High-Resolution Remote Sensing Imagery for the Recognition of Traditional Villages

Traditional Chinese villages,vital carriers of traditional culture,have faced significant alterations due to urbanization in recent years,urgently necessitating artificial intelligence data updates.This study integrates high spatial resolution remote sensing imagery with deep learning techniques,proposing a novel method for identifying rooftops of traditional Chinese village buildings using high-definition remote sensing images.Using 0.54 m spatial resolution imagery of traditional village areas as the data source,this method analyzes the geometric and spectral image characteristics of village building rooftops.It constructs a deep learning feature sample library tailored to the target types.Employing a semantically enhanced version of the improved Mask R-CNN(Mask Region-based Convolutional Neural Network)for building recognition,the study conducts experiments on localized imagery from different regions.The results demonstrated that the modified Mask R-CNN effectively identifies traditional village building rooftops,achieving an of 0.7520 and an of 0.7400.It improves the current problem of misidentification and missed detection caused by feature heterogeneity.This method offers a viable and effective approach for industrialized data monitoring of traditional villages,contributing to their sustainable development.

Instance Segmentation of Outdoor Sports Ground from High Spatial Resolution Remote Sensing Imagery Using the Improved Mask R-CNN

Aiming at the land cover (features) recognition of outdoor sports venues (football field, basketball court, tennis court and baseball field), this paper proposed a set of object recognition methods and technical flow based on Mask R-CNN. Firstly, through the preprocessing of high spatial resolution remote sensing imagery (HSRRSI) and collecting the artificial samples of outdoor sports venues, the training data set required for object recognition of land cover features was constructed. Secondly, the Mask R-CNN was used as the basic training model to be adapted to cope with outdoor sports venues. Thirdly, the recognition results were compared with the four object-oriented machine learning classification methods in eCognition&#174. The experiment results of effectiveness verification show that the Mask R-CNN is superior to traditional methods not only in technical procedures but also in outdoor sports venues (football field, basketball court, tennis court and baseball field) recognition results, and it achieves the precision of 0.8927, a recall of 0.9356 and an average precision of 0.9235. Finally, from the aspect of practical engineering application, using and validating the well-trained model, an empirical application experiment was performed on the HSRRSI of Xicheng and Daxing District of Beijing respectively, and the generalization ability of the trained model of Mask R-CNN was thoroughly evaluated.

A Cloud Framework for High Spatial Resolution Soil Moisture Mapping from Radar and Optical Satellite Imageries

Soil moisture plays an important role in crop yield estimation,irrigation management,etc.Remote sensing technology has potential for large-scale and high spatial soil moisture mapping.However,offline remote sensing data processing is time-consuming and resource-intensive,and significantly hampers the efficiency and timeliness of soil moisture mapping.Due to the high-speed computing capabilities of remote sensing cloud platforms,a High Spatial Resolution Soil Moisture Estimation Framework(HSRSMEF)based on the Google Earth Engine(GEE)platform was developed in this study.The functions of the HSRSMEF include research area and input datasets customization,radar speckle noise filtering,optical-radar image spatio-temporal matching,soil moisture retrieving,soil moisture visualization and exporting.This paper tested the performance of HSRSMEF by combining Sentinel-1,Sentinel-2 images and insitu soil moisture data in the central farmland area of Jilin Province,China.Reconstructed Normalized Difference Vegetation Index(NDVI)based on the Savitzky-Golay algorithm conforms to the crop growth cycle,and its correlation with the original NDVI is about 0.99(P<0.001).The soil moisture accuracy of the random forest model(R 2=0.942,RMSE=0.013 m3/m3)is better than that of the water cloud model(R 2=0.334,RMSE=0.091 m3/m3).HSRSMEF transfers time-consuming offline operations to cloud computing platforms,achieving rapid and simplified high spatial resolution soil moisture mapping.

Monitoring of Karst Rocky Desertification Control Projects Based on Remote Sensing Images with Medium and High Spatial Resolution——A Case Study of Disi River Basin in Puan County

[ Objective] The study aimed to improve methods of monitoring Karst Rocky Desertification （KRD） control projects and increase the working efficiency. [Method] Based on remote sensing images with medium and high spatial resolution, KRD control projects in Disi River basin in Puan County were monitored, that is, information of the project construction in the study area was extracted using supervised classification and hu- man-computer interactive interpretation, and the monitoring results were testified with the aid of GPS. [Result] It was feasible to monitor KRD con- trol projects in Disi River basin based on remote sensing images with medium and high resolution, and the monitoring accuracy was satisfactory, reaching above 80% or 90%, so the method is worthy of popularizing. [ Conclusion] Remote sensing images with medium and high resolution can be used to monitor other KRD control Droiects.

Smart Photogrammetric and Remote Sensing Image Processing for Very High Resolution Optical Images——Examples from the CRC-AGIP Lab at UNB

This paper introduces some of the image processing techniques developed in the Canada Research Chair in Advanced Geomatics Image Processing Laboratory (CRC-AGIP Lab) and in the Department of Geodesy and Geomatics Engineering (GGE) at the University of New Brunswick (UNB), Canada. The techniques were developed by innovatively/“smartly” utilizing the characteristics of the available very high resolution optical remote sensing images to solve important problems or create new applications in photogrammetry and remote sensing. The techniques to be introduced are: automated image fusion (UNB-PanSharp), satellite image online mapping, street view technology, moving vehicle detection using single set satellite imagery, supervised image segmentation, image matching in smooth areas, and change detection using images from different viewing angles. Because of their broad application potential, some of the techniques have made a global impact, and some have demonstrated the potential for a global impact.

Developing an Automated Land Cover Classifier Using LiDAR and High Resolution Aerial Imagery

The aim of this project is to create high resolution land cover classification as well as tree canopy density maps at a regional level using high resolution spatial data. Modeling and the data manipulation and analysis of LiDAR LAS point cloud dataset as well as multispectral aerial photographs from the National Agriculture Imagery Program (NAIP) were carried out. Using geoprocessing modeling, a land cover map is created based on filtered returns from LiDAR point cloud data (LAS dataset) to extract features based on their class and return values, and traditional classification methods of high resolution multi-spectral aerial photographs of the remaining ground cover for Clarion County in Pennsylvania. The newly developed model produced 7 classes at 10 ft × 10 ft spatial resolution, namely: water bodies, structures, streets and paved surfaces, bare ground, grassland, trees, and artificial surfaces (e.g. turf). The model was tested against areas with different sizes (townships and municipalities) which revealed a classification accuracy between 94% and 96%. A visual observation of the results shows that some tree-covered areas were misclassified as built up/structures due to the nature of the available LiDAR data, an area of improvement for further studies. Furthermore, a geoprocessing service was created in order to disseminate the results of the land cover classification as well as the tree canopy density calculation to a broader audience. The service was tested and delivered in the form of a web application where users can select an area of interest and the model produces the land cover and/or the tree canopy density results (http://maps.clarion.edu/LandCoverExtractor). The produced output can be printed as a final map layout with the highlighted area of interest and its corresponding legend. The interface also allows the download of the results of an area of interest for further investigation and/or analysis.

一种融合多尺度混合注意力的建筑物变化检测模型

针对高分辨率遥感图像非真实变化所引起的错误检测问题,提出一种新颖的轻量化孪生神经网络建筑物变化检测模型。其中轻量化的特征提取模块可以获取不同尺度的局部上下文信息,使其充分学习局部和全局特征。由通道和空间注意力组成的混合注意力模块可以充分利用周围丰富的时空语义信息,以实现变化建筑物的准确提取。针对变化建筑物尺度跨度较大,容易导致建筑物边缘细节提取粗糙、小尺度建筑物漏检等问题,引入多尺度概念,将提取到的特征图划分为多个子区域,并分别引入混合注意力模块,最终将不同尺度的输出特征进行加权融合,以加强边缘细节提取能力。模型在WHU-CD、LEVIR-CD公开数据集进行实验,并分别取得87.8%和88.1%的F 1值,相较于6种对比模型具有更高的变化检测精度。

High Spatial Resolution and High Temporal Frequency(30-m/15-day) Fractional Vegetation Cover Estimation over China Using Multiple Remote Sensing Datasets:Method Development and Validation

High spatial resolution and high temporal frequency fractional vegetation cover(FVC) products have been increasingly in demand to monitor and research land surface processes. This paper develops an algorithm to estimate FVC at a 30-m/15-day resolution over China by taking advantage of the spatial and temporal information from different types of sensors: the 30-m resolution sensor on the Chinese environment satellite(HJ-1) and the 1-km Moderate Resolution Imaging Spectroradiometer(MODIS). The algorithm was implemented for each main vegetation class and each land cover type over China. First, the high spatial resolution and high temporal frequency normalized difference vegetation index(NDVI) was acquired by using the continuous correction(CC) data assimilation method. Then, FVC was generated with a nonlinear pixel unmixing model. Model coefficients were obtained by statistical analysis of the MODIS NDVI. The proposed method was evaluated based on in situ FVC measurements and a global FVC product(GEOV1 FVC). Direct validation using in situ measurements at 97 sampling plots per half month in 2010 showed that the annual mean errors(MEs) of forest, cropland, and grassland were-0.025, 0.133, and 0.160, respectively, indicating that the FVCs derived from the proposed algorithm were consistent with ground measurements [R2 = 0.809,root-mean-square deviation(RMSD) = 0.065]. An intercomparison between the proposed FVC and GEOV1 FVC demonstrated that the two products had good spatial–temporal consistency and similar magnitude(RMSD approximates 0.1). Overall, the approach provides a new operational way to estimate high spatial resolution and high temporal frequency FVC from multiple remote sensing datasets.

基于多源遥感卫星数据的青海东昆仑沟里地区线性构造识别及找矿预测

沟里地区是青海东昆仑金及多金属成矿带重要组成部分之一,矿产资源丰富,具有良好的找矿前景,目前区内尚无大面积基于多源遥感卫星数据的线性构造识别及找矿应用方面的研究。选取Landsat8 OLI、GF-2不同空间分辨率遥感数据,运用最佳波段选择、主成分分析、图像融合、线性拉伸、定向滤波等遥感图像处理技术,结合DEM衍生产品和多元地学信息综合研究方法,实现了沟里地区线性构造识别和找矿预测。结果表明:(1)研究区构造格架以卡可特尔-色日德一线为界,可分为南部、北部2个区域,北部区域线性构造以NNE向最为发育,近EW向次之,NW、NE向分布较少,南部区域受昆中断裂带控制作用,线性构造主要发育近EW向和少量NW向、NE向;(2)已知矿床(点)全部位于线性构造内及其附近,构造控矿作用明显;(3)线性构造密集分布和交汇处以及遥感影像上不同色调连接区是寻找金矿化的有利地区。最后根据多元地学信息与遥感解译构造信息综合对比分析,在研究区圈定找矿靶区4处并进行了野外验证。研究结果表明,基于多源遥感卫星数据能够较好地识别地表构造空间结构特征,结果较为客观和准确,能够为该地区和外围找矿预测提供参考和依据。

基于高分辨率卫星和无人机的广西滨海盐沼面积变化监测

滨海盐沼作为重要的海岸带生态系统,在海岸保护、生物多样性维持、固碳减污等方面发挥了重要的生态服务功能。及时准确地监测滨海盐沼分布情况和动态变化,对于科学地管理和保护本地滨海盐沼生态系统意义重大。本研究基于2019年和2021年多源国产高空间分辨率卫星数据,结合无人机自主性强、灵活机动、不受云遮挡影响的优势,对广西壮族自治区滨海盐沼开展遥感跟踪监测。研究结果表明,广西2021年滨海盐沼总面积为1 341.40 hm2,其中,北海市、防城港市和钦州市3个海滨城市的滨海盐沼面积分别为1 247.82 hm2、49.73 hm2和43.85 hm2。与2019年相比,广西2021年滨海盐沼总面积减少108.96 hm2,其中,北海市互花米草(Spartina alterniflora)面积减少107.05 hm2,钦州市短叶茳芏(Cyperus malaccensis)和芦苇(Phragmites australis)面积减少1.91 hm2,防城港市滨海盐沼面积不变。广西当地对入侵种互花米草的治理卓有成效,互花米草大范围减少,但局部区域的互花米草分布仍呈不断增长的趋势,仍需重视对互花米草的监测与防控工作。

综合孔径微波辐射成像技术发展现状与趋势

从综合孔径微波辐射成像技术实际需求和技术特点出发,首先简要回顾了综合孔径微波辐射成像技术的整个发展历程;然后,从地球被动微波遥感和目标被动探测两个应用领域较为全面地介绍了综合孔径微波辐射成像技术的发展现状,包括综合孔径微波辐射成像系统研制和相关重要研究进展等;最后,从高空间分辨率和多手段联合等方面总结了综合孔径微波辐射成像技术的发展趋势。随着综合孔径微波辐射成像技术的发展,其在地球被动微波遥感和目标探测领域将会得到更广泛的应用。

基于U-Net、U-Net++和Attention-U-Net网络的遥感影像水体提取

目前,深度学习在高分辨率遥感影像水体提取方面的应用已成为遥感领域的研究热点。其中基于U-Net网络的算法在水体提取中表现出较好的性能,但鲜有研究对不同U-Net网络算法在水体提取任务中的性能差异进行深入比较。因此,本文选择U-Net、U-Net++和Attention-U-Net 3种卷积神经网络,基于GID数据集,进行试验与定量分析。结果表明:U-Net++的训练精度最高,其次为U-Net、Attention-U-Net,三者分别为0.912、0.907、0.899;U-Net++的边缘提取能力优于其他两种网络;在分割不同类型水体和区分遥感影像中与水体区域相似的非水体区域上,U-Net++的提取效果显著,U-Net和Attention-U-Net易出现漏提现象,效果欠佳。

结合全局特征与局部互通的河流断流接续优化

高分辨率遥感影像的水体提取常因地物类型复杂、部分河流狭窄等因素导致水体提取结果不完整、不连续。因此,结合水体自身光谱和纹理特征,提出了一种结合全局特征与局部互通的遥感影像水体提取优化方法。首先,在水体提取初始结果的基础上,通过多尺度Frangi滤波和大津法(OTSU)分割算法提取线性支流,对河流进行补充得到初步优化结果。然后,结合局部互通的断流接续算法,对初步优化结果中的断流部分进行连接。最后,通过K-means聚类提取水体部分,并与精确优化结果进行拓扑检查及光谱检查,实现块状水体的验证筛选。实验结果表明,本文方法能够提取到细小支流,提高优化的准确度;断流接续算法的加入,有助于提高河流提取的完整性。与其他方法相比,本文方法的总体精度分别提高1.04%、1.50%,F1分别提高5.84%、8.28%,可以作为有效提升水体优化后处理的手段,提高了水体提取的完整度和精度。

多尺度特征融合与空间优化的弱监督高分遥感建筑变化检测

针对建筑物变化检测中深度学习方法严重依赖大量高成本高难度的像素级标注样本进行模型训练的问题,本文提出一种基于图像级标注样本的高分辨率遥感建筑物弱监督变化检测方法MDF-LSR-Net。该方法首先提取双时相多尺度差异特征,并对多尺度差异特征进行渐进式融合,利用充分融合后的多层次多尺度差异特征来生成变化热力图;然后,利用低层融合差异特征的局部空间相似性来优化初始的变化热力图,进一步增强热力图中变化区域的完整性和准确性;最后,基于高质量的变化热力图训练最终的变化检测模型。在公开的建筑物变化检测数据集WHU和LEVIR上的多组试验结果表明,本文方法能够获取更加完整且准确的变化热力图,从而使得基于此训练的变化检测模型也取得更高的检测精度,其中最终的变化检测模型在WHU数据集上的IOU和F 1值分别可达65%和79%以上。

基于高分辨率遥感影像的土耳其地震建筑物震害特征

选取土耳其卡赫拉曼马拉什省努尔达吉镇城区和周边乡村地区作为研究区,通过获取地震前后的高空间分辨率遥感影像数据,提取房屋建筑震害信息,识别房屋建筑震害等级,利用震害指数计算区域内地震烈度等级,综合分析得到建筑物震害特征与主要成因,对地震灾情快速评估、应急救援和恢复重建具有重要参考。

基于融合多模态的遥感影像冰川识别方法

冰川对气候变化极为敏感,冰川变化与区域生态、自然灾害、水资源等息息相关。高原冰川遥感信息提取及实时监测是监测冰川变化不可或缺的手段。为有效识别多尺度高分辨率遥感影像中的冰川,设计一种Glacier-Unet模型。(1)针对现有的基于Landsat卫星遥感影像高原冰川提取算法因缺乏应对复杂地物干扰影响的有效方法,导致反射目标信息丢失的问题。以青藏高原阿尼玛卿雪山为试验对象,选取基于Landsat-9遥感卫星高分辨率影像制作数据集。对高分辨率冰川遥感影像进行数据预处理,采取特征级融合和像素级融合制作多模态遥感数据影像,通过滑动切片、数据增强手段丰富语义分割数据集,保证模型训练准确性和鲁棒性;(2)针对零散、细小冰川识别能力不足的问题,设计门控多尺度过滤层(Gated Multi-scale Filter Layer,G-MsFL)滤除无用特征信息,使模型具备多尺度特征提取和特征融合能力,有效识别复杂地物环境中的冰川;(3)针对冰川轮廓模糊问题,设计并联双通道注意力模块(Paralleling Dual Attention Module,P-DAM)。将冰川边界丰富的上下文信息进行编码作为特征图的局部特征,从而增强其特征表达能力。对改进的Glacier-Unet模型在阿尼玛卿测试数据集中的实验结果进行定性、定量分析,发现整体分割精度较对比方法提升6.1%,且能有效识别零散、细小冰川,对高原地区冰川识别工作具有重要意义。

融合Partial卷积与残差细化的遥感影像建筑物提取算法

由于高空间分辨率遥感图像中背景与建筑物对象的相似度高,导致网络难以兼顾不同大小的建筑物,建筑边界区域的像素与背景混淆,建筑边界很容易被漏检。为解决上述问题,提出融合Partial卷积与残差细化的遥感影像建筑物提取算法(UUNet)。以U-Net为基线网络,首先,改进编码器。在编码器前端加入两个Conv4×4,在最初扩大感受野,捕捉更多遥感影像特征信息,利用Partial卷积(PConv3×3)构造的PC模块,增强编码器提取多尺度建筑物特征的能力,用Conv2×2进行两倍下采样,减少建筑物特征信息丢失。其次,减少参数量。裁剪U-Net网络解码器三层结构为UUNet网络解码器。最后,增加改进的残差细化模块。在解码器输出端构造裁剪到三层结构的U型残差细化模块,对解码器输出的粗糙建筑物特征图进行进一步提纯,使建筑物边缘信息更加清晰,网络解码器与U型残差细化模块编码器进行跳跃连接,保留最初特征,将SimAM嵌入细化模块中,提高建筑物关注度,优化网络改善边界模糊,提升目标边界提取质量。在Satellite datasetⅡ(East Asia)数据集上进行消融实验,UUNet比U-Net的IoU_(Building)、IoU_(Background)、F1、OA和MIoU分别提高2.78个百分点、0.12个百分点、1.91个百分点、0.19个百分点、1.45个百分点,表明UUNet网络优于基线网络;在Satellite datasetⅡ(East Asia)数据集和WHU数据集上做对比实验,UUNet相较于现有的主流算法更优,能够显著地提升高分辨率遥感影像中建筑物提取的效果。

基于递归门控卷积的遥感图像超分辨率研究

由于受到硬件条件的限制,通常难以获得具有高分辨率(HR)的遥感图像。利用单幅图像超分辨率(SISR)技术对低分辨率(LR)遥感图像进行超分辨率重建是获取高分辨率遥感图像的常用方法。近年来,在图像超分辨率领域引入的卷积神经网络(CNN)改进了图像重建性能。然而,现有的基于CNN的超分辨率模型通常使用低阶注意力机制提取深层特征,其表征能力有待提高,且常规卷积的感受野有限,缺乏对远距离依赖关系的学习。为了解决以上问题,提出了一种基于递归门控卷积的遥感图像超分辨率方法RGCSR。该方法引入递归门控卷积g n Conv学习全局依赖和局部细节,通过高阶空间交互来获取高阶特征。首先,使用由高阶交互子模块(HorBlock)和前馈神经网络(FFN)组成的高阶交互——前馈神经网络模块(HFB)提取高阶特征。其次,利用由通道注意力(CA)和g n Conv构建的特征优化模块(FOB)优化各个中间模块的输出特征。最后,在多个数据集上的对比结果表明,RGCSR比现有的基于CNN的超分辨率方法具备更好的重建性能和视觉效果。

DSFA: cross-scene domain style and feature adaptation for landslide detection from high spatial resolution images

Rapid and accurate landslide inventory mapping is significant for emergency rescue and post-disaster reconstruction.Nowadays,deep learning methods exhibit excellent performance in supervised landslide detection.However,due to differences between cross-scene images,the performance of existing methods is significantly degraded when directly applied to another scene,which limits the application of rapid landslide inventory mapping.In this study,we propose a novel Domain Style and Feature Adaptation(DSFA)method for cross-scene landslide detection from high spatial resolution images,which can leverage labeled source domain images and unlabeled target domain images to mine robust landslide representations for different scenes.Specifically,we mitigate the large discrepancy between domains at the dataset level and feature level.At the dataset level,we introduce a domain style adaptation strategy to shift landslide styles,which not only bridges the domain gap,but also increases the diversity of landslide samples.At the feature level,adversarial learning and domain distance minimization are integrated to narrow large feature distribution discrepancies for learning domain-invariant information.In addition,to avoid information omission,we improve the U-Net3+model.Extensive experimental results demonstrate that DSFA has superior detection capability and outperforms other methods,showing its great application potential in unsupervised landslide domain detection.