“宝钢湛江项目”的实施对近十年湛江东海岛的地物分布产生剧烈影响,尤其是工业用地。本文基于2013年、2017年和2021年的陆地卫星8号(Landsat-8)数据对湛江东海岛进行地物分类,研究该区域近十年的用地变化趋势。以2013年数据为参照:采...“宝钢湛江项目”的实施对近十年湛江东海岛的地物分布产生剧烈影响,尤其是工业用地。本文基于2013年、2017年和2021年的陆地卫星8号(Landsat-8)数据对湛江东海岛进行地物分类,研究该区域近十年的用地变化趋势。以2013年数据为参照:采用归一化水体指数(Normalized Difference Water Index,NDWI)模型和谱间关系模型实现水陆分离,比对选择分离效果较优者以提取东海岛岸线;对比最大似然法、神经网络法和支持向量机法3种监督分类方法,选择提取地物效果最优者应用于其余数据。基于Google earth在线地图及无人机实测数据构建验证点集,使用混淆矩阵进行精度评价。结果表明:谱间关系模型的水陆分离效果较优,提取海岛岸线的精确度有明显提升;支持向量机法的分类总体精度和Kappa系数最高,分类结果能较好地反映研究区的真实地物分布;汇总三年数据的分类结果,发现用于发展工业的土地面积增长突出且处于持续增长趋势。谱间关系模型与支持向量机法分别实现了对东海岛岸线和地物类型的准确提取,得出近十年研究区的用地变化趋势,能为研究区的用地规划提供参考。展开更多
为精准识别水体信息并实时监测湖泊水体时空特征及其环境特征变化情况,以洞庭湖为例,基于Landsat-8影像数据分别使用改进的归一化差异水体指数(Modified Normalized Difference Water Index,MNDWI)、自动水体提取指数(Automated Water E...为精准识别水体信息并实时监测湖泊水体时空特征及其环境特征变化情况,以洞庭湖为例,基于Landsat-8影像数据分别使用改进的归一化差异水体指数(Modified Normalized Difference Water Index,MNDWI)、自动水体提取指数(Automated Water Extraction Index,AWEI sh)、支持向量机(Support Vector Machine,SVM)、人工神经网络(Artificial Neural Networks,ANNs)、随机森林(Random Forest,RF)等5种方法提取枯、丰水期水体分布信息,通过精度指标评价及影响因素分析,旨在找到提取精度高、鲁棒性强的水体提取方法。结果表明:5种方法中SVM法水体提取总精度最高且泛化能力良好。研究成果可为各方法适用性提供一定参考,并通过定量分析揭示漏提率在提取精度评价指标中的重要性。展开更多
The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeope...The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.展开更多
ET （Evapotranspiration） is one of the climate elements, which plays an important role in water balance, and effects on the ecosystem of any region. Therefore, many mathematical equations and algorithms have been fou...ET （Evapotranspiration） is one of the climate elements, which plays an important role in water balance, and effects on the ecosystem of any region. Therefore, many mathematical equations and algorithms have been found and designed to calculate and estimate values of evapotranspiration. Calculation methods are either based on data from meteorological stations or using other sources of data where the area is lacking from meteorological stations. Remote sensing data are one of the important sources and techniques to estimate many climate elements including evapotranspiration. The selected study area is located in Tatra Mountains on the borders between Poland and Slovakia. Tatra Mountains are the most valuable areas in Poland and Slovakia. The main objective of current study is to estimate the spatial variation of ET using SEBAL algorithm and Landsat-8 imagery. The analysis is carried out using Landsat-8 （OLI/TIRS） data, ASTER GDEM and reference weather parameters. Sixteen ERDAS models are prepared to calculate the various parameters related to solar radiation. The models are prepared to calculate the values of surface radiance surface reflectance, surface albedo, NDVI, LAI, surface emissivity, surface temperature, net radiation, soil heat flux, sensible heat flux, latent heat flux, which are consequently used to calculate the hourly and daily evapotranspiration in study area. Results ofpixel wise calculations show the values of surface temperature which are varied from 6.2℃ at mountain shadow areas to 34.6 ℃ at bare rocks and bare land area, while the spatial variation of ET at different land covers shows the hourly ET ranged from 0 to 0.72 mm/hr, while the daily ET varied from 0.0 to 17.0 mm/day. Results show clear relation between land use/land cover and solar radiation parameters and impact of vegetation cover on the ET values in pixel wise domain.展开更多
提出了一种对Landsat-8和Worldview-2协同后的岩性分类方法。首先对Landsat-8和Worldview-2影像进行协同:在对Landsat-8全色波段与其多光谱进行自协同后,与Worldview-2多光谱第8波段数据协同,将协同后的Landsat-8中短波红外数据与Worldv...提出了一种对Landsat-8和Worldview-2协同后的岩性分类方法。首先对Landsat-8和Worldview-2影像进行协同:在对Landsat-8全色波段与其多光谱进行自协同后,与Worldview-2多光谱第8波段数据协同,将协同后的Landsat-8中短波红外数据与Worldview-2数据进行叠加,得到最后协同结果。对协同后的数据进行岩性分类:利用基于最大似然法(maximum likelihood,ML)进行初始分类,由马尔科夫随机场法(Markov Random Field,MRF)对结果进行优化得到最终分类结果。采用新疆西昆仑地区遥感数据进行了实验,结果证实协同后数据的分类结果具有更高的分类精度。展开更多
文摘“宝钢湛江项目”的实施对近十年湛江东海岛的地物分布产生剧烈影响,尤其是工业用地。本文基于2013年、2017年和2021年的陆地卫星8号(Landsat-8)数据对湛江东海岛进行地物分类,研究该区域近十年的用地变化趋势。以2013年数据为参照:采用归一化水体指数(Normalized Difference Water Index,NDWI)模型和谱间关系模型实现水陆分离,比对选择分离效果较优者以提取东海岛岸线;对比最大似然法、神经网络法和支持向量机法3种监督分类方法,选择提取地物效果最优者应用于其余数据。基于Google earth在线地图及无人机实测数据构建验证点集,使用混淆矩阵进行精度评价。结果表明:谱间关系模型的水陆分离效果较优,提取海岛岸线的精确度有明显提升;支持向量机法的分类总体精度和Kappa系数最高,分类结果能较好地反映研究区的真实地物分布;汇总三年数据的分类结果,发现用于发展工业的土地面积增长突出且处于持续增长趋势。谱间关系模型与支持向量机法分别实现了对东海岛岸线和地物类型的准确提取,得出近十年研究区的用地变化趋势,能为研究区的用地规划提供参考。
基金the Natural Science Foundation of Shandong Province(ZR2021QE289)State Key Laboratory of Electrical Insulation and Power Equipment(EIPE22201).
文摘The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power grid.Machine vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.
文摘ET （Evapotranspiration） is one of the climate elements, which plays an important role in water balance, and effects on the ecosystem of any region. Therefore, many mathematical equations and algorithms have been found and designed to calculate and estimate values of evapotranspiration. Calculation methods are either based on data from meteorological stations or using other sources of data where the area is lacking from meteorological stations. Remote sensing data are one of the important sources and techniques to estimate many climate elements including evapotranspiration. The selected study area is located in Tatra Mountains on the borders between Poland and Slovakia. Tatra Mountains are the most valuable areas in Poland and Slovakia. The main objective of current study is to estimate the spatial variation of ET using SEBAL algorithm and Landsat-8 imagery. The analysis is carried out using Landsat-8 （OLI/TIRS） data, ASTER GDEM and reference weather parameters. Sixteen ERDAS models are prepared to calculate the various parameters related to solar radiation. The models are prepared to calculate the values of surface radiance surface reflectance, surface albedo, NDVI, LAI, surface emissivity, surface temperature, net radiation, soil heat flux, sensible heat flux, latent heat flux, which are consequently used to calculate the hourly and daily evapotranspiration in study area. Results ofpixel wise calculations show the values of surface temperature which are varied from 6.2℃ at mountain shadow areas to 34.6 ℃ at bare rocks and bare land area, while the spatial variation of ET at different land covers shows the hourly ET ranged from 0 to 0.72 mm/hr, while the daily ET varied from 0.0 to 17.0 mm/day. Results show clear relation between land use/land cover and solar radiation parameters and impact of vegetation cover on the ET values in pixel wise domain.
文摘提出了一种对Landsat-8和Worldview-2协同后的岩性分类方法。首先对Landsat-8和Worldview-2影像进行协同:在对Landsat-8全色波段与其多光谱进行自协同后,与Worldview-2多光谱第8波段数据协同,将协同后的Landsat-8中短波红外数据与Worldview-2数据进行叠加,得到最后协同结果。对协同后的数据进行岩性分类:利用基于最大似然法(maximum likelihood,ML)进行初始分类,由马尔科夫随机场法(Markov Random Field,MRF)对结果进行优化得到最终分类结果。采用新疆西昆仑地区遥感数据进行了实验,结果证实协同后数据的分类结果具有更高的分类精度。
