为提高对森林火烧迹地的检测精度,文章利用火灾后Sentinel-2卫星影像,提出一种基于改进PSPNet的森林火烧迹地检测模型。该模型以带空洞卷积的ResNet34作为主干网络,并在主干网络内部融合RFB(Receptive Field Block)模块和ULSAM(Ultra Li...为提高对森林火烧迹地的检测精度,文章利用火灾后Sentinel-2卫星影像,提出一种基于改进PSPNet的森林火烧迹地检测模型。该模型以带空洞卷积的ResNet34作为主干网络,并在主干网络内部融合RFB(Receptive Field Block)模块和ULSAM(Ultra Lightweight Subspace Attention Module)模块来增强其特征提取能力;最后利用跳跃连接使模型的解码器部分充分利用主干网络输出的四个层级特征图。实验结果表明改进PSPNet模型的平均交并比和总体准确率分别为91.86%和96.89%,相比PSPNet,分别提高1.52%和0.67%。与其他语义分割模型相比,改进模型得到的分割结果细节更加丰富,且具有较好的泛化性能。展开更多
Soil water management plays an important role in the response of kiwi plants (Actinidia deliciosa A. Chev.). In GuimarSes district soil moisture content is monitored in kiwifi'uit orchard as a routine parameter. Dr...Soil water management plays an important role in the response of kiwi plants (Actinidia deliciosa A. Chev.). In GuimarSes district soil moisture content is monitored in kiwifi'uit orchard as a routine parameter. Drip irrigation system is the method used. This crop tends to have high water requirements and extends over a wide area in Portugal, requiring innovative solutions to achieve better benefits. A method that correlates soil and crop conditions with the parameters of remote sensing was established in this study. To assess the level of accuracy of soil moisture measurements from satellites, it is important to compare satellite image with ground real data (namely the frequency domain reflectometry (FDR), Diviner 2000). The combination of multispectral satellite images produces an image representative of vegetation vigour, density and health. In this study, Landsat satellite images (2011 and 2013) are used and vegetation indexes are calculated for different periods of time, using the software Idrisi Taiga. The information of vegetation indexes is crossed with data of soil moisture, in situ, to establish a correlation between both of them. Thus, it allows to improve the soil water content monitoring, in particular for the soil water balance optimization and its effect on kiwi biornass production.展开更多
How to deal with geometric distortion is an open problem when using the massive amount of satellite images at a national or global scale, especially for multi-temporal image analysis. In this paper, an algorithm is pr...How to deal with geometric distortion is an open problem when using the massive amount of satellite images at a national or global scale, especially for multi-temporal image analysis. In this paper, an algorithm is proposed to automatically rectify the geometric distortion of time-series CCD multi- spectral data of small constellation for environmental and disaster mitigation (HJ-1A/B) which was launched by China in 2008. In this algorithm, the area-based matching method was used to automatically search tie points firstly, and then the polynomial function was introduced to correct the systematic errors caused by the satellite motion along the roll, pitch and yaw direction. The improved orthorectification method was finally used to correct pixel displacement caused by off-nadir viewing of topography, which are random errors in the images and cannot be corrected by the polynomial equation. Nine scenes of level 2 HJ CCD images from one path/row were taken as the warp images to test the algorithm. The test result showed that the overall accuracy of the proposed algorithm was within 2 pixels (the average residuals were 37.8 m, and standard deviations were 19.8 m). The accuracies of 45.96% validation points (VPs) were within 1 pixel and 90.33% VPs were within 2 pixels. The discussion showed that three main factors including the distortion patterns of HJ CCD images, pereent of cloud cover and the varying altitude of the satellite orbit may affect the search of tie points and the accuracy of results. Although the influence of varying altitude of the satellite orbits is less than the other factors, it is noted that detailed satellite altitude information should be given in the future to get a more precise result. The proposed algorithm should be an efficient tool for the geo-correction of HJ CCD multi-spectral images.展开更多
文摘针对两个特征波段组成的植被指数存在的饱和以及植物类型依赖问题,利用便携式地物光谱仪(analytical spectral devices,ASD)和哨兵2号多光谱卫星(Sentinel 2,S2)数据,使用改进的距离投影比值指数(improved distance projection ratio index,DPRI2)建立新叶片等效水厚度(leaf equivalent water thickness,LEWT)反演模型,进而反演冠层等效水厚度(canopy equivalent water thickness,CEWT)。研究表明:①R语言随机森林(random forest,RF)算法可减少特征波段选取过程中人为因素;②DPRI2结构简单,能充分反映特征波段之间角度、距离、投影三者组合关系,有利于提高LEWT、CEWT反演精度;③DPRI2不受植被类型限制,适用于具有多种植被类型的研究区CEWT反演。通过遥感手段监测CEWT,有利于探究植被在区域水文循环中的调控机制,以及科学评估区域水资源储量。
文摘Soil water management plays an important role in the response of kiwi plants (Actinidia deliciosa A. Chev.). In GuimarSes district soil moisture content is monitored in kiwifi'uit orchard as a routine parameter. Drip irrigation system is the method used. This crop tends to have high water requirements and extends over a wide area in Portugal, requiring innovative solutions to achieve better benefits. A method that correlates soil and crop conditions with the parameters of remote sensing was established in this study. To assess the level of accuracy of soil moisture measurements from satellites, it is important to compare satellite image with ground real data (namely the frequency domain reflectometry (FDR), Diviner 2000). The combination of multispectral satellite images produces an image representative of vegetation vigour, density and health. In this study, Landsat satellite images (2011 and 2013) are used and vegetation indexes are calculated for different periods of time, using the software Idrisi Taiga. The information of vegetation indexes is crossed with data of soil moisture, in situ, to establish a correlation between both of them. Thus, it allows to improve the soil water content monitoring, in particular for the soil water balance optimization and its effect on kiwi biornass production.
基金funded jointly by the "Hundred Talents" Project of Chinese Academy of Sciences (CAS)the Hundred Talent Program of Sichuan Province, International Cooperation Partner Program of Innovative Team, CAS (Grant No. KZZD-EW-TZ-06)+1 种基金the Knowledge Innovation Program of the Chinese Academy of Sciences (Grant No. KZCX2-YW-QN313)the Strategic Priority Research Program-Climate Change: Carbon Budget and Related Issues (Grant No. XDA05050105)
文摘How to deal with geometric distortion is an open problem when using the massive amount of satellite images at a national or global scale, especially for multi-temporal image analysis. In this paper, an algorithm is proposed to automatically rectify the geometric distortion of time-series CCD multi- spectral data of small constellation for environmental and disaster mitigation (HJ-1A/B) which was launched by China in 2008. In this algorithm, the area-based matching method was used to automatically search tie points firstly, and then the polynomial function was introduced to correct the systematic errors caused by the satellite motion along the roll, pitch and yaw direction. The improved orthorectification method was finally used to correct pixel displacement caused by off-nadir viewing of topography, which are random errors in the images and cannot be corrected by the polynomial equation. Nine scenes of level 2 HJ CCD images from one path/row were taken as the warp images to test the algorithm. The test result showed that the overall accuracy of the proposed algorithm was within 2 pixels (the average residuals were 37.8 m, and standard deviations were 19.8 m). The accuracies of 45.96% validation points (VPs) were within 1 pixel and 90.33% VPs were within 2 pixels. The discussion showed that three main factors including the distortion patterns of HJ CCD images, pereent of cloud cover and the varying altitude of the satellite orbit may affect the search of tie points and the accuracy of results. Although the influence of varying altitude of the satellite orbits is less than the other factors, it is noted that detailed satellite altitude information should be given in the future to get a more precise result. The proposed algorithm should be an efficient tool for the geo-correction of HJ CCD multi-spectral images.