- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - An Automatic Deployment Support for Processing Remote Sensing Data in the Cloud
摘要： Master/Worker distributed programming model enables huge remote sensing data processing by assigning tasks to Workers in which data is stored. Cloud computing features include the deployment of Workers by using virtualized technologies such as virtual machines and containers. These features allow programmers to configure, create, and start virtual resources for instance. In order to develop remote sensing applications by taking advantage of high-level programming languages (e.g., R, Matlab, and Julia), users have to manually address Cloud resource deployment. This paper presents the design, implementation, and evaluation of the Infra.jl research prototype. Infra.jl takes advantage of Julia Master/Worker programming simplicity for providing automatic deployment of Julia Workers in the Cloud. The assessment of Infra.jl automatic deployment is only ～2.8s in two different Azure Cloud data centers.
关键词： data management,cloud computing,big data,image processing,remote sensing
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Cloud-Gan: Cloud Removal for Sentinel-2 Imagery Using a Cyclic Consistent Generative Adversarial Networks
摘要： Cloud cover is a serious impediment in land surface analysis from Remote Sensing images either causing complete obstruction (thick clouds) with loss of information or blurry effects when being semi-transparent (thin clouds). While thick clouds require complete pixel replacement, thin cloud removal is fairly challenging as the atmospheric and land-cover information is intertwined. In this paper, we address this problem and propose a Cloud-GAN to learn the mapping between cloudy images and cloud-free images. The adversarial loss in the proposed method constrains the distribution of generated images to be close enough to the underlying distribution of the non-cloudy images. An additional cycle consistency loss is used to further restrain the generator to predict cloud-free images only of the same scene as reflected in the cloudy images. Our method not only rejects the necessity of any paired (cloud/cloud-free) training dataset but also avoids the need of any additional (expensive) spectral source of information such as Synthetic Aperture Radar imagery which is cloud penetrable. Lastly, we demonstrate the efficacy of our technique by training on an openly available and fairly new Sentinel-2 Imagery dataset consisting of real clouds. We also show significant improvement in PSNR values after removing clouds on synthetic images thus validating the competency of our methodology.
关键词： Deep Learning,Cloud Removal,Sentinel-2 Imagery,Generative Adversarial Networks
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Harmonization And Fusion of Global Scale Data
摘要： Remote sensing data provides scientists with synoptic coverage of the Earth's surface, allowing us to understand its system dynamics in a way that would be impossible with more direct observation. As more satellites have been deployed in recent years, imagery has become more readily available and diverse, encompassing a wider range of spatial, temporal, and spectral resolutions than ever before. While these data better inform our understanding of the Earth, anyone hoping to leverage this information is hampered by the large size and complexity of these datasets, a lack of easily accessible computing resources, and the broad expertise required to correctly interpret the imagery. To fully leverage the information in these disparate datasets, data fusion methods must be implemented that abstract access to them. Large scale fusion of geospatial data, using physically based and statistical methods, can be accomplished to create a living model of the earth. This presentation will discuss the Descartes Labs approach to data fusion and normalization as well as our effort to leverage these capabilities toward a synoptic earth model. Topics will include the current status of the physical normalization algorithms deployed into the Descartes Labs Platform as well as efforts to harmonize and abstract access to multi-vendor constellations.
关键词： cloud computing,data fusion,data normalization,surface reflectance
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Surface Deformation Mapping of Italy Through the P-Sbas Dinsar Processing of Sentinel-L Data in a Cloud Computing Environment
摘要： In this work we implement a completely automatic interferometric processing chain, based on the well-known advanced DInSAR algorithm referred to as Parallel Small BAseline Subset (P-SBAS), for the generation of Sentinel-1 (S-1) Interferometric Wide Swath (IWS) deformation mean velocity maps and time-series of very wide areas, implemented within the Amazon Web Services (AWS) Elastic Cloud Compute environment. Our processing chain consists of the initial data query to the S-1 archive that we created on the AWS S3 storage, then the data transfer to the AWS computing nodes, the data processing and, finally, the transfer of the obtained interferometric results back to the original S3 storage. In order to demonstrate the capability of the implemented Cloud-based processing chain to deal with massive amount of data, we focus our analysis on the whole Italian territory by processing all the available data acquired both from ascending and descending orbits within the October 2014 – March 2017 time interval. As final result we combine the retrieved LOS displacements in order to compute the mean velocity maps and time-series of the vertical and East-West surface deformation components.
关键词： P-SBAS,Sentinel-1,Cloud Computing,DInSAR,deformation time-series
更新于2025-09-10 09:29:36
-
[IEEE 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - Las Palmas de Gran Canaria, Spain (2018.6.21-2018.6.23)] 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES) - High Resolution 3D Thermal Imaging Using FLIR DUO R Sensor
摘要： With the spread of photogrammetry processes, photo-based 2D/3D reconstruction became general, in research as well as in the industry. Source images are taken using either a hand-held camera or an automated camera fixed to the carrier, a UAV, then they are matched during post-processing. The price of digital microbolometer-based high-resolution (1 megapixel) thermal cameras is currently very high, but these, compared to RGB cameras (16-20 megapixel), are still considered to have very low-resolution, in this way employing photogrammetry in this present case is not feasible. In the article, a novel method developed by us is introduced which by using a low thermal resolution camera (FLIR DUO R), based on which a 3D thermal image can be produced with the help of a camera capable of dual imaging (RGB and Thermal). The work is illustrated using measurements, and post-production was conducted using the MATLAB software. The process is adequate for producing 3D thermal images taken using UAV devices.
关键词： FLIR,photogrammetry,large scale point cloud,MATLAB,object reconstruction,3D thermal imaging
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Cloud Shadow Removal Based on Cloud Transmittance Estimation
摘要： This paper proposes a method of cloud shadow removal for multispectral images to retrieve the ground reflectance of areas shadowed by clouds. Cloud shadows are cast when incident direct solar irradiance gets attenuated by clouds. To retrieve the ground reflectance of the shadowed pixels, it is required to estimate pixel-wise attenuation factor for the solar irradiance. Unlike conventional methods, the proposed technique takes the physical model of cloud shadow formation into account to accurately estimate the attenuation factors. According to the physical model, the factors are derived from the transmittance of an occluding cloud. Visual and quantitative results demonstrate that the proposed method outperforms the well-known de-shadowing algorithm. The average correlation coefficient of the corrected image with a reference image is improved from 0.45 to 0.75 by the proposed method as compared to the conventional method. Further, the average spectral angle with a reference image is improved by 10%.
关键词： shadow removal,Cloud,physical model,spectral unmixing
更新于2025-09-10 09:29:36
-
Surface Light Field Compression using a Point Cloud Codec
摘要： Light ?eld (LF) representations aim to provide photo-realistic, free-viewpoint viewing experiences. However, the most popular LF representations are images from multiple views. Multi-view image-based representations generally need to restrict the range or degrees of freedom of the viewing experience to what can be interpolated in the image domain, essentially because they lack explicit geometry information. We present a new surface light ?eld (SLF) representation based on explicit geometry, and a method for SLF compression. First, we map the multi-view images of a scene onto a 3D geometric point cloud. The color of each point in the point cloud is a function of viewing direction known as a view map. We represent each view map ef?ciently in a B-Spline wavelet basis. This representation is capable of modeling diverse surface materials and complex lighting conditions in a highly scalable and adaptive manner. The coef?cients of the B-Spline wavelet representation are then compressed spatially. To increase the spatial correlation and thus improve compression ef?ciency, we introduce a smoothing term to make the coef?cients more similar across 3D space. We compress the coef?cients spatially using existing point cloud compression (PCC) methods. On the decoder side, the scene is rendered ef?ciently from any viewing direction by reconstructing the view map at each point. In contrast to multi-view image-based LF approaches, our method supports photo-realistic rendering of real-world scenes from arbitrary viewpoints, i.e., with an unlimited six degrees of freedom (6DOF). In terms of rate and distortion, experimental results show that our method achieves superior performance with lighter decoder complexity compared with a reference image-plus-geometry compression (IGC) scheme, indicating its potential in practical virtual and augmented reality applications.
关键词： point cloud compression,free-viewpoint,full 6DoF,augmented reality,Surface light ?eld,virtual reality
更新于2025-09-10 09:29:36
-
Efficient and robust lane marking extraction from mobile lidar point clouds
摘要： Surveys of roadways with Mobile Laser Scanning (MLS) are now being conducted on a regular basis by many transportation agencies to provide detailed geometric information to support a wide range of applications, including asset management. Most MLS systems provide intensity (return signal strength) data as a point attribute in georeferenced point clouds, which may be used to estimate retro-reflectivity of pavement markings for effective maintenance. Nevertheless, the extraction of pavement markings from mobile lidar data remains an open challenge, due to variable noise, degree of wear on the markings, and road conditions. This paper addresses these challenges, presenting a novel approach for efficient, reliable extraction of lane markings, including those that have been significantly worn. First, using the MLS trajectory information, the lidar data is discretized into smaller sections, and then transformed to the local coordinate system, such that the road surface is near-horizontal for reliable extraction on roads with significant grade. Subsequently, the road surface is extracted using the constrained Random Sampling and Consensus (RANSAC) algorithm and then rasterized into a 2D intensity image to apply image processing techniques, namely: image segmentation to separate the lane markings from the road pavement, and a morphological opening operation to remove small objects. However, the extracted lane markings are prone to over-segmentation, due to occlusions or worn portions caused by moving vehicles. To rectify this, topologically-similar lane markings are associated with each other by computing line parameters (i.e., orientation and distance from the origin), which enables the gaps to be filled among the associated lanes. Finally, the remaining incorrect lane markings are detected and removed through a noise filtering phase using Dip test statistics. Examples of the effectiveness and application of the methodology are shown for a variety of sites with stripes of variable condition to highlight the robustness of the approach. Using optimized parameter values, the algorithm achieved F1 scores of 89–97% when tested on a variety of datasets encompassing a wide range of road scene types.
关键词： Point cloud,Mobile laser scanning,Lane marking extraction
更新于2025-09-10 09:29:36
-
Improving NDVI by removing cirrus clouds with optical remote sensing data from Landsat-8 – A case study in Quito, Ecuador
摘要： The Andean region has a high cloud density throughout the year. The use of optical remote sensing data in the computation of environmental indices of this region has been hampered by the presence of clouds. To maximize accuracy in the computation of several environmental indices including the normalized difference vegetation index (NDVI), we compared the performance of two algorithms in removing clouds in Landsat-8 Operational Land Imager (OLI) data of a high-elevation area. The study area was Quito, Ecuador, which is a city located close to the equator and in a high-elevation area crossed by the Andes Mountains. The first algorithm was the automatic cloud removal method (ACRM), which employs a linear regression between the different spectral bands and the cirrus band. The second algorithm was independent component analysis (ICA), which considers the noise (clouds) as part of independent components applied over the study area. These methods were evaluated based on several images from different years with different cloud conditions. The results indicate that neither algorithm is effective over this region for the removal of clouds or for NDVI computation. However, after improving ACRM, the NDVI computed using ACRM showed a better correlation than ICA with the MODIS NDVI product.
关键词： Quito,optical remote sensing,cloud removal,NDVI,Landsat-8 OLI
更新于2025-09-10 09:29:36
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - R-Covnet: Recurrent Neural Convolution Network for 3D Object Recognition
摘要： Point cloud is a very precise digital format for recording objects in space. Point clouds have received increasing attention lately, due to the higher amount of information it provides compared to images. In this paper, we propose a new deep learning architecture called R-CovNet, designed for 3D object recognition. Unlike previous architectures that usually sample or convert point cloud into three-dimensional grids before processing, R-CovNet does not require any preprocessing. Our main goal is to provide a permutation invariant architecture especially designed for point clouds data of any size. Experiments with well-known benchmarks show that R-CovNet can achieve an accuracy of 92.7%, thus outperforming all the volumetric methods.
关键词： Point Cloud,RNN,3D Object Recognition
更新于2025-09-10 09:29:36