<p>精准农业是现代农业的重要组成部分,它通过各种技术手段获取农田内不同单元小区农作物的生长环境信息,并由此实现整个生产过程的精细化、准确化的农业微观经营管理。由于遥感技术能在不同的电磁谱段内周期性地采集地表信息,因此随着遥感技术的发展,其在精准农业领域开始发挥越来越大的作用,并在指导农田灌溉、施肥、病虫害防治、杂草控制及收获等方面均已有很多成功的应用。为使人们对遥感在精准农业中的应用有一总体了解,在概述遥感技术在精准农业领域应用进展的基础上,对其研究现状进行了分析总结,还对其发展进行了展望,并指出了技术方法的改进、新数据的应用、多源数据整合、遥感数据与农学/作物模型的整合以及监测技术的系统化是促进遥感技术在精准农业中发挥更大作用的主要研究内容。</p>

农业是遥感技术应用最重要和广泛的领域之一,本文回顾了遥感技术在国内外农业研究与应用中的进展,概括和总结了农田辐射传输机理及作物参量遥感反演、作物遥感分类与识别、农田养分遥感与变量施肥决策、作物产量与品质预测、农情遥感监测与预报、农业遥感监测空间决策支持系统6个主要研究与应用方面。在此基础上,针对农业遥感技术面临的问题与发展趋势,指出了农业遥感技术今后的重点发展方向。

介绍了遥感监测粮食作物播种面积的理论和现实意义,回顾了国内外基于常规方法、线状框架采样、面积框架采样、光谱混合模型(spectral mixture model , SMA)等方法进行植被制图和进行粮食作物识别研究的现状和存在的问题, 并对基于波谱库的农作物播种面积监测提出了建议。

农作物遥感识别是地理学和生态学研究的前沿和热点,多源数据在农作遥感识别中日益发挥重要作用。笔者从多源数据融合的角度,归纳了2000年后多源数据在农作物遥感识别中应用的总体概况,系统梳理并提炼了当前多源数据融合的主要融合技术和融合模式。围绕与多源数据融合和农作物遥感识别相关的关键词,在Google学术、ISI Web of Knowledge和中国知网中对2000—2014年间国内外发表的论文进行检索,并统计不同传感器的使用频率及结合方式。研究表明,以提高空间分辨率为目标的多源数据融合和以提高时间分辨率为目标的多源数据融合技术是当前的两种主要方式,可以在一定程度上实现时空尺度的扩展。前者的融合技...

The global environmental change research community requires improved and up-to-date land use/land cover (LULC) datasets at regional to global scales to support a variety of science and policy applications. Considerable strides have been made to improve large-area LULC datasets, but little emphasis has been placed on thematically detailed crop mapping, despite the considerable influence of management activities in the cropland sector on various environmental processes and the economy. Time-series MODIS 250 m Vegetation Index (VI) datasets hold considerable promise for large-area crop mapping in an agriculturally intensive region such as the U.S. Central Great Plains, given their global coverage, intermediate spatial resolution, high temporal resolution (16-day composite period), and cost-free status. However, the specific spectral emporal information contained in these data has yet to be thoroughly explored and their applicability for large-area crop-related LULC classification is relatively unknown. The objective of this research was to investigate the general applicability of the time-series MODIS 250 m Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) datasets for crop-related LULC classification in this region. A combination of graphical and statistical analyses were performed on a 12-month time-series of MODIS EVI and NDVI data from more than 2000 cropped field sites across the U.S. state of Kansas. Both MODIS VI datasets were found to have sufficient spatial, spectral, and temporal resolutions to detect unique multi-temporal signatures for each of the region's major crop types (alfalfa, corn, sorghum, soybeans, and winter wheat) and management practices (double crop, fallow, and irrigation). Each crop's multi-temporal VI signature was consistent with its general phenological characteristics and most crop classes were spectrally separable at some point during the growing season. Regional intra-class VI signature variations were found for some crops across Kansas that reflected the state's climate and planting time differences. The multi-temporal EVI and NDVI data tracked similar seasonal responses for all crops and were highly correlated across the growing season. However, differences between EVI and NDVI responses were most pronounced during the senescence phase of the growing season.

及时、准确的作物长势监测可以为宏观决策和农田生产提供作物生长信息,便于及时采取各种田间管理措施,达到科学管理和作物增产的目的。归一化植被指数(normalized difference vegetation index,NDVI)与植被的叶面积指数(leaf area index,LAI)和叶片叶绿素含量关系极为密切,可以用来评价作物的生长状况。为了降低主观因素及物候差异对大豆长势监测的影响,该研究以黑龙江红星农场主要农作物大豆为例,基于历史NDVI数据建立了该区域大豆长势评价的标准。利用NDVI时间序列拟合法提取大豆关键物候期,结合物候监测结果对大豆长势进行修正,最后利用41个地块的单产数据对长势评价结果进行了验证。物候修正前后长势与单产的一致性分别为58.5%、75.6%,容差为1个等级时分别为87.8%、95.1%,表明历史NDVI对大豆长势评价有一定参考意义,但简单同期对比不能完全反映大豆长势真实情况,物候修正可以进一步改善长势评价效果。研究可以为利用遥感进行大豆长势评价提供参考依据。

Land use and land cover changes have as consequences several social, economic, and environmental impacts. The understanding of these changes allows a better planning of public policies in order to map and monitor areas more susceptible to environmental problems. This research presents an analysis of the land use and land cover changes of a watershed region located in the Brazilian Amazon, and an evaluation of their impacts on sediment yield. Land use/land cover maps for each of the analyzed time periods (1973, 1984, and 2005) were compiled using images obtained by MSS/Landsat-1, TM/Landsat-5, and the MODIS/Terra sensors. The sediment yield modeling was performed by dividing the watershed into homogeneous subregions. Each of the subregions received average attributes that were used as input parameters for the Universal Soil Loss Equation. The results revealed that up to 2005, around 40% of the study area was already deforested, replaced by agricultural activities. In some parts of the watershed these changes were responsible for an increase of up to 7 ton/ha in annual average sediment yield. This study was successful in providing an assessment of the magnitude and spatial distribution of the changes.

Field crop yield prediction is crucial to grain storage, agricultural field management, and national agricultural decision-making. Currently, crop models are widely used for crop yield prediction. However, they are hampered by the uncertainty or similarity of input parameters when extrapolated to field scale. Data assimilation methods that combine crop models and remote sensing are the most effective methods for field yield estimation. In this study, the World Food Studies (WOFOST) model is used to simulate the growing process of spring maize. Common assimilation methods face some difficulties due to the scarce, constant, or similar nature of the input parameters. For example, yield spatial heterogeneity simulation, coexistence of common assimilation methods and the nutrient module, and time cost are relatively important limiting factors. To address the yield simulation problems at field scale, a simple yet effective method with fast algorithms is presented for assimilating the time-series HJ-1 A/B data into the WOFOST model in order to improve the spring maize yield simulation. First, the WOFOST model is calibrated and validated to obtain the precise mean yield. Second, the time-series leaf area index (LAI) is calculated from the HJ data using an empirical regression model. Third, some fast algorithms are developed to complete assimilation. Finally, several experiments are conducted in a large farmland (Hongxing) to evaluate the yield simulation results. In general, the results indicate that the proposed method reliably improves spring maize yield estimation in terms of spatial heterogeneity simulation ability and prediction accuracy without affecting the simulation efficiency.

以目前农业旱灾监测中应用较广泛的多波段MODIS卫星遥感数据为例,探讨农业旱灾遥感监测中所需要的地表温度反演问题,尤其是反演算法的选择、基本参数的估计和具体反演中的工作流程,为快速地进行农业旱灾监测中的水热遥感参数估计提供方法选择.虽然MODIS有8个热红外波段用来监测地表热量变化,但波段31和32特别适用于农业旱灾监测中所需要的地表温度遥感反演.因此,在算法上,我们将选择计算过程相对简便但反演精度又很高的两因素分裂窗算法.详细地讨论了如何快速地估计分裂窗算法中大气透过率和地表比辐射率这两个基本参数.从实际应用来看,本文所提出的方法能快速地用来反演我国农业旱灾监测中所需要的农田地表温度参数,并获得很好的反演结果.

This study presents a crop planting and type proportion (CPTP) method for crop acreage estimation of complex and diverse agricultural landscapes. CPTP has three major components: (1) Crop planting proportion (CPP), estimated with wide-swath satellite remote sensing data to completely cover the monitoring area by segmenting cropped and non-cropped areas through unsupervised classification. (2) Crop type proportion (CTP), estimated by transect sampling and a special GPS-Video-GIS instrument (GVG) and a visual interpretation of crop type proportion in collected pictures for different strata. (3) Multiplication of CPP and CTP with arable land area at the strata level, summed to the province and national level. Validation has been done with in situ data for different agricultural landscapes over China. Both CPP estimation with remote sensing data and CTP estimation through ground survey have a high accuracy with average relative error (RE) and root mean square error (RMSE) equal to 1.42% and 1.67% for CPP and to 2.63% and 2.25% for CTP. The RE for crop acreage estimation equals to 4.09%. The CPTP method thus has a high accuracy, yields timely information at low costs, and is robust and provides objective results. The study concludes that the CPTP method can be used for large area crop acreage estimation of complex agriculture landscapes.

To explore the feasibility of quickly extracting planting area using HJ satellite CCD data acquired at the main crop key growth periods, a quick and easy crop planting area extraction method was presented. The author took Wudi County of Shandong Province as a study area, 3 HJ remote sensing images acquired at the main crop key growth periods were selected based on the main crop cultivation technique calendar. Through the EVI time-series data analysis and regions of interesting (ROI) creations, the support vector machine (SVM) was used for extracting the main crop planting area. The results showed that: the EVI data of the crop key growth periods in combination with the SVM method could more accurately estimate the winter wheat, corn and cotton planting area of Wudi County, and overall accuracy of total planting area extraction and spatial distribution location was more than 93% and 75% respectively. Through using the remote sensing data acquired at a crop key growth period, time and labor for remote sensing data processing was reduced greatly, and it was easy to visualize the choice of ROI. Only used SVM could guarantee the regional crop planting area extraction accuracy, which greatly simplified the operation process and provided a reference for other regions to use HJ satellite data to extract crop planting area.

环境减灾卫星作为我国自主研制 发射的环境与灾害监测预报卫星,要发挥它的作用就是要更好的使用其数据源。支持向量机(Support Vector Machine,SVM)是一种卓越的分类方法,本文通过SVM方法对环境减灾卫星HJ-1B星CCD影像数据进行作物分类识别实验并将结果与最大似然法 分类结果进行比较。结果表明:利用SVM方法进行遥感图像分类,精度优于传统的最大似然法分类精度;Hj-1 A/1B星CCD数据对于农作物具有较好的指示效果,可应用于作物识别等农业领域。

Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image‐processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non‐parametric classifiers such as neural network, decision tree classifier, and knowledge‐based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image‐processing chain to improve classification accuracy.

The current paper investigates the potential contribution of ENVISAT wide swath (WS) images for discrimination and monitoring of crops at a regional scale. The study was based on synthetic aperture radar (SAR) images acquired throughout an entire growing season. Advanced synthetic aperture radar sensor (ASAR) images in both narrow swath (NS) and WS modes were simulated based on 15 European Remote Sensing (ERS) satellite images recorded over Belgium. Unlike ‘real’ ASAR imagery, this exercise provided a consistent data set (i.e. same incidence angle, same acquisition date, same acquisition hour) to study the impact of spatial resolution on the SAR signal information content. A quantitative approach using 787 parcels of medium field size and various data combinations assessed monitoring and discrimination capabilities for six crop types: wheat, barley, grasses, sugar beet, maize and potato. The spatial resolution impact of the ASAR sensor was discussed with respect to the field size by comparing the results obtained from NS (3002m) and WS (15002m) mode images. WS temporal profiles were able to discriminate the various crops of interest and were representative of the crop development observed in the region. Furthermore, parcel‐based unsupervised classifications successfully discriminated between grass, wheat, barley and other crops of large parcels (success rate of 83%). Dedicated interpretation schemes were developed in order to discriminate between cereal crops.

61Narrowbands explained ~25% greater variability than broadbands in crop modeling.61Narrowbands provided ~20% greater accuracies than broadbands in crop discrimination.613–7 narrowbands explained over 90% variability in crop models.61Highly informative and redundant narrowbands helped overcome Hughes phenomenon.6129 key Hyperion hyperspectral narrowband centers in crop studies were identified.

A comparison of agricultural crop maps from independent field-based classifications of the Satellite Pour l'Observation de la Terre (SPOT) 4 multispectral (XS), SPOT5 XS, IKONOS XS, QuickBird XS and QuickBird pan-sharpened (PS) images is presented. An agricultural area within the north-west section of Turkey was analysed for field-based crop identification. The SPOT4 XS, SPOT5 XS, IKONOS XS and QuickBird images were collected in similar climatic conditions during July and August 2004. The classification of each image was carried out separately on a per-field basis on all bands and the coincident bands that are green, red and near-infrared (NIR). To examine the effect of filtering on field-based classification, the images were each filtered using the 365×653, 565×655, 765×657 and 965×659 mean filter and the filtered bands were also classified on per-field basis. For the unfiltered images, IKONOS XS provided the highest overall accuracies of 88.9% and 88.1% for the all-bands and the coincident bands classifications, respectively. On average, IKONOS XS performed slightly better than QuickBird XS and QuickBird PS, while it outperformed SPOT4 XS and SPOT5 XS. The use of filtered images in field-based classification reduced the accuracies for SPOT4 XS, SPOT5 XS, IKONOS XS and QuickBird XS. The results of this study indicate that smoothing images prior to classification does not improve the accuracies for the field-based classification. On the contrary, the accuracies for the filtered QuickBird PS images indicated a slight improvement. On the whole, both IKONOS and QuickBird images produced quite promising results for field-based crop mapping, yielding overall accuracies above 83%.

以提高冬小麦种植面积估算精度为目标,选取种植结构复杂的都市农业区,采用QuickBird影像数字化农田地块边界,以多时相TM影像为核心数据源,以地块为基本分类单元,进行不同特征向量组合、不同分类器的冬小麦地块分类方法研究,并对比分析了基于地块分类和基于像元分类的冬小麦种植面积估算精度.研究结果表明,基于地块分类的冬小麦种植面积估算方法的总量精度和位置精度均高于像元分类;植被指数和纹理信息的引入有助于进一步提高地块分类精度;支持向量机与最大似然均能得到高达97%的总量精度和90%的位置精度,支持向量机地块分类所需的训练样本量远低于最大似然,因此支持向量机更加适合于冬小麦地块分类;冬小麦错分与漏分情况大多发生在细碎地块,其面积总量较小,而大地块错分和漏分较少,因此相对于像元分类,地块分类能在整个区域能得到较高的冬小麦位置精度和总量精度.

梯田信息准确和快速提取是区域水土保持动态监测和评价的核心技术之一,运用遥感技术进行地物信息提取是一种有效手段。该研究以燕沟流域为研究区,采用高分辨率的SPOT5遥感影像数据,基于面向对象分类技术,通过影像分割构建影像对象,在分析影像对象的光谱特征、纹理特征和空间特征的基础上,建立了梯田信息的遥感提取规则,实现了梯田的自动提取。最后用手工勾绘结果对梯田的遥感提取结果进行精度评价,从田块边界的吻合度评价位置精度,并通过比较该结果与人工目视解译结果进行面积精度评价。结果表明,基于面向对象分类的遥感方法可以较好地从原始影像中提取复杂地貌区梯田的位置信息,面积提取正确率达到78.38%,该方法可为黄土高原地区梯田信息遥感提取提供借鉴。

A land cover map of Jersey was created using remotely sensed images recorded by satellite. This map brought together a range of disparate techniques, developed in isolation and mostly applied experimentally, integrating multisensor, multitemporal, enhanced spatial resolution data within an object-oriented integrated Geographical Information System (GIS) for an applications-driven, operational programme. It was developed under the Classification of Environment with Vector- and Raster-Mapping (CLEVER-Mapping) project: this improved approach to operational land cover mapping used information on the subdivision of the landscape into land parcels to help classify remotely sensed images on a per-parcel basis. The object-oriented approach allowed the use of remotely sensed information which relates directly to ground features, and the application of improved knowledge-based corrections using a range of external data. Unlike a conventional map, the parcel-based approach produced a GIS database containing classified land parcels which could also be used as a storage framework and analysis tool for other datasets in later analyses. The GIS recorded 21 land cover types. Validation against reference land parcel data gave a correspondence of between 85% and 95% depending on the level of class aggregation.

农田地块是农田地理要素的典型要素。为此,分析了农田地块变更的数据源及其更新形式,并提出了农田地块更新模型,以便满足不同数据源的地块更新实现的需要,最后依据农田地块更新模型设计了面向精准农业应用的农田地块更新地理信息系统的体系结构、数据库结构及其功能结构。

本文基于南方五省稻农地块的微观数据,利用固定效应模型分析了地块特征对稻农农业机械利用的影响。地块特征通过4个方面影响农户农机利用:地块零碎化、土壤质量、基础设施便利性、地块来源。研究表明,地块面积越大,稻农越容易采用农机作业。土壤质量越差,越不利于稻农采用农机进行收割。相对于其他因素,地块基础设施对稻农是否采用农业机械生产的影响最大。如果地块灌溉条件不好或机耕路不便使得机器难以抵达田间,则农户使用机器耕整和收割的概率分别下降13.1和41.6个百分点。如果地块是从市场租入,则农户采用农机作业的概率增加。

Three Landsat7 ETM+ images acquired in May, July and August during the 2000 crop growing season were used for field‐based mapping of summer crops in Karacabey, Turkey. First, the classification of each image date was performed on a standard per pixel basis. The results of per pixel classification were integrated with digital agricultural field boundaries and a crop type was determined for each field based on the modal class calculated within the field. The classification accuracy was computed by comparing the reference data, field‐by‐field, to each classified image. The individual crop accuracies were examined on each classified data and those crops whose accuracy exceeds a preset threshold level were determined. A sequential masking classification procedure was then performed using the three image dates, excluding after each classification the class properly classified. The final classified data were analysed on a field basis to assign each field a class label. An immediate update of the database was provided by directly entering the results of the analysis into the database. The sequential masking procedure for field‐based crop mapping improved the overall accuracies of the classifications of the July and August images alone by more than 10%.

应用面向对象方法,对遥感图像进行多尺度分割,即首先进行大尺度分割,结合NDVI提取植被信息,将图像分为植被和非植被;然后在植被信息类内再进行小尺度分割,利用NDVI并融入几何特征进一步提取冬小麦种植面积及空间分布.在遥感分类的基础上,将线性数据按宽度缓冲,从分类结果中扣除.将扣除结果与地面样方实测数据对比分析.结果表明,监测结果减轻了传统分类方法的椒盐效应,监测结果与验证样方数据比较精度为94.06%.

61The proposed selfhood scales can measure local contexts of pixels.61Self-adaptive segmentation with selfhood scales outperforms multiresolution segmentation.61The proposed multi-level classifier excels in using multiscale features.61Selfhood scales can improve both per-pixel and object-based classifications.61The proposed methods produce urban land cover maps with larger accuracy.

The utility of Enhanced Thematic Mapper Plus (ETM+) has been diminished since the 2003 scan-line corrector (SLC) failure. Uncorrected images have data gaps of approximately 22% and gap-filling schemes have been developed to improve their usability. We present a method to classify a northeast Montana agricultural landscape using ETM+ SLC-off imagery without gap-filling. We use multitemporal data analysis and employ an object-oriented approach to define objects, agricultural fields, with cadastral data. This approach was assessed by comparison to a pixel-based approach. Results indicate that an ETM+ SLC-off image can be classified with better than 85% overall accuracy without gap-filling.

78 Decision tree modeling is suitable to identify crops at different field conditions. 78 Consideration of intra-class variations is required to improve classifications. 78 Textural features improve discrimination among heterogeneous permanent crops. 78 Information from NIR and SWIR bands is needed for detailed crop identification. 78 Crop identification requires the study of field status in distinct growing seasons.

The strategic management of agricultural lands involves crop field monitoring each year. Crop discrimination via remote sensing is a complex task, especially if different crops have a similar spectral response and cropping pattern. In such cases, crop identification could be improved by combining object-based image analysis and advanced machine learning methods. In this investigation, we evaluated the C4.5 decision tree, logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) neural network methods, both as single classifiers and combined in a hierarchical classification, for the mapping of nine major summer crops (both woody and herbaceous) from ASTER satellite images captured in two different dates. Each method was built with different combinations of spectral and textural features obtained after the segmentation of the remote images in an object-based framework. As single classifiers, MLP and SVM obtained maximum overall accuracy of 88%, slightly higher than LR (86%) and notably higher than C4.5 (79%). The SVM+SVM classifier (best method) improved these results to 89%. In most cases, the hierarchical classifiers considerably increased the accuracy of the most poorly classified class (minimum sensitivity). The SVM+SVM method offered a significant improvement in classification accuracy for all of the studied crops compared to the conventional decision tree classifier, ranging between 4% for safflower and 29% for corn, which suggests the application of object-based image analysis and advanced machine learning methods in complex crop classification tasks.

78 Image segmentation and the Random Forest framework are combined for landslide mapping from different VHR remote sensing images. 78 Newly introduced object features and feature selection enhance the classification accuracy. 78 A scheme to account for unbalanced error rates is proposed and tested. 78 The algorithm performs robustly with different types of input datasets. 78 Employing 20% of the data for training, mapping accuracies between 73% and 87% were achieved.

In this paper, we propose and evaluate six methods for the segmentation of skin lesions in dermoscopic images. This set includes some state of the art techniques which have been successfully used in many medical imaging problems (gradient vector flow (GVF) and the level set method of Chan et al.[(C-LS)]. It also includes a set of methods developed by the authors which were tailored to this particular application (adaptive thresholding (AT), adaptive snake (AS), EM level set (EM-LS), and fuzzy-based split-and-merge algorithm (FBSM)]. The segmentation methods were applied to 100 dermoscopic images and evaluated with four different metrics, using the segmentation result obtained by an experienced dermatologist as the ground truth. The best results were obtained by the AS and EM-LS methods, which are semi-supervised methods. The best fully automatic method was FBSM, with results only slightly worse than AS and EM-LS.

The effects of land cover composition on land surface temperature (LST) have been extensively documented. Few studies, however, have examined the effects of land cover configuration. This paper investigates the effects of both the composition and configuration of land cover features on LST in Baltimore, MD, USA, using correlation analyses and multiple linear regressions. Landsat ETM + image data were used to estimate LST. The composition and configuration of land cover features were measured by a series of landscape metrics, which were calculated based on a high-resolution land cover map with an overall accuracy of 92.3%. We found that the composition of land cover features is more important in determining LST than their configuration. The land cover feature that most significantly affects the magnitude of LST is the percent cover of buildings. In contrast, percent cover of woody vegetation is the most important factor mitigating UHI effects. However, the configuration of land cover features also matters. Holding composition constant, LST can be significantly increased or decreased by different spatial arrangements of land cover features. These results suggest that the impact of urbanization on UHI can be mitigated not only by balancing the relative amounts of various land cover features, but also by optimizing their spatial configuration. This research expands our scientific understanding of the effects of land cover pattern on UHI by explicitly quantifying the effects of configuration. In addition, it may provide important insights for urban planners and natural resources managers on mitigating the impact of urban development on UHI.

A crop map of The Netherlands was created using a methodology that integrates multi-temporal and multi-sensor satellite imagery, statistical data on crop area and parcel boundaries from a 165:651065000 digital topographic map. In the first phase a crop field database was created by extracting static parcel boundaries from the digital topographic map and by adding dynamic crop boundaries using on-screen digitizing. In the next phase the crop type was determined from the spectral and phenological properties of each field. The resulting crop map has an accuracy larger than 80% for most individual crops and an overall accuracy of 90%. By comparing cost and man-hours it was demonstrated that per-field classification is more efficient than per-pixel classification and decreased the effort for classification from 1500 to 500 man-hours, but the effort for creating the crop field database was estimated at 2300 man-hours. The use of image segmentation techniques for deriving the crop field database was discussed. It was concluded that image segmentation cannot replace the use of a large-scale topographic map but, in the future, image segmentation may be used to map the dynamic crop boundaries within the topographic parcels.

第一次地理国情普查在全国范围内如火如荼地进行着,其数据的科学性、准确性和实用性一直受到相关行业的关注。本文对某市的地理国情普查成果数据与国土二调成果数据进行了对比分析,验证了地理国情普查数据的科学性和有效性,为下一步地理国情普查中数据时点核准提供了参考意见。

地理国情主要是指地表自然和人文地理要素的空间分布、特征及其相互关系,是基本国情的重要组成部分,是重要的基本国情。全国地理国情普查为中国经济发展的科学规划、科学布局、科学发展提供了重要的基础信息。全国地理国情普查应从全局和战略的高度开展,需采用多种技术和手段采集、制作覆盖全国的、内容丰富的、客观真实的、准确权威的地理国情数据库,是对测绘地理信息部门的全面检验,也是推动测绘地理信息事业转型升级的一次重大机遇。

地理国情普查是地理国情监测的首要任务,其成果作为地理国情本底数据,可为我国经济建设和社会发展提供科学的空间依据。本文在简要介绍地理国情普查背景和成果内容的基础上,阐述了地理国情普查成果在宏观决策、减灾防灾、生态文明建设等领域的应用构想。

以恩平市农村集体土地所有权登记发证项目为例,讨论了3S技术在农村集体土地确权中的应用。文章介绍了3S技术在农村土地确权中技术路线,结合项目特点,从调查底图制作、界址点测量、数据库管理等方面阐述了3S技术具体应用,为土地确权工作提供了强有力的工具,大大提高了作业效率;总结了3S技术在土地确权工作中应该注意的问题,以及未来3S技术在土地类项目中的发展趋势。

The overarching goal of this research was to explore accurate methods of mapping irrigated crops, where digital cadastre information is unavailable: (a) Boundary separation by object-oriented image segmentation using very high spatial resolution (2.5 5 m) data was followed by (b) identification of crops and crop rotations by means of phenology, tasselled cap, and rule-based classification using high resolution (15 30 m) bi-temporal data. The extensive irrigated cotton production system of the Khorezm province in Uzbekistan, Central Asia, was selected as a study region. Image segmentation was carried out on pan-sharpened SPOT data. Varying combinations of segmentation parameters (shape, compactness, and color) were tested for optimized boundary separation. The resulting geometry was validated against polygons digitized from the data and cadastre maps, analysing similarity (size, shape) and congruence. The parameters shape and compactness were decisive for segmentation accuracy. Differences between crop phenologies were analyzed at field level using bi-temporal ASTER data. A rule set based on the tasselled cap indices greenness and brightness allowed for classifying crop rotations of cotton, winter-wheat and rice, resulting in an overall accuracy of 80 %. The proposed field-based crop classification method can be an important tool for use in water demand estimations, crop yield simulations, or economic models in agricultural systems similar to Khorezm.

Crop mapping is one major component of agricultural resource monitoring using remote sensing. Yield or water demand modeling requires that both, the total surface that is cultivated and the accurate distribution of crops, respectively is known. Map quality is crucial and influences the model outputs. Although the use of multi-spectral time series data in crop mapping has been acknowledged, the potentially high dimensionality of the input data remains an issue. In this study Support Vector Machines (SVM) are used for crop classification in irrigated landscapes at the object-level. Input to the classifications is 71 multi-seasonal spectral and geostatistical features computed from RapidEye time series. The random forest (RF) feature importance score was used to select a subset of features that achieved optimal accuracies. The relationship between the hard result accuracy and the soft output from the SVM is investigated by employing two measures of uncertainty, the maximum a posteriori probability and the alpha quadratic entropy. Specifically the effect of feature selection on map uncertainty is investigated by looking at the soft outputs of the SVM, in addition to classical accuracy metrics. Overall the SVMs applied to the reduced feature subspaces that were composed of the most informative multi-seasonal features led to a clear increase in classification accuracy up to 4.3%, and to a significant decline in thematic uncertainty. SVM was shown to be affected by feature space size and could benefit from RF-based feature selection. Uncertainty measures from SVM are an informative source of information on the spatial distribution of error in the crop maps.

This paper assessed the use of optical and SAR imagery for crop identification in an operational context with a particular emphasis on actual crop diversity and information delivery time. Fifteen ERS and Radarsat and 3 optical images were used to discriminate agricultural crop types based on dedicated per-parcel classification and photo interpretation schemes. For crop area control, the efficiency concept was introduced as a complementary indicator of classification performance. A set of 6571 parcels were classified into 39 crop types from various combinations of images. The efficiency computed from an independent set of 899 parcels peaked based on a combination of optical images and 3 to 5 SAR images. Moreover, the delivery time of the relevant information was improved when SAR data was included. The hierarchical classification strategy based on nested classifications also improved the operational crop control system for all image combinations. Finally, this research documented the respective contributions of optical and SAR time series for any control system of agricultural land.

For many applied problems in agricultural monitoring and food security, it is important to provide reliable crop classification maps. Satellite imagery is extremely valuable source of data to provide crop maps in a timely way at moderate and high spatial resolution. Information on parcel boundaries that takes into account the spatial context may improve the quality of maps compared to pixel-based classification approaches. In general, parcels may contain several plots with different crops and such situations should be taken into account when using parcel boundaries. In this paper, we aim to compare pixel-based and parcel-based approaches to crop classification from multitemporal optical (Landsat-8) and synthetic-aperture radar (SAR) Sentinel-1 imagery. For this, we propose a parcel-based approach that involves a pixel-based classification map and specifically designed rules to account for several plots within parcel. The study is carried out for the Joint Experiment of Crop Assessment and Monitoring test site in Ukraine covering the Kyiv oblast (North of Ukraine) in 2013-2015, and the Odessa oblast (South of Ukraine) in 2014-2015. We found that pixel-based overall classification accuracy can be increased from 85.32% to 89.40% when using parcel boundaries. Among tested parcel-based approaches, the one that relied on pixel-based classification map and a procedure to select multiple plots within the parcel yielded the best performance.

Rice means life for millions of people and it is planted in many regions of the world. It primarily grows in the major river deltas of Asia and Southeast Asia, such as the Mekong Delta, known as the Rice Bowl of Vietnam, the second-largest rice-producing nation on Earth. However, Latin America, the USA, and Australia have extensive rice-growing regions. In addition, rice is the most rapidly growing source of food in Africa. Rice is therefore of significant importance to food security in an increasing number of low-income food-deficit countries. This review article gives a complementary overview of how remote sensing can support the assessment of paddy rice cultivation worldwide. This article presents and discusses methods for rice mapping and monitoring, differentiating between the results achievable using different sensors of various spectral characteristics and spatial resolution. The remote sensing of rice-growing areas can not only contribute to the precise mapping of rice areas and the assessment of the dynamics in rice-growing regions, but can also contribute to harvest prediction modelling, the analyses of plant diseases, the assessment of rice-based greenhouse gas (methane) emission due to vegetation submersion, the investigation of erosion-control-adapted agricultural systems, and the assessment of ecosystem services in rice-growing areas.

本文以北京顺义区为研究区，研究、探讨利用高光谱遥感数据，通过逐级分层分类方法进行农作物信息提取与挖掘的基本思路和步骤。该方法面向应用目标，将复杂的信息提取过程分为相对简单的子过程，每个子过程根据拟提取的目标不同而选择不同特征参数和信息提取方法，从而实现有效地利用高光谱数据丰富的信息，提高了信息提取的精度目的。

在传统的可见光与红外波段基础上增加红边波段(690~730 nm),是当前高分辨卫星传感器研制的明显趋势。德国RapidEye卫星携带有红边波段传感器,该文基于黑龙江省北安市东胜乡2014年7月27日的RapidEye遥感数据,采用监督分类的方法,通过计算有红边参与条件下、无红边参与条件下,玉米、大豆及其他3种地物类型的可分性测度、分类精度及景观破碎度等指标,比较分析了2种波段组合方式下的红边波段对农作物面积提取精度的影响。其中,监督分类的训练样本是以覆盖研究区的2 km×2 km格网为基本单元,在玉米和大豆面积比例等概率原则下,选取了10个网格作为训练样本,样方内作物的识别采用目视解译的方式完成。精度验证是采用覆盖研究区的农作物面积本底调查结果评价的,本底调查数据是在5 m空间分辨率Rapideye数据初步分类基础上,根据多时相Landsat8/OLI(Operational Land Imager)数据季节变化规律,结合地面调查,采用目视修正的方法完成。结果表明,有红边参与的玉米、大豆和其他3种地物类型识别的总体精度为88.4%,Kappa系数为0.81,玉米、大豆和其他3种地物类型的制图精度分别为93.1%,86.0%和87.3%；没有红边参与的3种地物识别的总体精度为81.7%,Kappa系数为0.71,玉米、大豆和其他3种地区类型的制图精度分别为83.9%,73.4%和84.6%；通过引入红边波段,3种地物的总体识别精度提高了6.7百分点,玉米、大豆和其他3种地物类型的识别精度分别提高了9.2百分点,12.6百分点和2.7百分点。利用JeffriesMatusita方法计算了3种地物的可分性测度,玉米-大豆、玉米-其他、大豆-其他的可分性测度分别由0.84变为1.73、1.37变为1.81、1.27变为1.29；采用破碎度指数计算了景观破碎度,地块数量减少了69.2%,平均地块面积增加了2.2倍,平均地块周长增加了60.50%,地块面积与周长比增加了1.0倍。由上述研究结果可以看出,通过红边波段的引入,增加了地物的间的可分性测度,减少了“椒盐”效应造成的景观破碎度的增加,农作物面积识别整体精度得到了提高。目前搭载红边波段的卫星载荷越来越多,即将发射的国产卫星也拟增加红边波段提高作物识别能力,该文研究结果将为国产红边卫星数据在农业上的应用提供参考。

Rice monitoring and production estimation has special significance to China, as rice is the staple grain and accounts for 42% of the crop production in this country. Radar remote sensing is appropriate for monitoring rice because the areas where this crop is cultivated are often cloudy and rainy. Synthetic Aperture Radar (SAR) is thus anticipated to be the dominant high-resolution remote sensing data source for agricultural applications in tropical and subtropical regions. It also provides revisit schedules suitable for agricultural monitoring. This paper presents the results of a study examining the backscatter behavior of rice as a function of time using multitemporal RADARSAT data acquired in 1996 and 1997. A rice-type distribution map was produced, showing four types of rice with different life spans ranging from 80 days to 120 125 days. The life span of a rice crop has significant impact on the yield, as well as on the taste and quality of the rice, with the longer growing varieties having the best taste and the highest productivity. The rice production of three counties and two administrative regions, totaling 5000 km 2, was estimated in this study. The accuracy of the rice classification was found to be 91% (97% after postclassification filtering) providing confidence that multitemporal RADARSAT data is capable of rice mapping. An empirical growth model was then applied to the results of the rice classification, which related radar backscatter values to rice life spans. These life spans could then be used to sum up the production estimates, which were obtained from agronomic models already in use for rice by local agronomists. These models related the yield of rice to their life span based on empirical observations for each type of rice. The resulting productivity estimate could not be compared to any other existing data on yield production for the study-area, but was well received by the local authorities. Based on the studies carried out in the Zhaoqing test site since 1993, it is suggested that rice production estimates require three radar data acquisitions taken at three different stages of crop growth and development. These three growth stages are: at the end of the transplanting and seedling development period, during the ear differentiation period, and at the beginning of the harvest period. Alternatively, if multiparameter radar data is available, only two data acquisitions may be needed. These would be at the end of the transplanting and seedling development period, and at the beginning of the harvest period. This paper also proposes an operational scenario for rice monitoring and production estimation.

农作物遥感分类是农作物种植面积估算的重要核心问题,是提高农作物种植面积估算精度的关键研究内容。特征变量的选择是农作物遥感分类的重要步骤,有效地使用多种特征变量是提高农作物遥感分类精度的关键。随着多源数据获取的更加容易,电磁波谱特征、空间特征、时间特征以及辅助数据特征在农作物遥感分类中发挥着重要的作用。本文简要回顾和综合分析了在农作物遥感分类中所使用的各种特征变量,包括多光谱特征、微波散射特征、多源数据特征、高光谱数据特征等电磁波谱特征,以及空间特征、时间特征和辅助数据特征等,并分析了农作物遥感分类特征变量选择方面存在的问题和发展趋势。指出目前农作物遥感分类特征变量选择存在的关键问题主要包括特征变量选择的理论研究不足和综合应用存在缺陷两个方面。未来农作物遥感分类特征选择研究的核心内容主要包括生化组分特征及冠层结构特征等农作物遥感分类新特征变量的挖掘、分类特征变量的综合应用、农作物遥感分类特征变量的敏感性和不确定性研究3个方面。

A framework for automated land-cover classification based on a concept of a classification model was developed and tested. The framework employs a user-specified rule base to describe a classification model, defined as the series of spatial data operations and decisions used in landcover classification. Both evidential and hierarchical inference are supported utilizing a set of spatial data operators. The concept was tested through the development and application of a set of computer programs which support classification models. A rule base, thematic spatial data, and satellite image data were then used to define a classification model for conditions in northeastern Wisconsin. The test model incorporated Landsat Thematic Mapper data, soil texture data, and topographic position data. Classification accuracies and efficiencies using the developed system were then compared to those for supervised maximum-likelihood classifications. The classification model approach resulted in statistically significant, 15 percent improvements in classification accuracy when averaged across different analysts, geographic areas, and years.

该文提出了用高分辨率遥感数据提取水稻种值面积本底数据和用可靠低廉的NOAAAVHRR数据估计水稻种植面积变化趋势的方法。该方法具有运行化的特点,成功地应用于1994年度湖北省早稻种植面积估算。

Variable and feature selection have become the focus of much research in areas of application for which datasets with tens or hundreds of thousands of variables are available. These areas include text processing of internet documents, gene expression array analysis, and combinatorial chemistry. The objective of variable selection is three-fold: improving the prediction performance of the predictors, providing faster and more cost-effective predictors, and providing a better understanding of the underlying process that generated the data. The contributions of this special issue cover a wide range of aspects of such problems: providing a better definition of the objective function, feature construction, feature ranking, multivariate feature selection, efficient search methods, and feature validity assessment methods.

遥感识别多源特征综合和特征优选是提高遥感影像分类精度的关键技术。农作物遥感识别中，识别特征的相对单一和数量过多均会导致作物识别精度不理想。随机森林（random forests）采用分类与回归树（CART）算法来生成分类树，结合了bagging和随机选择特征变量的优点，是一种有效的分类方法。单变量特征选择（univariate feature selection）能够对每一个待分类的特征进行测试，衡量该特征和响应变量之间的关系，根据得分舍弃不好的特征，优选得到的特征用于分类。本文基于随机森林和单变量特征选择，利用多时相光谱信息、植被指数信息、纹理信息及波段差值信息，设计多组分类实验方案，对江苏省泗洪县的高分一号（GF-1）和环境一号（HJ-1A）影像进行分类研究，旨在选择最佳的分类方案对实验区主要农作物进行识别和提取。实验结果表明：（1）多源信息综合的农作物分类精度明显高于单一的原始光谱特征分类，说明不同类型特征的引入能改善分类效果；（2）基于单变量特征选择算法的优选特征分类效果最佳,总体精度97.07%，Kappa系数0.96，表明了特征优选在降低维度的同时，也保证了较高的分类精度。随机森林和单变量特征选择结合的方法可以提高遥感影像的分类精度，为农作物的识别和提取研究提供了有效的方法。

High resolution satellite imagery offers new opportunities for crop monitoring and assessment. A SPOT 5 image with four spectral bands (green, red, near-infrared, and mid-infrared) and 10-m pixel size covering intensively cropped areas in south Texas was evaluated for crop identification. Two images with pixel sizes of 20 m and 30 m were also generated from the original image to simulate coarser resolution satellite imagery. Two subset images covering a variety of crops with different growth stages were extracted from the satellite image and four supervised classification techniques, including minimum distance, Mahalanobis distance, maximum likelihood, and spectral angle mapper, were applied to the 10-m subset images and the two coarser resolution images to identify crop types. The effect of the mid-infrared band on classification was also studied. Accuracy assessment showed that the 10-m, four-band images based on maximum likelihood resulted in the best overall accuracy values of 91% and 87% for the two sites. The 20-m and 30-m images had essentially the same accuracy values as the 10-m images, though the inclusion of the mid-infrared band significantly increased classification results. These results indicate that SPOT 5 multispectral imagery can be a useful data source for identifying crop types and estimating crop areas.

Cropland mapping via remote sensing can provide crucial information for agri-ecological studies. Time series of remote sensing imagery is particularly useful for agricultural land classification. This study investigated the synergistic use of feature selection, Object-Based Image Analysis (OBIA) segmentation and decision tree classification for cropland mapping using a finer temporal-resolution Landsat-MODIS Enhanced time series in 2007. The enhanced time series extracted 26 layers of Normalized Difference Vegetation Index (NDVI) and five NDVI Time Series Indices (TSI) in a subset of agricultural land of Southwest Missouri. A feature selection procedure using the Stepwise Discriminant Analysis (SDA) was performed, and 10 optimal features were selected as input data for OBIA segmentation, with an optimal scale parameter obtained by quantification assessment of topological and geometric object differences. Using the segmented metrics in a decision tree classifier, an overall classification accuracy of 90.87% was achieved. Our study highlights the advantage of OBIA segmentation and classification in reducing noise from in-field heterogeneity and spectral variation. The crop classification map produced at 30 m resolution provides spatial distributions of annual and perennial crops, which are valuable for agricultural monitoring and environmental assessment studies.

The decision tree method has grown fast in the past two decades and its performance in classification is promising. The tree-based ensemble algorithms have been used to improve the performance of an individual tree. In this study, we compared four basic ensemble methods, that is, bagging tree, random forest, AdaBoost tree and AdaBoost random tree in terms of the tree size, ensemble size, band selection (BS), random feature selection, classification accuracy and efficiency in ecological zone classification in Clark County, Nevada, through multi-temporal multi-source remote-sensing data. Furthermore, two BS schemes based on feature importance of the bagging tree and AdaBoost tree were also considered and compared. We conclude that random forest or AdaBoost random tree can achieve accuracies at least as high as bagging tree or AdaBoost tree with higher efficiency; and although bagging tree and random forest can be more efficient, AdaBoost tree and AdaBoost random tree can provide a significantly higher accuracy. All ensemble methods provided significantly higher accuracies than the single decision tree. Finally, our results showed that the classification accuracy could increase dramatically by combining multi-temporal and multi-source data set.

以黑龙江省漠河县为研究区域,采用陆地卫星-8遥感影像为数据源,结合影像的光谱信息和数字高程模型辅助数据,分别采用最大似然分类法(MLC)和随机森林模型法(RFM)对研究区森林植被进行分类,并分析和评价光谱特征变量对模型的重要性、2种分类方法对森林植被类型分类的适用性。结果表明:随机森林分类方法的总体分类精度为81.65%、卡帕(Kappa)系数为0.812。与传统的MLC方法相比,RFM法均提高了3种森林类型的生产者精度和使用者精度,其中针阔混交林精度提高最多。通过分析特征变量的重要性,发现高程、归一化植被指数、红光波段、近红外波段、短波红外波段对模型分类精度有较重要的影响。说明随机森林模型方法结合多源信息是森林植被类型遥感分类的一种有效手段。

With the significantly improved data availability in remote sensing technology,mid-resolution images have become the primary data source for crop sown area estimation in large scale.However,it is still difficult to solve the problems of spectrum heterogeneity in one field and spectra similarity between fields,especially in transitional region by using mid-resolution images.In order to maximally avoid above motioned problems and accurately measure the sown area of winter wheat,this paper developed per-field classification method and tested the method in an urban agriculture region with complex planting structure through several steps:first,digitalizing field boundary from QuickBird image;second,extracting characteristic index including spectrum and texture information as well as vegetation index for each field from the multi-temporal TM images;third,operating support vector machine(SVM) and maximum likelihood classification(MLC) with different field characteristic index;finally,estimating the accuracy of our method.Results show that the per-field classification method has a higher accuracy than per-pixel classification both in amount(estimated sown area of winter wheat divide by reference sown area of winter wheat,Kr) and position(equal to product accuracy,Kp).Although both SVM and MLC could get very high amount and position accuracy(97% and 90% respectively),the estimations of SVM are more stable.The errors of per-field classification mainly happened at the fragmentized parcels.Additionally,characteristic information could enhance the performance of per-field classification.Our method also has an outstanding advantage that no optimum period requires on satellite imagery which could enhance practicability and operationality of our method.