Identification of Rice in Southern Mountainous Area Based on Object‐Oriented and Machine Learning Methods

doi:10.15933/j.cnki.1004-3268.2025.04.015

Abstract

Abstract: The phenology information of rice varies with terrain.In view of the cloudy and rainy conditions and complex terrain in the southern mountainous areas，it is of certain research value to find a remote sensing identification method for rice. With Yongshun County，a typical mountainous terrain in Hunan Province，as the research area，combined with Sentinel‐1 SAR and Sentinel‐2 MSI data，the time series curve was generated by the images of four key phenology periods of rice to grasp the growth trend of rice.Firstly，the object‐oriented method was used to segment the images of transplanting period and harvesting period；secondly，the feature variables optimized by the feature space optimization algorithm（FSO）were input into four models for classification such as random forest（RF）；finally，the results were compared. Otherwise，according to the transplanting order，the rice samples were divided into early moving and late moving samples，the images of transplanting period and harvesting period were reclassified to explore the influence of rice transplanting time on the classification of the two images.The results showed that，compared to imagery from the transplanting stage，imagery from the harvesting stage offered better classification accuracy and was more suitable for rice mapping.The object‐oriented FSO‐RF model achieved the best classification results for imagery during the harvest period，with an overall accuracy of 93.19% and a kappa coefficient of 0. 901. The time of rice transplanting had little effect on the image classification at harvest stage，but had a great influence on the image classification at transplanting stage. The reason was that the earliest transplanted rice was easy to be similar to the spectral characteristics and texture characteristics of some dry land crops and woodlands，and there was a phenomenon of confusion and mis‐classification. In order to improve the recognition accuracy of the image during the transplanting period，it is necessary to improve the time resolution of the image，add more texture features or mask the ground objects.

Key words: Rice, Sentinel‐1/2, Object‐oriented, Multi‐feature optimization, Random forest, Transplanting period, Harvest period, Identification

摘要： 水稻的物候信息随地形的差异而不同，针对南方山区多云多雨、地形复杂的情况，寻找一种合适的水稻识别方法具有一定的研究价值。以湖南省典型山地地形的永顺县为研究区，协同Sentinel-1 SAR和Sentinel-2 MSI数据，结合水稻4个关键物候期影像生成时间序列曲线以掌握水稻生长趋势，使用面向对象方法对移栽期和收割期影像分割，将经过样本特征空间优化算法（FSO）优选的特征变量输入到随机森林（RF）等4种模型中进行分类，并对比结果；之后将水稻样本按移栽先后分为早移、晚移样本，对移栽期和收割期影像重新分类，分析水稻移栽的早晚对该两景影像分类的影响。结果表明，与移栽期影像相比，收割期影像分类精度更好，更适合水稻制图；利用面向对象的FSO-RF模型对收割期影像分类的效果最好，总体精度为93.19%，Kappa系数为0.901。水稻移栽的早晚对收割期影像的分类几乎没有影响，对移栽期影像分类的影响较大，原因是最早移栽的水稻易与部分旱地作物、林地的光谱特征和纹理特征相似，出现混淆错分现象。提高移栽期影像的识别精度，需使用其他指数、纹理特征或进行地物掩膜。

关键词: 水稻, Sentinel-1/2, 面向对象, 多特征优选, 随机森林, 移栽期, 收割期, 识别

CLC Number:

S127
S511

WANG Yingying, DUAN Liangxia, ZHAO Yining, SUN Guangrui, YANG Lihong, ZHOU Qing, XIE Hongxia. Identification of Rice in Southern Mountainous Area Based on Object‐Oriented and Machine Learning Methods[J]. Journal of Henan Agricultural Sciences, 2025, 54(4): 144-154.

王莹莹, 段良霞, 赵怡凝, 孙广睿, 杨丽红, 周清, 谢红霞. 基于面向对象与机器学习融合的南方山区水稻识别研究[J]. 河南农业科学, 2025, 54(4): 144-154.

Figures/Tables 11

References

［1］谭深，吴炳方，张鑫.基于Google Earth Engine与多源遥感数据的海南水稻分类研究［J］.地球信息科学学报，2019，21（6）：937‐947.
TAN S，WU B F，ZHANG X.Mapping paddy rice in the Hainan Province using both Google Earth Engine and remote sensing images［J］.Journal of Geo‐information Science，2019，21（6）：937‐947.

［2］张焕雪，李强子，文宁，等.农作物种植面积遥感抽样调查的误差影响因素分析［J］.农业工程学报，2014，30（13）：176‐184.

ZHANG H X，LI Q Z，WEN N，et al.Analysis on estimation accuracy of crop area caused by spatial sampling factors based on remote sensing data［J］.Transactions of the Chinese Society of Agricultural Engineering，2014，30（13）：176‐184.

［3］陶莉，胡召玲.利用Sentinel-2A数据提取长江中下游丘陵地带农作物种植信息［J］.测绘通报，2021（7）：39‐43.

TAO L，HU Z L.Crop planting structure identification based on Sentinel‐2A data in hilly region of middle and lower reaches of Yangtze River［J］.Bulletin of Surveying and Mapping，2021（7）：39‐43.

［4］贾坤，李强子.农作物遥感分类特征变量选择研究现状与展望［J］.资源科学，2013，35（12）：2507‐2516.

JIA K，LI Q Z.Review of features selection in crop classification using remote sensing data［J］.Bulletin of Surveying and Mapping，2013，35（12）：2507‐2516.

［5］DE CASTRO FILHO H C，DE CARVALHO JÚNIOR O A，FERREIRA DE CARVALHO O L，et al.Rice crop detection using LSTM，Bi ‐LSTM，and machine learning models from Sentinel‐1 time series［J］.Remote Sensing，2020，12（16）：2655.

［6］ORYNBAIKYZY A，GESSNER U，CONRAD C.Crop type classification using a combination of optical and radar remote sensing data：A review［J］.International Journal of Remote Sensing，2019，40（17）：6553‐6595.

［7］YANG M，GUO B，WANG J. A novel and robust method for large‐scale single‐season rice mapping based on phenology and statistical data［J］.ISPRS Journal of Photogrammetry and Remote Sensing，2024，213：14‐32.

［8］郭交，朱琳，靳标.基于Sentinel-1和Sentinel-2数据融合的农作物分类［J］.农业机械学报，2018，49（4）：192‐198.

GUO J，ZHU L，JIN B.Crop classification based on data fusion of Sentinel‐1 and Sentinel‐2［J］.Transactions of the Chinese Society for Agricultural Machinery，2018，49（4）：192‐198.

［9］GIBRIL M B A，BAKAR S A，YAO K，et al.Fusion of RADARSAT‐2 and multi‐spectral optical remote sensing data for LULC extraction in a tropical agricultural area［J］.Geocarto International，2017，32（7）：735‐748.

［10］何泽，李世华.水稻雷达遥感监测研究进展［J］.遥感学报，2023，27（10）：2363‐2382.

HE Z，LI S H.Research progress on radar remote sensing for rice growth monitoring［J］.National Remote Sensing Bulletin，2023，27（10）：2363‐2382.

［11］YE Z X，YANG K L，LIN Y W，et al.A comparison between pixel‐based deep learning and object‐based image analysis（OBIA） for individual detection of cabbage plants based on UAV visible‐light images［J］.Computers and Electronics in Agriculture，2023，209：107822.

［12］XIAO W，XU S C，HE T T.Mapping paddy rice with Sentinel‐1/2 and phenology，object‐based algorithm：A implementation in Hangjiahu plain in China using GEE platform［J］.Remote Sensing，2021，13（5）：990.

［13］XIAO X M，BOLES S，LIU J Y，et al.Mapping paddy rice agriculture in Southern China using multi‐temporal MODIS images［J］.Remote Sensing of Environment，2005，95：480‐492.

［14］DONG J W，XIAO X M，MENARGUEZ M A，et al.Mapping paddy rice planting area in northeastern Asia with Landsat 8 images，phenology‐based algorithm and Google Earth Engine［J］.Remote Sensing of Environment，2016，185：142‐154.

［15］于飞，吕争，隋正伟，等. 基于特征优选的多时相SAR 数据水稻信息提取方法［J］.农业机械学报，2023，54（3）：259‐265，327.

YU F，LV Z，SUI Z W，et al. Extraction of rice information using multi‐temporal SAR data based on feature optimization［J］.Transactions of the Chinese Society for Agricultural Machinery，2023，54（3）：259‐265，327. ［16］刘通，任鸿瑞.GEE平台下利用物候特征进行面向对象的水稻种植分布提取［J］.农业工程学报，2022，38（12）：189‐196.

LIU T，REN H R. Object‐oriented extraction of paddy rice planting areas using phenological features from the GEE platform［J］. Transactions of the Chinese Society of Agricultural Engineering，2022，38（12）：189‐196.

［17］张卫春.基于Sentinel-2数据的低山丘陵区水稻种植面积监测［D］.重庆：西南大学，2020.

ZHANG W C. Mapping rice paddy based on machine learning with Sentinel‐2 multi‐temporal data［D］.Chongqing：Southwestern University，2020.

［18］桑国庆，唐志光，毛克彪，等.基于GEE云平台与Sentinel数据的高分辨率水稻种植范围提取：以湖南省为例［J］.作物学报，2022，48（9）：2409‐2420.

SANG G Q，TANG Z G，MAO K B，et al.High‐resolution paddy rice mapping using Sentinel data based on GEE platform：A case study of Hunan Province，China［J］. Acta Agronomica Sinica，2022，48 （9）：2409‐2420.

［19］张征云，江文渊，张彦敏，等.基于哨兵SAR数据和多光谱数据的水稻识别研究［J］.生态与农村环境报，2023，39（4）：556‐564.

ZHANG Z Y，JIANG W Y，ZHANG Y M，et al.Research on rice area extraction based on Sentinel SAR data and multi‐spectral data［J］.Journal of Ecology and Rural Environment，2023，39（4）：556‐564.

［20］范莉，王妍，祝好，等.多种光谱指数联合地形特征对复杂地形区主要粮食作物种植面积的遥感识别［J］.中国农业气象，2023，44（9）：845‐856.

FAN L，WANG Y，ZHU H，et al.Remote sensing for the planting area of major grain crops in complex terrain regions by integrating multiple spectral indices with topographic features［J］.Chinese Journal of Agrometeorology，2023，44（9）：845‐856.

［21］翟鹏飞，李世华，胡月明.协同光学与雷达遥感数据的面向对象土地覆盖变化检测［J］. 农业工程学报，2021，37（23）：216‐224.

ZHAI P F，LI S H，HU M Y.Object‐oriented land cover change detection combining optical and radar remote sensing data［J］.Transactions of the Chinese Society of Agricultural Engineering，2021，37（23）：216‐224.

［22］HAN J C，ZHANG Z，LUO Y C，et al.Annual paddy rice planting area and cropping intensity datasets and their dynamics in the Asian monsoon region from 2000 to 2020［J］.Agricultural Systems，2022，200：103437.

［23］郑紫瑞，赵辉杰，位盼盼，等.集成多源遥感数据与生育期时序光谱特征的水稻种植面积提取［J］.河南农业科学，2023，52（10）：153‐161.

ZHENG Z R，ZHAO H J，WEI P P，er al.Integration of multi‐source remote sensing data and temporal spectral features of growth stages for rice planting area extraction［J］.Journal of Henan Agricultural Sciences，2023，52（10）：153‐161.

［24］YIN Q，LIU M，CHENG J，et al.Mapping paddy rice planting area in northeastern China using spatiotemporal data fusion and phenology‐based method［J］.Remote Sensing，2019，11（14）：1699.

［25］姚园，毋亭，李一凡，等.基于水稻物候参数及面向对象算法的稻田识别［J］.农业工程学报，2024，40（11）：150‐158.

YAO Y，WU T，LI Y F，et al.Paddy field identification using rice phenological parameters and object‐oriented algorithm［J］.Transactions of the Chinese Society of Agricultural Engineering，2024，40（11）：150‐158.

［26］张昊，高小红，史飞飞，等.基于Sentinel-2 MSI与Sentinel-1 SAR相结合的黄土高原西部撂荒地提取：以青海民和县为例［J］.自然资源遥感，2022，34（4）：144‐154.

ZHANG H，GAO X H，SHI F F，et al.Sentinel‐2 MSI and Sentinel‐1 SAR based information extraction of abandoned land in the western Loess Plateau：A case study of Minhe County in Qinghai［J］.Remote Sensing for Natural Resources，2022，34（4）：144‐154.

［27］VELOSO A，MERMOZ S，BOUVET A，et al.Understanding the temporal behavior of crops using Sentinel‐1 and Sentinel‐2‐like data for agricultural applications［J］.Remote Sensing of Environment，2017，199：415‐426.

［28］BREIMAN L. Random forests［J］.Machine Learning，2001，45：5‐32.

［29］王斌，何丙辉，林娜，等. 基于随机森林特征选择的茶园遥感提取［J］.吉林大学学报（工学版），2022，52（7）：1719‐1732.

WANG B，HE B H，LIN N，et al.Tea plantation remote sensing extraction based on random forest feature selection［J］.Journal of Jilin University（Engineering and Technology Edition），2022，52（7）：1719‐1732.

［30］陈映彤.多时相遥感影像的湖南省醴陵市水稻生长期以及面积提取［D］.广州：华南农业大学，2018.

CHEN Y T. Extraction of paddy rice growing period and cropping area in Liling City，Hunan Province using multi‐temporal remote sensing images［D］.Guangzhou：South China Agricultural University，2018.

［31］任鸿瑞，张悦琦，何奇瑾，等.基于FY-3 MERSI遥感数据的水稻种植分布提取［J］.光谱学与光谱分析，2023，43（5）：1606‐1611.

REN H R，ZHANG Y Q，HE Q J，et al.Extraction of paddy rice planting area based on multi‐temporal FY‐3 MERSI remote sensing images［J］.Spectroscopy and Spectral Analysis，2023，43（5）：1606‐1611.

［32］滕文秀，王妮，施慧慧，等.结合面向对象和深度特征的高分影像树种分类［J］.测绘通报，2019（4）：38‐42.

TENG W X，WANG N，SHI H H，et al.Tree species classification of high resolution image combining with object‐oriented and deep feature［J］.Bulletin of Surveying and Mapping，2019（4）：38‐42.

［33］王佳玥，蔡志文，王文静，等.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 J Y，CAI Z W，WANG W J，et al.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.

［34］闫明，庞勇，何云玲，等.基于GEE云平台和Sentinel-2 数据的普洱市森林覆盖制图［J］.遥感技术与应用，2023，38（2）：432‐442.

YAN M，PANG Y，HE Y L，et al.Remote sensing based land cover classification of Pu'er City using GEE cloud platform and Sentinel‐2 data［J］.Remote Sensing Technology and Application，2023，38（2）：432‐442.

[1]	CAI Yumeng, WANG Ying, HE Fei, LIU Yanqing, LIU Jingyan, GUO Yanli, SUN Yue, SU Jingping, WANG Shengjun, LI Junling. Cloning and Function Analysis of Rice Sucrose Transporter OsSUT4 Gene [J]. Journal of Henan Agricultural Sciences, 2025, 54(3): 1-7.
[2]	LIU Haolin, SHEN Wenjuan, GAO Yu, QI Jingyi, LIU Hairui, GUAN Ruijie, MA Yu, ZHANG Tianchang, ZHANG Yinxia. Distribution of Rice Blast Resistance Genes Pita and Pikm in Japonica Rice Germplasm Resources and Their Relationship with Rice Blast Resistance [J]. Journal of Henan Agricultural Sciences, 2025, 54(2): 10-20.
[3]	LI Lingzi, JI Changli, LIU Ye, FU Mingfang, LI Zongrun, TONG Jundan, CHEN Qiuyuan, ZHANG Jing, ZHAO Yafan, WANG Daoli, PENG Ting. Effects of Mixed Ensiling of Rice with Sorghum‑Sudangrass Hybrid on Forage Nutritional Quality and Microbial Community [J]. Journal of Henan Agricultural Sciences, 2024, 53(9): 132-140.
[4]	FENG Peiyuan, DONG Yue, JIAO Zilan, CHEN Min, KONG Weiru, RAN Jie, LI Peifu, TIAN Lei. Comprehensive Evaluation of Salt Tolerance and Genome‑Wide Association Study of Japonica Rice Germplasms at Seedling Stage [J]. Journal of Henan Agricultural Sciences, 2024, 53(7): 1-9.
[5]	ZHANG Chaoran, PENG Yi, YANG Kaili, YUAN Ningge, LI Yuanjin, LIU Xiaojuan, WU Huili. Estimation of Rice Panicle Biomass by Remotely Sensed Photosynthetically Active Absorption [J]. Journal of Henan Agricultural Sciences, 2024, 53(6): 154-161.
[6]	LIU Qihua, SUN Zhaowen, YIN Xiubo, ZHENG Chongke. Effect of Optimal Reduction of Chemical Fertilizer on Eating and Nutritional Quality of Superior and Inferior Grains of Dry Direct‑Sowing Rice in Wheat‑Rice Rotation Cropping District [J]. Journal of Henan Agricultural Sciences, 2024, 53(6): 27-36.
[7]	DONG Hongrui, ZHU Jie, ZHOU Yong, LI Haoxuan, YANG Wei, JIANG Mengdie, ZHU Bo, NIE Jiangwen, LIU Zhangyong. Effects of Panicle Potassium Fertilizer Rates and Foliar Fertilizer on Rice Physiological Characteristics，Yield and Quality under Crayfish‑Rice Integrated System [J]. Journal of Henan Agricultural Sciences, 2024, 53(5): 30-39.
[8]	ZHANG Yongze, WANG Ruigang, WANG Yimei, WANG Zihao, LI Junzhou, DU Yanxiu, SUN Hongzheng, PENG Ting, ZHAO Quanzhi, ZHANG Jing. Effects of Sowing Date and Nitrogen Application Rate on Population Quality，Yield and Nitrogen Use Efficiency of Medium Indica Hybrid Rice [J]. Journal of Henan Agricultural Sciences, 2024, 53(4): 37-46.
[9]	QU Xiaotian, WANG Ya’nan, XU Qianru, LI Xueyang, ZHANG Shenli, ZHANG Erqin, ZHANG Gaiping. Expression and Purification of H5N1 Subtype Avian Influenza Virus HA Protein in Rice Endosperm [J]. Journal of Henan Agricultural Sciences, 2024, 53(3): 125-132.
[10]	LIU Yue, ZHOU Meng, LUO Haiwei, DANG Chengcheng, HAO Rongrong, HU Yuting, YAN Peng, CHEN Longzhou, LIU Yangxuan, TIAN Xiaohai. Optimal Zinc Application Rate for Rice Yield and Quality Improvement in Jianghan Plain [J]. Journal of Henan Agricultural Sciences, 2024, 53(3): 43-52.
[11]	DU Xueli, KE Luyao, LIU Zhan, DAI Mingzhu, ZHOU Yu, LI Jianxing, XU Jiuliang. Effects of Foliar Magnesium on Yield，Quality and Contents of Anthocyanin and Metabolites of Purple Rice [J]. Journal of Henan Agricultural Sciences, 2024, 53(2): 28-36.
[12]	FAN Yifan, ZHANG Yanyan, WANG Yimei, LI Junzhou, DU Yanxiu, SUN Hongzheng, PENG Ting, ZHAO Quanzhi, ZHANG Jing. Effects of Temperature and Light Conditions on Yield and Quality of Indica Rice under Different Sowing Dates [J]. Journal of Henan Agricultural Sciences, 2024, 53(2): 17-27.
[13]	ZHANG Zhaoran, ZHU Boyi, GAO Song, LI Zhaowei. Identification of Rice B12D Gene Family and Expression Analysis under Submergence Stress [J]. Journal of Henan Agricultural Sciences, 2024, 53(12): 31-42.
[14]	WU Zhongying, ZHANG Sipu, CUI Wei, GUO Chaofeng, LU Yunfeng, XIE Yuanming, NIU Jiajia. Effects of Different Harvesting Periods on the Quality of Suli Pear and Fresh‑keeping Effect in Semi‑underground Ventilation Storeroom [J]. Journal of Henan Agricultural Sciences, 2024, 53(11): 164-172.
[15]	. Effects of Sowing Date and Enhancing Fragrance Fertilizer on Yield，Quality and Fragrance of Aromatic Rice with High Quality [J]. Journal of Henan Agricultural Sciences, 2024, 53(11): 50-62.