Rapid retrieval strategy for massive remote sensing metadata based on GeoHash coding

With the rapid development of Earth observation technology, satellite data centres have accumulated large amounts of remote sensing data from different spaceborne and airborne sensors. The efficient management and quick retrieval of multisource, massive and heterogeneous remote sensing data in the Big Data age have become increasingly important. In this paper, a spatio-temporal organization model based on GeoHash coding is proposed. First, based on the ISO (International Organization for Standardization) standard, the heterogeneous remote sensing metadata can be converted into a unified format, and the differences in the multisource remote sensing metadata are screened. Then, the GeoHash algorithm is used to encode and convert the latitude and longitude coordinates of the remote sensing metadata to reduce the remote sensing metadata dimensions under space retrieval conditions. Finally, by building an HBase key value model based on GeoHash, a primary key is used to realize the rapid retrieval of massive remote sensing metadata through the simulation of 1500 million remote sensing metadata retrieval experiments; by comparing with the traditional multi-conditional filtering retrievals, the results show that a spatio-temporal organization strategy for remote sensing metadata based on GeoHash coding can effectively improve the efficiency of remote sensing data retrievals.     

Replacing pixel representations by point-function schemes for reducing discretization error in ill-posed remote sensing problems,with examples from cloud tomography

Because of their simplicity and low computational cost, discretizations based on pixels have held sway in remote sensing since its inception. Yet functional representations are clearly superior in many applications, for example when combining retrievals from dissimilar remote sensing instruments. Using cloud tomography as an example, this letter shows that a point-function discretization scheme based on linear interpolation can reduce retrieval error of cloud water content up to 40% compared to a conventional pixel scheme. This improvement is particularly marked because cloud tomography, like the vast majority of remote sensing problems, is ill-posed and thus a small inaccuracy in the formulation of the retrieval problem, such as discretization error, can cause a large error in the retrievals.     

Application of a parallel spectral–spatial convolution neural network in object-oriented remote sensing land use classification

Due to the abundance of spatial information and relative lack of spectral information in high spatial resolution remote sensing images, a land use classification method for high-resolution remote sensing images is proposed based on a parallel spectral-spatial convolutional neural network (CNN) and object-oriented remote sensing technology. The contour of a remote sensing object is taken as the boundary and the set of pixels that comprises the object are extracted to form the input data set for the deep neural network. The proposed network considers both the features of the object and the pixels which forms the object. The spatial and spectral features of remote sensing image objects are extracted independently in the parallel network using panchromatic and multispectral remote sensing techniques. Then, through a fully connected layer, both spectral and spatial information are integrated to produce remote sensing object class coding. The experimental results demonstrate that the parallel spectral-spatial CNN, which combines spatial and spectral features, achieves better classification performance than the individual CNN. Therefore, the proposed method provides a novel approach to land use classification based on high spatial resolution remote sensing images.     

Fast orientation prediction-based discrete wavelet transform for remote sensing image compression

In this letter, a fast orientation prediction-based discrete wavelet transform (DWT) is introduced for high-spatial-resolution remote sensing image compression. The proposed fast orientation prediction-based approach is designed to improve coding performance and reduce computational complexity of the previous adaptive directional lifting method. The main contribution of the proposed approach consists of three parts: a new orientation map is designed to achieve a better transform coding performance; an orientation prediction model is presented to fast obtain the optimal transform orientation; the new fast orientation prediction-based DWT is introduced. Experimental results show that the proposed fast orientation prediction-based high-spatial-resolution remote sensing image coding technique outperforms the traditional lifting wavelet and the method based on adaptive directional lifting in coding performance, and the computational complexity of the proposed transform is far lower than that of adaptive directional lifting method.     

Review article: Primary aeromedical retrievals in Australia: An interrogation and search for context

Primary aeromedical retrievals are a direct scene response to patients with a critical injury or illness using a medically equipped aircraft. They are often high‐acuity taskings. In Australia, information on primary retrieval taskings is housed by service providers, of which there are many across the country. This exploratory literature review aims to explore the contemporary peer‐reviewed literature on primary aeromedical retrievals in Australia. The focus is on adult primary aeromedical retrievals undertaken in Australia and clinical tools used in this pre‐hospital setting. Included articles were reviewed for research theme (clinical and equipment, systems and/or outcomes), data coverage and appraisal of the evidence. Of the 37 articles included, majority explored helicopter retrievals (n = 32), retrieval systems (n = 21), compared outcomes within a service (n = 10) and explored retrievals in the state of New South Wales (n = 19). Major topics of focus included retrieval of trauma patients and airway management. Overall, the publications had a lower strength of evidence because of the preponderance of cross‐sectional and case‐study methodology. This review provides some preliminary but piecemeal insight into primary retrievals in Australia through a localised systems lens. However, there are several areas for research action and service outcome improvements suggested, all of which would be facilitated through the creation of a national pre‐hospital and retrieval registry. The creation of a registry would enable consideration of the frequency and context of retrievals, comparison across services, more sophisticated data interrogation. Most importantly, it can lead to service and pre‐hospital and retrieval system strengthening.     

Evaluation of soil moisture derived from FY3B microwave brightness temperature over the Tibetan Plateau

In recent years, remote sensing has become one newest technology for deriving soil moisture at large scales. Using a radiative transfer algorithm, we have derived soil moisture over the Tibetan Plateau from the brightness temperature of the microwave radiometer imager (MWRI) onboard China’s Fengyun 3B (FY3B) satellite. The derived FY3B soil moisture data are evaluated with in situ observations, the ERA-Interim reanalysis and the retrievals from microwave imager (TMI) onboard the Tropical Rainforest Measuring Mission (TRMM). The FY3B and the TMI data are found to have both overestimated the soil moisture magnitudes against in situ observations. The FY3B data significantly outperform the TMI retrievals and particularly the ERA-Interim data with respect to their temporal dynamics, which is more important in soil moisture applications. This finding suggests the promising potential for using FY3B microwave brightness temperature to derive soil moisture over the Tibetan Plateau.     

Selective convolutional neural networks and cascade classifiers for remote sensing image classification

Training convolutional neural network (CNN) architecture fully, using pretrained CNNs as feature extractors, and fine-tuning pretrained CNNs on target datasets are three popular strategies used in state-of-the-art methods for remote sensing image classification. The full training strategy requires large-scale training dataset, whereas the fine-tuning strategy requires a pretrained model to resume network learning. In this study, we propose a new strategy based on selective CNNs and cascade classifiers to improve the classification accuracy of remote sensing images relative to single CNN. First, we conduct a comparative study of existing pretrained CNNs in terms of data augmentation and the use of fully connected layers. Second, selective CNNs, which based on class separability criterion, are presented to obtain an optimal combination from multiple pretrained models. Finally, classification accuracy is improved by introducing two-stage cascade linear classifiers, the prediction probability of which in the first stage is used as input for the second stage. Experiments on three public remote sensing datasets demonstrate the effectiveness of the proposed method in comparison with state-of-the-art methods.     

Atmospheric correction for MASTER image data using localized modelled and observed meteorology and trace gases

Atmospheric correction for remote sensing-based studies typically does not use information from spatio-temporally resolved meteorological models. We assessed the effect of using observations and mesoscale weather and chemical transport models on multispectral retrievals of land and ocean properties. We performed two atmospheric corrections on image data acquired by the Moderate Resolution Imaging Spectroradiometer (MODIS)/Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) airborne simulator over Monterey Bay, California. One correction used local atmospheric profiles of meteorology and trace gases at overpass and the other used the 1976 US Standard default atmospheric profile in the MODTRAN4 radiative transfer model. We found only minor impacts from atmospheric correction in the Fluorescence Line Height index of ocean chlorophyll, but substantive differences in retrievals of surface temperature and the Normalized Difference Vegetation Index. Improvements in sea surface temperature retrieval were validated by in situ measurements. Results indicate that spatio-temporally specific atmospheric correction factors from mesoscale models can improve retrievals of surface properties from remotely sensed image data.     

A generally applicable noise-estimating method for remote sensing images

Local mean and local standard deviations (LMLSD), which is one of the most widely used methods for estimating noise in remote sensing images, is suitable only for the images with many homogeneous regions. For those composed of heterogeneous features and textures, it may cause overestimation of noise. Edge-extracted local standard deviations (EELSD) method performs better than LMLSD in most instances, but it still cannot work out the accurate noise estimation in most heterogeneous images. Spectral and spatial de-correlation (SSDC) is an effective noise-estimation method for hyperspectral images. However, it cannot be applied to single-band or multispectral images because of the use of pixel spectral information in the calculation process. In this article, a new noise-estimating method for remote sensing images, which is based on the principle of LMLSD and has made improvements in three aspects, is proposed. The new method has been tested with several Airborne Visible Infrared Imaging Spectrometer images with different degrees of uniformity. Compared with LMLSD and EELSD, the results of the improved method are more accurate, stable, and applicable in terms of complex land cover types. Furthermore, in contrast to SSDC, this method is suitable not only for hyperspectral images but also for single-band and multispectral images.     

A method for detecting the atmospheric refraction effect using satellite remote sensing

The atmospheric refraction effect seriously restricts the precision of satellite measurements. Various atmospheric refraction models have been proposed to solve the bending effect due to refraction. But the atmosphere shows a complicated spatio-temporal distribution due to turbulences, which affects the precision of the atmosphere models. In this study, we proposed a novel method to detect the atmospheric refraction effect according to the dispersion of the electromagnetic wave. Depending on one satellite image only, we can invert the displacement of atmospheric refraction effect. And this method makes it a reality without constructing the atmosphere model and monitoring a series of meteorological data. In the experiment, two high-resolution images were used to validate the method, an inclined shooting scene at zenith angle of 30° and a vertical shooting scene as a control. The result is close to the value calculated by the atmospheric refraction model. So the proposed method is effective to detect the atmospheric refraction effect using satellite remote sensing.     

Change detection based on Faster R-CNN for high-resolution remote sensing images

Change detection is of great significance in remote sensing. The advent of high-resolution remote sensing images has greatly increased our ability to monitor land use and land cover changes from space. At the same time, high-resolution remote sensing images present a new challenge over other satellite systems, in which time-consuming and tiresome manual procedures must be needed to identify the land use and land cover changes. In recent years, deep learning (DL) has been widely used in the fields of natural image target detection, speech recognition, face recognition, etc., and has achieved great success. Some scholars have applied DL to remote sensing image classification and change detection, but seldomly to high-resolution remote sensing images change detection. In this letter, faster region-based convolutional neural networks (Faster R-CNN) is applied to the detection of high-resolution remote sensing image change. Compared with several traditional and other DL-based change detection methods, our proposed methods based on Faster R-CNN achieve higher overall accuracy and Kappa coefficient in our experiments. In particular, our methods can reduce a large number of false changes.     

Deep multi-feature fusion network for remote sensing images

ABSTRACT

Learning discriminative and robust features is crucial in remote sensing image processing. Many of the currently used approaches are based on Convolutional Neural Networks (CNNs). However, such approaches may not effectively capture various different semantic objects of remote sensing images. To overcome this limitation, we propose a novel end-to-end deep multi-feature fusion network (DMFN). DMFN combines two different deep architecture branches for feature representations; the global and local branch. The global branch, which consists of three losses, is used to learn discriminative features from the whole image. The local branch is then used in the partitioning of the entire image into multiple strips in order to obtain local features. The two branches are then combined, used to learn fusion feature representations for the image. The proposed method is an end-to-end framework during training. Comprehensive validation experiments on two public datasets indicate that relative to existing deep learning approaches, this strategy is superior for both retrieval and classification tasks.     

Mutual information based multi-modal remote sensing image registration using adaptive feature weight

Multi-module images registration is a challenging task in image processing, and more especially in the field of remote sensing. In this letter, we strive to present a novel mutual information scheme for image registration in remote sensing scenario based on feature map technique. We firstly take saliency detection advantages to extract geographic pattern, and then utilize the efficient Laplacian of Gaussian(LOG) and Guided Filter methods to construct a new feature map based on different characteristic of multi-channel images. To avoid practical traps of sub-optimization, we propose an novel mutual information(MI) algorithm based on an adapted weight strategy. The proposed model divides an image into patches and assigns weighted values according to patch similarities in order to solve the optimization problem, improve accuracy and enhance performance. Note that, our proposed method incorporates the LOG and Guided Filter methods into image registration for the first time to construct a new feature map based on differences and similarities strategy. Experiments are conducted over island and coastline scenes, and reveal that our hybrid model has a significant performance and outperforms the state-of-the-art methods in remote sensing image registration.     

Hyperspectral remote sensing of aboveground biomass on a river meander bend using multivariate adaptive regression splines and stochastic gradient boosting

Research on aboveground biomass (AGB) retrieval via remote sensing in floodplain forests, in particular, is urgently needed for improved understanding of carbon cycling in such areas. AGB estimation is particularly challenging in floodplain forests, which are characterized by high spatial variability in AGB resulting from biogeomorphodynamic processes. In this study, we perform remote AGB retrieval for a deciduous riparian forest on a river meander bend based on hyperspectral/high-dimensional Hyperion bands and other input variables. We compare multivariate adaptive regression splines (MARS)-, stochastic gradient boosting (SGB)- and Cubist-based AGB estimates. Results show that MARS- and SGB-derived estimates are significantly more accurate than Cubist-based AGB. The most accurate MARS and SGB estimates have a coefficient of determination, R², of 0.97 and 0.95, respectively, whereas the Cubist estimate with the lowest error has an R² of 0.85. MARS and SGB AGB are not significantly different, however. These modelling approaches are applicable across scales and environments.     

An observation-driven optimization method for continuous estimation of soil moisture over large heterogeneous areas

ABSTRACT

In most remote sensing-based soil moisture (SM) retrieval methods, in-situ SM measurements are commonly used for validation purposes. Few studies have investigated whether such measurements can be used for calibration. In this paper, an observation-driven optimization method was proposed to estimate SM from remote sensing observations. Specifically, the optimization method was developed within the surface temperature-vegetation index (TVX) framework for the definition of objective function and constraints. In-situ SM measurements were used to optimize the theoretical boundaries of the TVX feature space. We demonstrated the applicability of the new method with Moderate Resolution Imaging Spectroradiometer (MODIS) products over the Southern Great Plains (SGP) of the United States of America. Results indicate that the accuracy produced using only one site for calibration has reached a level comparable with those produced by traditional methods. Moreover, the method has not only bypassed the complex parameterization of aerodynamic and surface resistance but also achieved continuous monitoring of SM. That is just the capacity that the traditional TVX method does not possess. Therefore, although our optimization method requires the ancillary of in-situ observations, its simplicity proves that it is a useful tool for a quick and continuous monitoring of SM over large heterogeneous areas.     

Scene classification in remote sensing images using a two-stage neural network ensemble model

Scene classification has long been a challenging task in the remote sensing field. Conventional approaches based on hand-crafted features are not suitable in large scale remote sensing images. Convolutional Neural Network (CNN) achieves great success in computer vision field by learning hierarchical features automatically from mass data. However, the shortage of labeled dataset in remote sensing field results in severe overfitting and the ensemble of several networks have better generalization ability than one single network. In this letter, we propose a novel Two-Stage Neural Network Ensemble Model to solve the problems mentioned above. Firstly, to overcome overfitting, we pre-train a CNN using the ImageNet dataset and fine tune the network by labeled remote sensing images. Then, the output features are fed to a Restricted Boltzmann Machine (RBM) Retrained Network to get better feature representations. Finally, in testing stage, a method based on Ensemble Inference Network (EIN) is introduced to enhance the generalization ability by combining the classification results of several networks. Experimental results on the UC Merced Land Use (UCML) dataset demonstrate the effectiveness of our proposed method.     

元数据研究在医学数据资源共享中的作用

目的在医学数据资源共享中,通过对元数据的研究对异构医学数据资源进行检索与发现.方法研究元数据的定义与特征,制定元数据标准、然后建立目录服务系统进行数据检索服务.结果建立了基于元数据的目录服务体系,实现了数据发现服务.结论元数据方法的研究是对异构数据进行检索与发现的有效方法,也是实现医学数据资源共享的重要途径.