基于TWDTW的时间序列GF-1 WFV农作物分类

doi:10.3864/j.issn.0578-1752.2019.17.004

Abstract

Abstract:

【Objective】 Yanqi Basin is an important production base of characteristic agricultural products in Xinjiang, and the planting structure of crops is complicated. In this study, the time series remote sensing data were used to classify and identify crops in the study area, so as to obtain the spatial distribution of different crops and their planting areas, which were the important basis for government sectors to formulate grain policies and economic plans. At the same time, the applicability of time-weighted dynamic time warping (TWDTW ) method in crop classification and the application potential of GF-1 WFV in agriculture were also discussed.【Method】 The normalized vegetation index (NDVI), calculated from the 2018 time series GF-1 WFV data set in Yanqi Basin, Xinjiang, was used to study the crops recognition based on TWDTW method. Sample points of different crops were collected to form standard sequence of NDVI for each crop. The TWDTW similarity matching algorithm was used to calculate the similarity distance between each pixel to be classified and the standard sequence of different crops. The smaller the distance was, the higher the similarity was. The similarity was used to determine the crop type of the pixel, and the final classification result was obtained. At the same time, the classification rules of decision tree were established according to the NDVI curve of time series, and the classification result was obtained by manually setting the classification threshold, and compared with that of the TWDTW method. 【Result】 The classification results of the two methods were very consistent. Peppers were the most widely planted and the wheat was mainly distributed in the northern part of the Yanqi Basin and the 21st Division of the Second Agricultural Division. The distributions of tomato and sugar beet were relatively sporadic. Among the results of planting area, pepper had the largest planting area, followed by tomato, wheat and sugar beet. The accuracy of the classification results of the TWDTW and decision tree methods was verified by the field sample points: The overall accuracy of them were 89.58% and 90.97%, respectively, and the kappa index of them were 0.804 and 0.830, respectively. The classification accuracy of the TWDTW method was slightly higher than that of the decision tree method. 【Conclusion】 Compared with the decision tree classification method, the classification accuracy of the TWDTW method was slightly improved, the classification result was more objective and reliable. The algorithm of TWDTW method was not limited by geographical factors and had strong flexibility and applicability. The experimental results showed that using TWDTW algorithm to identify crops based on the GF-1 WFV data set of dense temporal phase could get better classification results, and it had great application and popularization value in agricultural field.

Key words: TWDTW, time series, GF-1, crop identification, decision trees

QIU PengXun, WANG XiaoQin, CHA MingXing, LI YaLi. Crop Identification Based on TWDTW Method and Time Series GF-1 WFV[J].Scientia Agricultura Sinica, 2019, 52(17): 2951-2961.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://www.chinaagrisci.com/EN/10.3864/j.issn.0578-1752.2019.17.004

https://www.chinaagrisci.com/EN/Y2019/V52/I17/2951

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 1

Table 2

Table 3

References 38

[1]	陈水森, 柳钦火, 陈良富, 李静, 刘强 . 粮食作物播种面积遥感监测研究进展. 农业工程学报, 2005,21(6):166-171.
	CHEN S S, LIU Q H, CHEN L F, LI J, LIU Q . Review of research advances in remote sensing monitoring of grain crop area. Transactions of the Chinese Society of Agricultural Engineering, 2005,21(6):166-171. (in Chinese)
[2]	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 Snica, 2015,48(10):1900-1914. (in Chinese) doi: 10.3864/j.issn.0578-1752.2015.10.004
[3]	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)
[4]	GÓMEZ C, WHITE J C, WULDER M A . Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 2016,116:55-72.
[5]	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)
[6]	WU W, YU Q, PETER V H, YOU L, YANG P, TANG H . How could agricultural land systems contribute to raise food production under global change. Journal of Integrative Agriculture, 2014,13(7):1432-1442.
[7]	CONGALTON R G . A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 1998,37(2):270-279.
[8]	刘亚群 . 基于多时相遥感影像的黑河流域农作物种植结构提取研究[D]. 重庆: 重庆交通大学, 2016.
	LIU Y Q . Changes in crop planting structure of the Heihe River Basin in China based on the multi-temporal NDVI from TM/ETM+/OLI images. Chongqing: Chongqing Jiaotong University, 2016. (in Chinese)
[9]	VINTROU E, DESBROSSE A, BEGUE A, TRAORE S, BARON C, LO SEEN D . Crop area mapping in west Africa using landscape stratification of MODIS time series and comparison with existing global land products. International Journal of Applied Earth Observation and Geoinformation, 2012,14(1):83-93.
[10]	SHAO Y, LUNETTA R S, WHEELER B, IIAMES J S, CAMPBELL J B . An evaluation of time-series smoothing algorithms for land-cover classifications using MODIS-NDVI multi-temporal data. Remote Sensing of Environment, 2016,174:258-265.
[11]	ZHANG J, FENG L, YAO F . Improved maize cultivated area estimation over a large scale combining MODIS-EVI time series data and crop phenological information. ISPRS Journal of Photogrammetry and Remote Sensing, 2014,94:102-113.
[12]	CHEN Y, LU D, MORAN E, BATISTELLA M, DUTRA L V, SANCHES I D A, DA SILVA R F B, HUANG J, LUIZ A J B, DE OLIVEIRA M A F . Mapping croplands, cropping patterns, and crop types using MODIS time-series data. International Journal of Applied Earth Observation and Geoinformation, 2018,69:133-147.
[13]	杨小唤, 张香平, 江东 . 基于MODIS时序NDVI特征值提取多作物播种面积的方法. 资源科学, 2004,26(6):17-22.
	YANG X H, ZHANG X P, JIANG D . Extraction of multi-crop planting areas from MODIS data. Resources Science, 2004,26(6):17-22. (in Chinese)
[14]	陈颖姝, 张晓春, 王修贵, 罗强, 熊勤学, 罗文兵 . 基于Landsat8 OLI与MODIS数据的洪涝季节作物种植结构提取. 农业工程学报, 2014,30(21):165-173.
	CHEN Y S, ZHANG X C, WANG X G, LUO Q, XIONG Q X, LUO W B . Extraction of crop planting structure in seasons prone to waterlogging using Landsat8 OLI and MODIS data. Transactions of the Chinese Society of Agricultural Engineering, 2014,30(21):165-173. (in Chinese)
[15]	张焕雪, 曹新, 李强子, 张淼, 郑新奇 . 基于多时相环境星NDVI时间序列的农作物分类研究. 遥感技术与应用, 2015,30(2):304-311. doi: 10.11873/j.issn.1004-0323.2015.2.0304
	ZHANG H X, CAO X, LI Q Z, ZHANG M, ZHENG X Q . Research on crop identification using multi-temporal NDVI HJ images. Remote Sensing Technology and Application, 2015,30(2):304-311. (in Chinese) doi: 10.11873/j.issn.1004-0323.2015.2.0304
[16]	白照广 . 高分一号卫星的技术特点. 中国航天, 2013(8):5-9.
	BAI Z G . Technical characteristics of GF-1 satellite.Aerospace China, 2013(8):5-9. (in Chinese)
[17]	郭燕, 武喜红, 程永政, 王来刚, 刘婷 . 用高分一号数据提取玉米面积及精度分析. 遥感信息, 2015,30(6):31-36.
	GUO Y, WU X H, CHENG Y Z, WANG L G, LIU T . Maize recognition and accuracy evaluation based on high resolution remote sensing (GF-1) data. Remote Sensing Information, 2015,30(6):31-36. (in Chinese)
[18]	刘原峰 . 基于多时相GF-1 WFV影像的绿洲主要粮食作物识别及估产——以民勤绿洲为例[D]. 兰州: 西北师范大学, 2016.
	LIU Y F . Oasis main food crops remote-sensing recognition and yield estimation based on multi-temporal GF-1 WFV Images a case study in Minqin Oasis. Lanzhou: Northwest Normal University, 2016. (in Chinese)
[19]	黄健熙, 侯矞焯, 苏伟, 刘峻明, 朱德海 . 基于GF-1 WFV数据的玉米与大豆种植面积提取方法. 农业工程学报, 2017,33(7):164-170.
	HUANG J X, HOU Y Z, SU W, LIU J M, ZHU D H . Mapping corn and soybean cropped area with GF-1 WFV data. Transactions of the Chinese Society of Agricultural Engineering, 2017,33(7):164-170. (in Chinese)
[20]	原继东, 王志海 . 时间序列的表示与分类算法综述. 计算机科学, 2015(3):1-7.
	YUAN J D, WANG Z H . Review of time series representation and classification techniques.Computer Science, 2015(3):1-7. (in Chinese)
[21]	ARVOR D, JONATHAN M, MEIRELLES M S P, DUBREUIL V, DURIEUX L . Classification of MODIS EVI time series for crop mapping in the state of Mato Grosso, Brazil. International Journal of Remote Sensing, 2011,32(22):7847-7871.
[22]	SAKOE H, CHIBA S . Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978,26(1):43-50.
[23]	KEOGH E . Exact indexing of dynamic time warping. Knowledge and Information Systems, 2005,7:386-758.
[24]	HAMOONI H . Phoneme sequence recognition via DTW-based classification. Knowledge and Information Systems, 2016,48:253-275.
[25]	JEONG Y S, JEONG M K, OMITAOMU O A . Weighted dynamic time warping for time series classification. Pattern Recognition, 2011,44(9):2231-2240.
[26]	钟礼山, 李满春, 伍阳, 夏南, 程亮 . 利用SAR影像时间序列的耕地提取研究. 地理科学进展, 2015,34(7):830-839.
	ZHONG L S, LI M C, WU Y, XIA N, CHENG L . Cropland extraction using SAR time series image. Progress in Geography, 2015,34(7):830-839. (in Chinese)
[27]	叶燕清, 杨克巍, 姜江, 葛冰峰, 豆亚杰 . 基于加权动态时间弯曲的多元时间序列相似性匹配方法. 模式识别与人工智能, 2017,30(4):314-327.
	YE Y Q, YANG K W, JIANG J, GE B F, DOU Y J . Multivariate time series similarity matching method based on weighted dynamic time warping algorithm. Pattern Recognition and Artificial Intelligence, 2017,30(4):314-327. (in Chinese)
[28]	MAUS V, $\widehat{C}$AMARA G, APPEL M . dtwSat: Time-weighted dynamic time warping for satellite image time series analysis in R. Journal of Statistical Software, 2017,90(1):1-30.
[29]	BELGIU M . Sentinel-2 cropland mapping using pixel-based and object-based time weighted dynamic time warping analysis. Remote Sensing of Environment, 2018,204:509-523.
[30]	GUAN X, HUANG C, LIU G . Mapping rice cropping systems in Vietnam using an NDVI-based time-series similarity measurement based on DTW distance. Remote Sensing, 2016,8(19):3390-3415.
[31]	MANABE V D, MELO M R S, ROCHA J V . Framework for mapping integrated crop-livestock systems in Mato Grosso, Brazil. Remote Sensing, 2018,10(9):1-17.
[32]	王凯, 赵军, 朱国锋, 张佩云, 刘江涛, 陈栋栋 . 基于GF-1遥感数据决策树与混合像元分解模型的冬小麦种植面积早期估算. 遥感技术与应用, 2018,33(1):158-167.
	WANG K, ZHAO J, ZHU G F, ZHANG P Y, LIU J T, CHEN D D . Early estimation of winter wheat planting area in Qingyang city by decision tree and pixel unmixing methods based on GF-1 satellite data. Remote Sensing Technology and Application, 2018,33(1):158-167. (in Chinese)
[33]	王连喜, 徐胜男, 李琪, 薛红喜, 吴建生 . 基于决策树和混合像元分解的江苏省冬小麦种植面积提取. 农业工程学报, 2016,32(5):182-187.
	WANG L X, XU S N, LI Q, XUE H X, WU J S . Extraction of winter wheat planted area in Jiangsu province using decision tree and mixed-pixel methods. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(5):182-187. (in Chinese)
[34]	苏伟, 姜方方, 朱德海, 展郡鸽, 马鸿元, 张晓东 . 基于决策树和混合像元分解的玉米种植面积提取方法. 农业机械学报, 2015,46(9):289-295.
	SU W, JIANG F F, ZHU D H, ZHAN J G, MA H Y, ZHANG X D . Extraction of maize planting area based on decision tree and mixed-pixel unmixing methods. Transactions of the Chinese Society for Agricultural Machinery, 2015,46(9):289-295. (in Chinese)
[35]	周静平, 李存军, 史磊刚, 史姝, 胡海棠, 淮贺举 . 基于决策树和面向对象的作物分布信息遥感提取. 农业机械学报, 2016,47(9):318-326.
	ZHOU J P, LI C J, SHI L G, SHI S, HU H T, HUAI H J . Crops distribution information extracted by remote sensing based on decision tree and object-oriented method. Transactions of the Chinese Society for Agricultural Machinery, 2016,47(9):318-326. (in Chinese)
[36]	管续栋, 黄翀, 刘高焕 . 基于DTW距离的时序相似性方法提取水稻遥感信息—以泰国为例. 资源科学, 2014,36(2):267-272.
	GUAN X D, HUANG C, LIU G H . Extraction of paddy rice area using a DTW distance based similarity measure. Resources Science, 2014,36(2):267-272. (in Chinese)
[37]	杨闫君, 占玉林, 田庆久, 顾行发, 余涛, 王磊 . 基于GF-1/ WFVNDVI时间序列数据的作物分类. 农业工程学报, 2015,31(24):155-161.
	YANG Y J, ZHAN Y L, TIAN Q J, GU X F, YU T, WANG L . Crop classification based on GF- 1/WFV NDVI time series. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(24):155-161. (in Chinese)
[38]	姬忠林, 张月平, 李乔玄, 刘绍贵, 李淑娟, 任红艳 . 基于GF-1影像的冬小麦和油菜种植信息提取. 遥感技术与应用, 2017,32(4):760-765.
	JI Z L, ZHANG Y P, LI Q X, LIU S G, LI S J, REN H Y . Planting information extraction of winter wheat and rape based on GF-1 images. Remote Sensing Technology and Application, 2017,32(4):760-765. (in Chinese)

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

县(市) County	辣椒 Pepper		甜菜 Beet		小麦 Wheat		番茄 Tomato
县(市) County	决策树 DTs	TWDTW	决策树 DTs	TWDTW	决策树 DTs	TWDTW	决策树 DTs	TWDTW
和静 Hejing	23537.05	23538.66	2149.73	2434.94	3403.83	3226.04	5336.78	5668.15
和硕 Heshuo	23615.80	21033.42	2759.81	2263.35	4721.87	4740.92	3046.27	4051.12
焉耆 Yanqi	16028.77	15553.89	1695.72	1024.51	1906.18	2144.56	3040.53	4317.03
博湖 Bohu	15669.43	13244.26	1171.26	745.24	394.32	298.88	741.61	1128.58

类别 Class	辣椒 Pepper	甜菜 Beet	番茄 Tomato	小麦 Wheat	芦苇及其他植被 Reed and others	用户精度 UA	总体精度 OA
辣椒 Pepper	77	3	1	0	7	87.50%
甜菜 Beet	1	34	0	3	2	85.00%
番茄 Tomato	0	0	43	0	6	87.75%
小麦 Wheat	0	0	0	68	1	98.55%
其他 Others	4	2	0	0	36	85.71%
制图精度 PA	93.90%	87.18%	97.72%	95.83%	69.23%		89.58%

类别 Class	辣椒 Pepper	甜菜 Beet	番茄 Tomato	小麦 Wheat	芦苇及其他植被 Reed and others	用户精度 UA	总体精度 OA
辣椒 Pepper	79	2	1	0	6	89.77%
甜菜 Beet	1	36	0	1	2	90.00%
番茄 Tomato	1	0	45	0	3	91.84%
小麦 Wheat	0	0	2	65	2	94.20%
其他 Others	3	2	0	0	37	88.10%
制图精度 PA	94.05%	90.00%	93.75%	98.48%	74.00%		90.97%

Crop Identification Based on TWDTW Method and Time Series GF-1 WFV

RichHTML

PDF

Abstract

Cite this article

share this article

Figures/Tables 8

References 38

Related Articles 6

Metrics

Comments

Recommended 0

[1]	YANG JingYa,HU Qiong,WEI HaoDong,CAI ZhiWen,ZHANG XinYu,SONG Qian,XU BaoDong. Consistency Analysis of Classification Results for Single and Double Cropping Rice in Southern China Based on Sentinel-1/2 Imagery [J]. Scientia Agricultura Sinica, 2022, 55(16): 3093-3109.
[2]	XIANG FangLin,LI XinGe,MA JiFeng,LIU XiaoJun,TIAN YongChao,ZHU Yan,CAO WeiXing,CAO Qiang. Using Canopy Time-Series Vegetation Index to Predict Yield of Winter Wheat [J]. Scientia Agricultura Sinica, 2020, 53(18): 3679-3692.
[3]	PAN YangYang,WANG Meng,RUI Xian,WANG LiBin,HE HongHong,WANG JingLei,MA Rui,XU GengQuan,CUI Yan,FAN JiangFeng,YU SiJiu. RNA-Binding Motif Protein 3(RBM3) Expression is Regulated by Insulin-Like Growth Factor (IGF-1) for Protecting Yak (Bos grunniens) Cumulus Cells from Apoptosis During Hypothermia Stress [J]. Scientia Agricultura Sinica, 2020, 53(11): 2285-2296.
[4]	LIU HuanJun, YU ShengNan, ZHANG XinLe, GUO Dong, YIN JiXian. Timeliness Analysis of Crop Remote Sensing Classification One Crop A Year [J]. Scientia Agricultura Sinica, 2017, 50(5): 830-839.
[5]	. Monitoring Spatial Patterns of Cropland Phenology in North China Based on NOAA NDVI Data [J]. Scientia Agricultura Sinica, 2009, 42(2): 552-560 .
[6]	. Effect of IGF-1 on expression of related hair follicle growth factors and receptors in varied sheepskin [J]. Scientia Agricultura Sinica, 2007, 40(3): 594-600 .