AN EXPERIMENT IN AUTOMATED INTERPRETATION OF REMOTE SENSING IMAGERY

Algorithms, designed for digital image processing in standard mainframe computers and representing sequential stages in a land-use classification procedure, are used to produce maps of agricultural crop types from multispectral satellite imagery. Pixel reflectance values are first grouped according to an unsupervised “rapid classification algorithm,” or data compression procedure. Mean reflectance values of the resulting classes then go into a supervised “sequential clustering algorithm” where classes are refined according to training value and other parameter inputs. The objective is to increase the accessibility of automated image interpretation while balancing classification accuracy and processing time. Translated from: Vestnik Moskovskogo Universiteta, geografiya, 1984, No. 4, pp. 63-69.     

Improving crop type determination using satellite imagery: A study for the Regione del Veneto,Italy

The Regione del Veneto (Italy) is cooperating with the University of California, Santa Barbara and other researchers in Italy and the U.S.A. to develop a system of econometric crop production modeling. Five crops are to be included in this project: small grains (wheat and barley), corn, sugar beets, soybeans, orchards and vineyards. A critical part of the crop yield modeling process is the identification of crops using multispectral satellite data. This paper explores two strategies to improve crop classification accuracies: (1) use of ancillary data stored in digital format and (2) use of multitemporal data. Ancillary information stored on digital files were used in this research to remove (mask) non‐agricultural areas from satellite image data. Comparison between the classification of masked and unmasked images showed that improvement ranged from 3% to 26% depending on crop type. The multidate classification was performed by compiling an image of transformed spectral bands and three TM‐5 bands. The transformed bands were TM band 4 over TM band 3. Based on the work conducted in this study it is clear that crop type determination from satellite imagery is possible for small field agricultural areas such as those found in Italy.     

Integration of optical and Synthetic Aperture Radar (SAR) imagery for delivering operational annual crop inventories

Agriculture plays a critical role within Canada’s economy and, as such, sustainability of this sector is of high importance. Targeting and monitoring programs designed to promote economic and environmental sustainability are a vital component within Canada’s agricultural policy. A hierarchy of land information, including up to date information on cropping practices, is needed to measure the impacts of programs on land use decision-making and to gauge the environmental and economic benefits of these investments. A multi-year, multi-site research activity was completed to develop a robust methodology to inventory crops across Canada’s large and diverse agricultural landscapes. To move towards operational implementation the methodology must deliver accurate crop inventories, with consistency and reliability. In order to meet these operational requirements and to mitigate risk associated with reliance on a single data source, the methodology integrated both optical and Synthetic Aperture Radar (SAR) imagery. The results clearly demonstrated that multi-temporal satellite data can successfully classify crops for a variety of cropping systems present across Canada. Overall accuracies of at least 85% were achieved, and most major crops were also classified to this level of accuracy. Although multi-temporal optical data would be the preferred data source for crop classification, a SAR-optical dataset (two Envisat ASAR images and one optical image) provided acceptable accuracies and will mitigate risk associated with operational implementation. The preferred dual-polarization mode would be VV–VH. Not only were these promising classification results repeated year after year, but the target accuracies were met consistently for multiple sites across Canada, all with varying cropping systems.     

Geostatistical and visualization analysis of crop suitability for diversification in sub-mountain area of Punjab,North-West India

This study presents a Geographic Information System (GIS)-based geostatistical and visualization analysis of crop suitability in two blocks of sub-mountain area of Punjab under diversification programme. It combines the limitation approach of land capability classification, productivity potential evaluation procedure and crop suitability evaluation framework of FAO. Two blocks from the sub mountain Siwalik region of Punjab viz., Mahalpur and Garhshankar were selected. This study evaluates the capabilities of the study area for traditional crops like wheat, paddy and maize, and recently introduced crops like sugarcane, sunflower, pea, rapeseed-mustard, potatoes and kinnow for agricultural diversification. The suitability of the crops has been worked out at the village level. About 35–40 per cent of total area mostly in Siwallik hills is not fit for growing any type of crop. Sandy texture, uneven topography, moderately steep slopes and excessive drainage are responsible for unsuitability of this area. The GIS based suitability analysis for traditional crops as well as for new crops, under diversification of agriculture has been undertaken. The geostatistical analysis points towards suitability of relatively large areas for new crops like sunflower, potato, pea (green) and sugarcane. Forty three and 14 per cent of total area has been found highly suitable and suitable respectively for growing green pea - a cash crop. Thirty three per cent of total area is suitable for growing kinnow fruit. The success of diversification programme is subject to logical government policy in terms of providing cold storage, food processing facility and marketing infrastructure.     

Monitoring US agriculture: the US Department of Agriculture,National Agricultural Statistics Service,Cropland Data Layer Program

The National Agricultural Statistics Service (NASS) of the US Department of Agriculture (USDA) produces the Cropland Data Layer (CDL) product, which is a raster-formatted, geo-referenced, crop-specific, land cover map. CDL program inputs include medium resolution satellite imagery, USDA collected ground truth and other ancillary data, such as the National Land Cover Data set. A decision tree-supervised classification method is used to generate the freely available state-level crop cover classifications and provide crop acreage estimates based upon the CDL and NASS June Agricultural Survey ground truth to the NASS Agricultural Statistics Board. This paper provides an overview of the NASS CDL program. It describes various input data, processing procedures, classification and validation, accuracy assessment, CDL product specifications, dissemination venues and the crop acreage estimation methodology. In general, total crop mapping accuracies for the 2009 CDLs ranged from 85% to 95% for the major crop categories.     

农作物长势综合遥感监测方法

作物收获之前进行大范围作物生长状况评价 ,可以尽早的获得有关作物产量信息。介绍了中国农情遥感监测系统的综合作物长势监测方法。以遥感数据标准化处理、云标识、云污染去除和非耕地去除为基础 ,生成质量一致的遥感数据产品集 ,提取区域作物生长过程。作物长势监测分为实时作物长势监测和作物生长趋势分析。实时的作物长势监测可以定性和定量地在空间上分析作物生长状况 ,分级显示作物生长状况 ,分区域统计水田和旱地中不同长势占的比重。作物生长趋势分析可以进行年际间的生长过程对比 ,从时间轴上反映作物持续生长的差异性 ,统计全国、主产区、省和区划单元 4个尺度的耕地、水田、旱地作物生长过程曲线年际间差异 ,从而为早期的产量预测提供信息。通过处理流程的系统化 ,建设了运行化的作物长势遥感监测分析系统 ,为用户构建了综合的作物实时生长状况 ,苗情的生长趋势分析环境。同时可以依据野外地面实测信息对遥感监测结果进行标定和检验。 1998年以来 ,系统在满足日常运行的前提下 ,技术方法逐渐改进和完善 ,监测结果的精度和可靠性不断得到提高。     

An ensemble pansharpening approach for finer-scale mapping of sugarcane with Landsat 8 imagery

We tested the effects of three fast pansharpening methods – Intensity-Hue-Saturation (IHS), Brovey Transform (BT), and Additive Wavelet Transform (AWT) – on sugarcane classification in a Landsat 8 image (bands 1–7), and proposed two ensemble pansharpening approaches (band stacking and band averaging) which combine the pixel-level information of multiple pansharpened images for classification. To test the proposed ensemble pansharpening approaches, we classified “sugarcane” and “other” land cover in the unsharpened Landsat multispectral image, the individual pansharpened images, and the band-stacked and band-averaged ensemble images using Support Vector Machines (SVM), and assessed the classification accuracy of each image. Of the individual pansharpened images, the AWT image achieved higher classification accuracy than the unsharpened image, while the IHS and BT images did not. The band-stacked ensemble images achieved higher classification accuracies than the unsharpened and individual pansharpened images, with the IHS-BT-AWT band-stacked image producing the most accurate classification result, followed by the IHS-BT band-stacked image. The ensemble images containing averaged pixel values from multiple pansharpened images achieved lower classification accuracies than the band-stacked ensemble images, but most still had higher accuracies than the unsharpened and individual pansharpened results. Our results indicate that ensemble pansharpening approaches have the potential to increase classification accuracy, at least for relatively simple classification tasks. Based on the results of the study, we recommend further investigation of ensemble pansharpening for image analysis (e.g. classification and regression tasks) in agricultural and non-agricultural environments.     

中国农情遥感速报系统

介绍了中国农情遥感速报系统的建设情况 ,系统内容包括农作物长势监测、农作物种植面积监测、农作物单产预测与粮食产量估算、作物时空结构监测和粮食供需平衡预警等。简要介绍了 1998年以来中国农情遥感速报系统在监测内容与监测范围、监测频率、技术发展以及质量控制与过程检验体系建立等方面的进展 ,并就中国农情遥感速报系统的发展方向提出了展望。     

面向农作物监测的遥感信息处理技术研究

以区域性主要农作物种类识别、长势分析与产量估算及农业种植结构现状监测为主要研究对象,开展适于农业管理部门业务化运行的卫星遥感信息处理的关键技术研究。从分析主要作物类型识别的遥感物理依据入手,提出了卫星遥感数据处理及专题信息提取的基本技术框架、主要农作物类型及种植面积信息的提取方法以及主要粮食作物长势分析和产量估算模型,并对结果进行了简要的精度分析。     

煤矿关闭前后土地利用RS与GIS动态监测

采用遥感和GIS技术来监测矿区土地利用动态情况,对于矿区土地资源合理利用、科学管理和综合治理具有重要的意义。本文从数据的获取、遥感影像处理、年度变化信息提取、土地利用转移矩阵的建立等过程来分析土地利用RS与GIS动态监测过程。研究结果表明煤矿关闭前土地利用类型之间相互转换明显,呈现出建设用地和水域面积增加的趋势;关闭后水域面积趋于稳定,而农用地增加,土地利用集约化水平得到提高。总体来说矿区土地利用粗放,没有一个合理的土地利用结构方向,缺乏一个土地利用总体规划,但通过长期复垦整治,在一定程度上缓解了当地人地矛盾。     

Analytical Modelling of Positional and Thematic Uncertainties in the Integration of Remote Sensing and Geographical Information Systems

This paper describes three aspects of uncertainty in geographical information systems (GIS) and remote sensing. First, the positional uncertainty of an area object in a GIS is discussed as a function of positional uncertainties of line segments and boundary line features. Second, the thematic uncertainty of a classified remote sensing image is described using the probability vectors from a maximum likelihood classification. Third, the "S-band" model is used to quantify uncertainties after combining GIS and remote sensing data.     

综合多特征的Landsat 8时序遥感图像棉花分类方法

传统的多时相遥感图像分类大多拘泥于单一特征,本文基于多时相的Landsat 8遥感数据,开展了综合多特征的特征提取与特征选择方法研究。综合了NDVI时间序列、最佳时相反射率光谱特征以及纹理特征作为初始分类特征,并采用基于属性重要度的粗糙集特征选择算法对其进行特征约简。分类结果表明:(1)利用初始分类特征,分类的总体精度达到92.81%,棉花提取精度达87.4%,与仅利用NDVI时间序列相比,精度分别提高5.53%和5.05%;(2)利用粗糙集选择后的特征分类,分类总体精度可达93.66%,棉花分类精度达92.73%,与初始分类特征提取结果相比,棉花分类精度提高5.33%。基于属性重要度的粗糙集特征选择不仅提高了分类精度,同时有效降低了分类器的计算复杂度。     

面向多分辨率层次结构的遥感影像分析方法

将输入数据源经过扩展分段处理，形成具有不同分辨率层次结构的影像目标。通过构建同层次目标之间、不同分辨率层次目标之间的关系，将目标识别、目标语义提取以及影像信息提取集成在单一的平台完成。     

基于证据理论的水稻遥感信息提取方法研究

水稻播种面积是农业管理部门关心的重要问题之一。本文介绍了证据理论在遥感图像分类上的应用,并以汉川市为示范区,采用2002年TM遥感影像,在GIS技术支持下,通过建模运算,剔除不可能是水稻的像元。然后将证据理论用于影像分类,将影像初次分类结果,与参考图对照,将不满足要求的区域提取出来,再次进行第二次分类。将第二次分类结果与参考图对照,显示分类效果满足要求;若不满足要求,可继续进行再次分类,直到分类效果满意为止。将两次分类结果中的水稻信息进行叠加,提取出水稻遥感信息,经检验精度达到91.39%。     

水稻种植面积估计的运行化遥感方法

该文提出了用高分子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。     

Object-based urban land cover classification using rule inheritance over very high-resolution multisensor and multitemporal data

Very high spatial and temporal resolution remote sensing data facilitate mapping highly complex and diverse urban environments. This study analyzed and demonstrated the usefulness of combined high-resolution aerial digital images and elevation data, and its processing using object-based image analysis for mapping urban land covers and quantifying buildings. It is observed that mapping heterogeneous features across large urban areas is time consuming and challenging. This study presents and demonstrates an approach for formulating an optimal land cover classification rule set over small representative training urban area image, and its subsequent transfer to the multisensor, multitemporal images. The classification results over the training area showed an overall accuracy of 96%, and the application of rule set to different sensor images of other test areas resulted in reduced accuracies of 91% for the same sensor, 90% and 86% for the different sensors temporal data. The comparison of reference and classified buildings showed ±4% detection errors. Classification through a transferred rule set reduced the classification accuracy by about 5%–10%. However, the trade-off for this accuracy drop was about a 75% reduction in processing time for performing classification in the training area. The factors influencing the classification accuracies were mainly the shadow and temporal changes in the class characteristics.     

Classifying a high resolution image of an urban area using super-object information

In this study, a multi-scale approach was used for classifying land cover in a high resolution image of an urban area. Pixels and image segments were assigned the spectral, texture, size, and shape information of their super-objects (i.e. the segments that they are located within) from coarser segmentations of the same scene, and this set of super-object information was used as additional input data for image classification. The accuracies of classifications that included super-object variables were compared with the classification accuracies of image segmentations that did not include super-object information. The highest overall accuracy and kappa coefficient achieved without super-object information was 78.11% and 0.727%, respectively. When single pixels or fine-scale image segments were assigned the statistics of their super-objects prior to classification, overall accuracy increased to 84.42% and the kappa coefficient increased to 0.804.     

深度学习农作物分类的弱样本适用性

基于大数据驱动的深度学习挖掘图像数据的规律和层次已成为遥感影像解译的研究热点。海量标签样本是训练深度学习模型的前提条件,但成本昂贵的人工标记样本限制了深度学习技术在遥感领域的应用。本文提出了一种基于弱样本的深度学习模型农作物分类策略：以GF-1影像为数据源,将传统分类器SVM分类结果视为弱样本,训练深度卷积网络模型DCNN (Deep Convolutional Neural Networks),获取辽宁省水稻和玉米的空间分布,分析弱样本的适用性。结果显示：测试集总体精度达到0.90,水稻和玉米F1分数分别为0.81和0.90;在不同地形地貌、复杂种植结构的农业景观下均表现出良好的分类效果;与SVM结果的空间一致性为0.90;当弱样本最大面积误差比例小于0.36时,弱样本仍适用于DCNN作物分类,结果的总体精度保持在0.86以上。综上,该策略一定程度上消除了深度学习模型对大量人工标记样本高度依赖的局限性,为实现大尺度农作物遥感分类提供了一种新途径。     

Crop classification from full-year fully-polarimetric L-band UAVSAR time-series using the Random Forest algorithm

Accurate and timely information on the distribution of crop types is vital to agricultural management, ecosystem services valuation and food security assessment. Synthetic Aperture Radar (SAR) systems have become increasingly popular in the field of crop monitoring and classification. However, the potential of time-series polarimetric SAR data has not been explored extensively, with several open scientific questions (e.g. the optimal combination of image dates for crop classification) that need to be answered. In this research, the usefulness of full year (both 2011 and 2014) L-band fully-polarimetric Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data in crop classification was fully investigated over an agricultural region with a heterogeneous distribution of crop categories. In total, 11 crop classes including tree crops (almond and walnut), forage crops (grass, alfalfa, hay, and clover), a spring crop (winter wheat), and summer crops (corn, sunflower, tomato, and pepper), were discriminated using the Random Forest (RF) algorithm. The SAR input variables included raw linear polarization channels as well as polarimetric parameters derived from Cloude-Pottier (CP) and Freeman-Durden (FD) decompositions. Results showed clearly that the polarimetric parameters yielded much higher classification accuracies than linear polarizations. The combined use of all variables (linear polarizations and polarimetric parameters) produced the maximum overall accuracy of 90.50 % and 84.93 % for 2011 and 2014, respectively, with a significant increase of approximately 8 percentage points compared with linear polarizations alone. The variable importance provided by the RF illustrated that the polarimetric parameters had a far greater influence than linear polarizations, with the CP parameters being much more important than the FD parameters. The most important acquisitions were the images dated during the peak biomass stage (July and August) when the differences in structural characteristics between most crops were the largest. At the same time, the images in spring (April and May) and autumn (October) also contributed to the crop classification since they respectively provided unique information for discriminating fruit crops (almond and walnut) as well as summer crops (corn, sunflower, and tomato). As a result, the combined use of only four acquisitions (dated May, July, August, and October for 2011 and April, June, August, and October for 2014) was adequate to achieve a nearly-optimal overall accuracy. In light of the promising classification accuracies demonstrated in this research, it becomes increasingly viable to provide accurate and up-to-date crops inventories over large areas based solely on multitemporal polarimetric SAR.     

单变量特征选择的苏北地区主要农作物遥感识别

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。