1/2 imagery. Scientia Agricultura Sinica, 2022, 55(16): 3093-3109. (in Chinese) doi: 10.3864/j.issn.0578-1752.2022.16.003
[21]	TAO W C, XIE Z X, ZHANG Y, LI J Y, XUAN F, HUANG J X, LI X C, SU W, YIN D Q. Corn residue covered area mapping with a deep learning method using Chinese GF-1 B/D high resolution remote sensing images. Remote Sensing, 2021, 13(15): 2903. doi: 10.3390/rs13152903
[22]	XIA T, HE Z, CAI Z W, WANG C, WANG W J, WANG J Y, HU Q, SONG Q. Exploring the potential of Chinese GF-6 images for crop mapping in regions with complex agricultural landscapes. International Journal of Applied Earth Observation and Geoinformation, 2022, 107: 102702. doi: 10.1016/j.jag.2022.102702
[23]	FAN J L, ZHANG X Y, ZHAO C L, QIN Z H, DE VROEY M, DEFOURNY P. Evaluation of crop type classification with different high resolution satellite data sources. Remote Sensing, 2021, 13(5): 911. doi: 10.3390/rs13050911
[24]	WANG L J, WANG J Y, LIU Z Z, ZHU J, QIN F. Evaluation of a deep-learning model for multispectral remote sensing of land use and crop classification. The Crop Journal, 2022, 10(5): 1435-1451. doi: 10.1016/j.cj.2022.01.009
[25]	WU M Q, HUANG W J, NIU Z, WANG Y, WANG C Y, LI W, HAO P Y, YU B. Fine crop mapping by combining high spectral and high spatial resolution remote sensing data in complex heterogeneous areas. Computers and Electronics in Agriculture, 2017, 139: 1-9. doi: 10.1016/j.compag.2017.05.003
[26]	WU M Q, ZHANG X Y, HUANG W J, NIU Z, WANG C Y, LI W, HAO P Y. Reconstruction of daily 30 m data from HJ CCD, GF-1 WFV, landsat, and MODIS data for crop monitoring. Remote Sensing, 2015, 7(12): 16293-16314. doi: 10.3390/rs71215826
[27]	郑利娟. 基于高分一/六号卫星影像特征的农作物分类研究[D]. 北京: 中国科学院大学, 2017.
	ZHENG L J. Crop classification using multi-features of Chinese Gaofen-1/6 satellite remote sensing images[D]. Beijing: University of Chinese Academy of Sciences, 2017. (in Chinese)
[28]	童旭东. 中国高分辨率对地观测系统重大专项建设进展. 遥感学报, 2016, 20(5): 775-780.
	TONG X D. Development of China high-resolution earth observation system. Journal of Remote Sensing, 2016, 20(5): 775-780. (in Chinese)
[29]	蔡志文, 何真, 王文静, 杨靖雅, 魏浩东, 王聪, 徐保东. 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, 2022, 26(7): 1368-1382.
	CAI Z W, HE Z, WANG W J, YANG J Y, WEI H D, WANG C, XU B D. Mapping cropland at metric resolution using the spatiotemporal information from multi-source GF satellite data. National Remote Sensing Bulletin, 2022, 26(7): 1368-1382. (in Chinese) doi: 10.11834/jrs.20221069
[30]	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. 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. Chinese Journal of Agricultural Resources and Regional Planning, 2021, 42(7): 254-268. (in Chinese)
[31]	SONG Q, ZHOU Q B, WU W B, HU Q, LU M, LIU S B. Mapping regional cropping patterns by using GF-1 WFV sensor data. Journal of Integrative Agriculture, 2017, 16(2): 337-347. doi: 10.1016/S2095-3119(16)61392-8
[32]	何真, 胡洁, 蔡志文, 王文静, 胡琼. 协同多时相国产GF-1和GF-6卫星影像的艾草遥感识别. 农业工程学报, 2022, 38(1): 186-195.
	HE Z, HU J, CAI Z W, WANG W J, HU Q. Remote sensing identification for Artemisia argyi integrating multi-temporal GF-1 and GF-6 images. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(1): 186-195. (in Chinese)
[33]	JIANG X Q, FANG S H, HUANG X A, LIU Y H, GUO L L. Rice mapping and growth monitoring based on time series GF-6 images and red-edge bands. Remote Sensing, 2021, 13(4): 579. doi: 10.3390/rs13040579
[34]	KANG Y P, MENG Q Y, LIU M, ZOU Y F, WANG X M. Crop classification based on red edge features analysis of GF-6 WFV data. Sensors, 2021, 21(13): 4328. doi: 10.3390/s21134328
[35]	KANG Y P, HU X L, MENG Q Y, ZOU Y F, ZHANG L L, LIU M A, ZHAO M F. Land cover and crop classification based on red edge indices features of GF-6 WFV time series data. Remote Sensing, 2021, 13(22): 4522. doi: 10.3390/rs13224522
[36]	YANG L B, WANG L M, ABUBAKAR G A, HUANG J F. High-resolution rice mapping based on SNIC segmentation and multi-source remote sensing images. Remote Sensing, 2021, 13(6): 1148. doi: 10.3390/rs13061148
[37]	CAI Z W, HU Q, ZHANG X Y, YANG J Y, WEI H D, HE Z, SONG Q, WANG C, YIN G F, XU B D. An adaptive image segmentation method with automatic selection of optimal scale for extracting cropland parcels in smallholder farming systems. Remote Sensing, 2022, 14(13): 3067. doi: 10.3390/rs14133067
[38]	XU L, MING D P, ZHOU W, BAO H Q, CHEN Y Y, LING X A. Farmland extraction from high spatial resolution remote sensing images based on stratified scale pre-estimation. Remote Sensing, 2019, 11(2): 108. doi: 10.3390/rs11020108
[39]	SONG Q, HU Q, ZHOU Q B, HOVIS C, XIANG M T, TANG H J, WU W B. In-season crop mapping with GF-1/WFV data by combining object-based image analysis and random forest. Remote Sensing, 2017, 9(11): 1184. doi: 10.3390/rs9111184
[40]	ZHANG L, LIU Z, REN T W, LIU D Y, MA Z, TONG L A, ZHANG C, ZHOU T Y, ZHANG X D, LI S M. Identification of seed maize fields with high spatial resolution and multiple spectral remote sensing using random forest classifier. Remote Sensing, 2020, 12(3): 362. doi: 10.3390/rs12030362
[41]	张超, 金虹杉, 刘哲, 李智晓, 宁明宇, 孙海艳. 基于GF遥感数据纹理分析识别制种玉米. 农业工程学报, 2016, 32(21): 183-188.
	ZHANG C, JIN H S, LIU Z, LI Z X, NING M Y, SUN H Y. Seed maize identification based on texture analysis of GF remote sensing data. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(21): 183-188. (in Chinese)
[42]	LUO H X, LI M F, DAI S P, LI H L, LI Y P, HU Y Y, ZHENG Q A, YU X A, FANG J H. Combinations of feature selection and machine learning algorithms for object-oriented betel palms and mango plantations classification based on Gaofen-2 imagery. Remote Sensing, 2022, 14(7): 1757. doi: 10.3390/rs14071757
[43]	SCHEFFLER D, HOLLSTEIN A, DIEDRICH H, SEGL K, HOSTERT P. AROSICS: An automated and robust open-source image co-registration software for multi-sensor satellite data. Remote Sensing, 2017, 9(7): 676. doi: 10.3390/rs9070676
[44]	宋茜. 基于GF-1/WFV和面向对象的农作物种植结构提取方法研究[D]. 北京: 中国农业科学院, 2016.
	SONG Q. Object-based image analysis with machine learning algorithms for cropping pattern mapping using GF-1/WFV imagery[D]. Beijing: Chinese Academy of Agricultural Sciences, 2016. (in Chinese)
[45]	苏伟, 李京, 陈云浩, 张锦水, 胡德勇, 刘翠敏. 基于多尺度影像分割的面向对象城市土地覆被分类研究——以马来西亚吉隆坡市城市中心区为例. 遥感学报, 2007, 11(4): 521-530.
	SU W, LI J, CHEN Y H, ZHANG J S, HU D Y, LIU C M. Object-oriented urban land-cover classification of multi-scale image segmentation method—— a case study in Kuala Lumpur city center Malaysia. Journal of Remote Sensing, 2007, 11(4): 521-530. (in Chinese)
[46]	佃袁勇, 方圣辉, 姚崇怀. 多尺度分割的高分辨率遥感影像变化检测. 遥感学报, 2016, 20(1): 129-137.
	DIAN Y Y, FANG S H, YAO C H. Change detection for high- resolution images using multilevel segment method. Journal of Remote Sensing, 2016, 20(1): 129-137. (in Chinese)
[47]	YANG L B, MANSARAY L, HUANG J F, WANG L M. Optimal segmentation scale parameter, feature subset and classification algorithm for geographic object-based crop recognition using multisource satellite imagery. Remote Sensing, 2019, 11(5): 514. doi: 10.3390/rs11050514
[48]	SHEN Y, CHEN J Y, XIAO L, PAN D L. Optimizing multiscale segmentation with local spectral heterogeneity measure for high resolution remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 157: 13-25. doi: 10.1016/j.isprsjprs.2019.08.014
[49]	马燕妮, 明冬萍, 杨海平. 面向对象影像多尺度分割最大异质性参数估计. 遥感学报, 2017, 21(4): 566-578.
	MA Y N, MING D P, YANG H P. Scale estimation of object-oriented image analysis based on spectral-spatial statistics. Journal of Remote Sensing, 2017, 21(4): 566-578. (in Chinese)
[50]	DRĂGUŢ L, CSILLIK O, EISANK C, TIEDE D. Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 88: 119-127. doi: 10.1016/j.isprsjprs.2013.11.018
[51]	BREIMAN L. Random forests. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[52]	DOS SANTOS LUCIANO A C, PICOLI M C A, ROCHA J V, DUFT D G, LAMPARELLI R A C, LEAL M R L V, LE MAIRE G. A generalized space-time OBIA classification scheme to map sugarcane areas at regional scale, using Landsat images time-series and the random forest algorithm. International Journal of Applied Earth Observation and Geoinformation, 2019, 80: 127-136. doi: 10.1016/j.jag.2019.04.013
[53]	HU Q, WU W B, SONG Q, YU Q Y, LU M, YANG P, TANG H J, LONG Y Q. Extending the pairwise separability index for multicrop identification using time-series MODIS images. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(11): 6349-6361. doi: 10.1109/TGRS.2016.2581210
[54]	CONGALTON R G. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 1991, 37(1): 35-46. doi: 10.1016/0034-4257(91)90048-B
[55]	ZURQANI H A, POST C J, MIKHAILOVA E A, COPE M P, ALLEN J S, LYTLE B A. Evaluating the integrity of forested riparian buffers over a large area using LiDAR data and Google Earth Engine. Scientific Reports, 2020, 10: 14096. doi: 10.1038/s41598-020-69743-z pmid: 32839474

参数Parameter		GF-2 PMS	GF-1 WFV	GF-6 WFV
光谱范围 Spectral range (μm)	全色Panchromatic band	0.45-0.90	—	—
	蓝Blue（B₁）	0.45-0.52	0.45-0.52	0.45-0.52
	绿Green（B₂）	0.52-0.59	0.52-0.59	0.52-0.59
	红Red（B₃）	0.63-0.69	0.63-0.69	0.63-0.69
	近红外NIR（B₄）	0.77-0.89	0.77-0.89	0.77-0.89
	红边 I Red-edge I（B₅）	—	—	0.69-0.73
	红边Ⅱ Red-edge Ⅱ（B₆）	—	—	0.73-0.77
	紫Purple（B₇）	—	—	0.40-0.45
	黄Yellow（B₈）	—	—	0.59-0.63
幅宽Width (km)		45	800
空间分辨率Spatial resolution (m)		1（全色PAN）/4（多光谱MSS）	16
重访周期 Revisit cycle (d)		5	2（GF-1和GF-6组网运行 Joint operation with GF-1 and GF-6 satellites）

方案 Scenarios	数据源与分类单元 Data source and classification units	光谱特征 Spectral features GF-1/GF-6	空间特征 Spatial features GF-2	影像数量 Number of images			特征总数 Number of features
方案 Scenarios	数据源与分类单元 Data source and classification units	光谱特征 Spectral features GF-1/GF-6	空间特征 Spatial features GF-2		潜江 Qianjiang	枣阳 Zaoyang	潜江 Qianjiang	枣阳 Zaoyang
1 试验组 Experimental group	GF-2（面向对象 Object-oriented） &GF-1+GF-6	蓝、绿、红、近红外、红边Ⅰ、红边Ⅱ、紫、黄 Blue, Green, Red, NIR, Red-edge I, Red-edge Ⅱ, Purple, Yellow	范围、方向、最大边长、最小边长 Extent, Orientation, Major length, Minor length	GF-1	3	8	56	116
				GF-6	5	10
				GF-2	1	1
2 对照组 Control group	GF-2（面向对象 Object-oriented） &GF-1	蓝、绿、红、近红外 Blue, Green, Red, NIR	范围、方向、最大边长、最小边长 Extent, Orientation, Major length, Minor length	GF-1	3	8	16	36
3 对照组 Control group	GF-2（面向对象 Object-oriented） &GF-6	蓝、绿、红、近红外、红边Ⅰ、红边Ⅱ、紫，黄 Blue, Green, Red, NIR, Red-edge I, Red-edge Ⅱ, Purple, Yellow	范围、方向、最大边长、最小边长 Extent, Orientation, Major length, Minor length	GF-6	5	10	44	84
3 对照组 Control group	GF-2（面向对象 Object-oriented） &GF-6			GF-2	1	1	44	84
4 对照组 Control group	GF-1+GF-6 （面向像元 Pixel-oriented）	蓝、绿、红、近红外、红边Ⅰ、红边Ⅱ、紫、黄 Blue, Green, Red, NIR, Red-edge I, Red-edge Ⅱ, Purple, Yellow	/	GF-1	3	8	52	112
4 对照组 Control group	GF-1+GF-6 （面向像元 Pixel-oriented）		/	GF-6	5	10	52	112

	方案1 Scenario 1 GF-2（面向对象Object-oriented） &GF-1+GF-6			方案2 Scenario 2 GF-2（面向对象Object-oriented） &GF-1			方案3 Scenario 3 GF-2（面向对象Object-oriented） &GF-6			方案4 Scenario 4 GF-1+GF-6 （面向像元Pixel-oriented）
	PA (%)	UA (%)	F1-score	PA (%)	UA (%)	F1-score	PA (%)	UA (%)	F1-score	PA (%)	UA (%)
小麦 Wheat	96.20	98.70	0.97	92.40	92.40	0.92	96.30	97.43	0.95	97.50	98.73
油菜 Rape	98.77	97.56	0.97	96.29	95.12	0.96	97.53	97.53	0.96	98.79	97.61
早稻 Early rice	98.57	94.52.	0.98	92.85	86.66	0.91	97.14	94.44	0.96	98.57	93.24
虾稻Rice-crayfish	98.79	92.13	0.92	90.36	91.46	0.88	97.59	90.00	0.91	97.59	88.04
其他作物 Other crops	86.00	91.49	0.84	74.00	75.51	0.77	86.00	89.58	0.81	75.47	90.90
总体精度OA (%)	95.49			90.12			94.42			94.09
Kappa	0.94			0.88			0.93			0.93

	方案1 Scenario 1 GF-2（面向对象Object-oriented） &GF-1+GF-6			方案2 Scenario 2 GF-2（面向对象Object-oriented） &GF-1			方案3 Scenario 3 GF-2（面向对象Object-oriented） &GF-6			方案4 Scenario 4 GF-1+GF-6 （面向像元Pixel-oriented）
	PA (%)	UA (%)	F1-score	PA (%)	UA (%)	F1-score	PA (%)	UA (%)	F1-score	PA (%)	UA (%)
小麦 Wheat	94.85	98.92	0.97	91.75	96.73	0.94	92.78	98.90	0.95	93.00	96.87
早稻 Early rice	92.86	85.53	0.89	88.57	79.48	0.84	91.42	85.33	0.88	90.24	85.05
其他作物 Other crops	80.36	83.33	0.82	73.21	78.84	0.76	82.14	79.31	0.80	77.04	79.66
总体精度OA (%)	93.78			91.35			92.97			92.46
Kappa	0.92			0.89			0.91			0.90

协同多源国产高分影像和面向对象方法的南方农作物遥感识别

Integrating Multi-Source Gaofen Images and Object-Based Methods for Crop Type Identification in South China

RichHTML

PDF

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 55

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	黄翀,侯相君. 基于Bi-LSTM模型的时间序列遥感作物分类研究[J]. 中国农业科学, 2022, 55(21): 4144-4157.
[2]	吴俊,郭大千,李果,郭熙,钟亮,朱青,国佳欣,叶英聪. 基于CARS-BPNN的江西省土壤有机碳含量高光谱预测[J]. 中国农业科学, 2022, 55(19): 3738-3750.
[3]	郭灿,岳晓凤,白艺珍,张良晓,张奇,李培武. 花生黄曲霉毒素平衡取样-随机森林风险预警模型的应用研究[J]. 中国农业科学, 2022, 55(17): 3426-3436.
[4]	申哲,张认连,龙怀玉,徐爱国. 基于机器学习方法的宁夏南部土壤质地空间分布研究[J]. 中国农业科学, 2022, 55(15): 2961-2972.
[5]	周珂, 柳乐, 张俨娜, 苗茹, 杨阳. GEE支持下的河南省冬小麦面积提取及长势监测[J]. 中国农业科学, 2021, 54(11): 2302-2318.
[6]	张振华,丁建丽,王敬哲,葛翔宇,王瑾杰,田美玲,赵启东. 集成土壤-环境关系与机器学习的干旱区土壤属性数字制图[J]. 中国农业科学, 2020, 53(3): 563-573.
[7]	夏树凤,王凡,王龙俊,周琴,蔡剑,王笑,黄梅,戴廷波,姜东. 江苏省小麦籽粒蛋白质达标弱筋小麦的适生性分析与评价[J]. 中国农业科学, 2020, 53(24): 4992-5004.
[8]	申哲,张认连,龙怀玉,王转,朱国龙,石乾雄,喻科凡,徐爱国. 基于3种空间预测方法的黄土区土壤颗粒组成空间分布研究—以宁夏海原县为例[J]. 中国农业科学, 2020, 53(18): 3716-3728.
[9]	姬旭升,李旭,万泽福,姚霞,朱艳,程涛. 基于高空间分辨率卫星影像的新疆阿拉尔市棉花与枣树分类[J]. 中国农业科学, 2019, 52(6): 997-1008.
[10]	邱鹏勋, 汪小钦, 茶明星, 李娅丽. 基于TWDTW的时间序列GF-1 WFV农作物分类[J]. 中国农业科学, 2019, 52(17): 2951-2961.
[11]	张春兰，杨贵军，李贺丽，汤伏全，刘畅，张丽妍. 基于随机森林算法的冬小麦叶面积指数遥感反演研究[J]. 中国农业科学, 2018, 51(5): 855-867.
[12]	王飞,杨胜天,魏阳,杨晓东,丁建丽. 基于RF和SGT算法的子区优先建模对绿洲尺度土壤盐度预测精度的影响[J]. 中国农业科学, 2018, 51(24): 4659-4676.
[13]	贺英，邓磊，毛智慧，孙杰. 基于数码相机的玉米冠层SPAD遥感估算[J]. 中国农业科学, 2018, 51(15): 2886-2897.
[14]	刘焕军，于胜男，张新乐，郭栋，殷继先. 一年一季农作物遥感分类的时效性分析[J]. 中国农业科学, 2017, 50(5): 830-839.
[15]	刘亚秋，陈红艳，王瑞燕，常春艳，陈哲. 基于可见/近红外光谱的黄河口区土壤盐分及其主要离子的定量分析[J]. 中国农业科学, 2016, 49(10): 1925-1935.