Accurate object retrieval for high-resolution remote-sensing imagery using high-order topic consistency potentials

We propose incorporating semantic topic information into a hierarchical conditional random fields (CRFs) framework to promote object recognition and retrieval accuracy. Specially, we devise convenient yet effective methods based on multiple segmentations to perform accurate image retrieval tasks for rigid and amorphous man-made objects. Through a robust topic consistency potential (RTCP) modelling approach, we perform accurate multi-class segmentation on high-resolution remote-sensing images. The generated segments can be readily used for object recognition and discovery. We report satisfactory the performance on two sets of high-resolution remote-sensing images that cover a highly populated urban area and a rural area, respectively. Experimental results demonstrate that our approach outperforms the state-of-the-art CRF models, due to its ability to capture inherent semantic information for efficient object recognition and boundary discovery.     

Modified N-FINDR endmember extraction algorithm for remote-sensing imagery

The N-FINDR, developed by Winter, is one of the most widely used algorithms for endmember extraction for hyperspectral images. N-FINDR usually needs an outer loop to control the stopping rule and two inner loops for pixel replacement, so it suffers from computational inefficiency, particularly when the size of the remote-sensing image is large. Recently, geometric unmixing using a barycentric coordinate has become a popular research field in hyperspectral remote sensing. According to Cramer’s rule, a barycentric coordinate estimated by the ratios of simplex volumes is equivalent to a least-squares solution of a linear mixture model. This property implies a brand new strategy for endmember extraction. In other words, we can deduce endmembers by comparison only of abundances derived from a least-squares approach rather than a complicated volume comparison in N-FINDR. Theoretical analysis shows that the proposed method has the same performance as N-FINDR but with much lower computational complexity. In the experiment using real hyperspectral data, our method outperforms several other N-FINDR-based methods in terms of computing times.     

Particle swarm optimization-based sub-pixel mapping for remote-sensing imagery

Mixed pixels are widely existent in remote-sensing imagery. Although the proportion occupied by each class in mixed pixels can be determined by spectral unmixing, the spatial distribution of classes remains unknown. Sub-pixel mapping (SPM) addresses this problem and a sub-pixel/pixel spatial attraction model (SPSAM) has been introduced to realize SPM. However, this algorithm fails to adequately consider the correlation between sub-pixels. Consequently, the SPM results created by SPSAM are noisy and the accuracy is limited. In this article, a method based on particle swarm optimization is proposed as post-processing on the SPM results obtained with SPSAM. It searches the most likely spatial distribution of classes in each coarse pixel to improve the SPSAM. Experimental results show that the proposed method can provide higher accuracy and reduce the noise in the results created by SPSAM. When compared with the available modified pixel-swapping algorithm, the proposed method often yields higher accuracy results.     

Vectorial boundary-based sub-pixel mapping method for remote-sensing imagery

This article presents a vectorial boundary-based sub-pixel mapping (VBSPM) method to obtain the land-cover distribution with finer spatial resolution in mixed pixels. With inheritance from the geometric SPM (GSPM), VBSPM first geometrically partitions a mixed pixel using polygons, and then utilizes a vectorial boundary extraction model (VBEM), rather than the rasterization method in GSPM, to determine the location and length of each edge in the polygon, while these edges are located at the boundary of and within the interior of the mixed pixel. Furthermore, VBSPM uses a decay function to manage the mixed pixels along the image boundary region due to the missing parts of their neighbours. Finally, a ray-crossing algorithm is employed to determine the land-cover class of each sub-pixel in terms of vectorial boundaries. The experiments with artificial and remotely sensed images have demonstrated that VBSPM can reduce the inconsistency between the boundaries of different land-cover classes, approximately calculating errors with an odd zoom factor, and achieve more accurate sub-pixel mapping results than the hard classification methods and GSPM.     

Principal kurtosis analysis and its application for remote-sensing imagery

Fast Independent Component Analysis (FastICA) is the commonly used feature extraction method for non-Gaussian structure data and it is often used in multispectral/hyperspectral image processing. However, FastICA requires all pixels to be involved at each iteration. Therefore, it is a very time-consuming method when the total number of iterations is large. In this study, we propose an equivalent algebraic method for FastICA when selecting kurtosis as a non-Gaussian index. We name this new method principal kurtosis analysis (PKA). The feature extraction result of PKA is equivalent to that of FastICA when considering kurtosis as the measurement of non-Gaussianity. Similar to FastICA, PKA also applies the fixed-point iteration method to search for extreme kurtosis directions. However, when computing the projected direction in the iteration process, PKA only requires a co-kurtosis tensor and not all of the pixels. Therefore, this reduces the time complexity. The proposed algorithm (PKA) has been applied on multispectral and hyperspectral images and shows its time advantage in the experiments.     

Segmentation for remote-sensing imagery using the object-based Gaussian-Markov random field model with region coefficients

The Markov random field (MRF) model is a widely used method for remote-sensing image segmentation, especially the object-based MRF (OMRF) method has attracted great attention in recent years. However, the OMRF method usually fails to capture the correlation between regional features by just considering the mixed-Gaussian model. In order to solve this problem and improve the segmentation accuracy, this article proposes a new method, object-based Gaussian-Markov random field model with region coefficients (OGMRF-RC), for remote-sensing image segmentation. First, to describe the complicated interactions among regional features, the OGMRF-RC method employs the region size and edge information as region coefficients to build the object-based linear regression equation (OLRE) for each region. Second, the classic Gaussian-Markov model is extended to region level for modelling the errors in OLREs. Finally, the segmentation is achieved through a principled probabilistic inference designed for the OGMRF-RC method. Experimental results over synthetic texture images and remote-sensing images from different datasets show that the proposed OGMRF-RC method can achieve more accurate segmentation than other state-of-the-art MRF-based methods and the method using convolutional neural networks.     

Estimating crop-specific evapotranspiration using remote-sensing imagery at various spatial resolutions for improving crop growth modelling

By governing water transfer between vegetation and atmosphere, evapotranspiration (ET) can have a strong influence on crop yields. An estimation of ET from remote sensing is proposed by the EUMETSAT ‘Satellite Application Facility’ (SAF) on Land Surface Analysis (LSA). This ET product is obtained operationally every 30 min using a simplified SVAT scheme that uses, as input, a combination of remotely sensed data and atmospheric model outputs. The standard operational mode uses other LSA-SAF products coming from SEVIRI imagery (the albedo, the downwelling surface shortwave flux, and the downwelling surface longwave flux), meteorological data, and the ECOCLIMAP database to identify and characterize the land cover.

With the overall objective of adapting this ET product to crop growth monitoring necessities, this study focused first on improving the ET product by integrating crop-specific information from high and medium spatial resolution remote-sensing data. A Landsat (30 m)-based crop type classification is used to identify areas where the target crop, winter wheat, is located and where crop-specific Moderate Resolution Imaging Spectroradiometer (MODIS) (250 m) time series of green area index (GAI) can be extracted. The SVAT model was run for 1 year (2007) over a study area covering Belgium and part of France using this supplementary information. Results were compared to those obtained using the standard operational mode.

ET results were also compared with ground truth data measured in an eddy covariance station. Furthermore, transpiration and potential transpiration maps were retrieved and compared with those produced using the Crop Growth Monitoring System (CGMS), which is run operationally by the European Commission's Joint Research Centre to produce in-season forecast of major European crops. The potential of using ET obtained from remote sensing to improve crop growth modelling in such a framework is studied and discussed.

Finally, the use of the ET product is also explored by integrating it in a simpler modelling approach based on light-use efficiency. The Carnegie–Ames–Stanford Approach (CASA) agroecosystem model was therefore applied to obtain net primary production, dry matter productivity, and crop yield using only LSA-SAF products. The values of yield were compared with those obtained using CGMS, and the dry matter productivity values with those produced at the Flemish Institute for Technological Research (VITO). Results showed the potential of using this simplified remote-sensing method for crop monitoring.     

A WTLS-based rational function model for orthorectification of remote-sensing imagery

The rational function model (RFM) is widely applied to orthorectification of aerial and satellite imagery. This article proposes a new method named Ortho-WTLS to solve the RFM in remote-sensing imagery orthorectification. Based on a weighted total least squares (WTLS) estimator, the proposed method allows one to handle coordinates of ground control points (GCPs) that contain errors and are of unequal accuracies. This situation occurs, e.g. if GCPs are automatically selected. In the proposed model, first, the relationship of two linearization methods for an RFM with errors contained in GCPs is investigated and results in a hybrid linearization. Next, based on WTLS, RFM coefficients are estimated with an iterative computation function. Finally, the performance of the Ortho-WTLS method thus obtained is investigated using simulated images and remotely sensed images by collecting GCPs with varying errors. Experimental results show that the Ortho-WTLS method achieves a more robust estimation of model parameters and a higher orthorectification accuracy when compared with standard LS-based RFM estimation. We conclude that the quality of GCPs has a large impact on the accuracy and that an increasing number of low-precision GCPs may lead to a decrease in orthorectification quality.     

An unsupervised classifier for remote-sensing imagery based on improved cellular automata

Traditional unsupervised classification algorithms for remote-sensing images, such as k-means (KM), have been widely used for massive data sets due to their simplicity and high efficiency. However, they do not usually take the interaction between neighbouring pixels into account, but only take individual pixels as the elements for clustering and classification. According to Tobler’s first law of geography, everything is related to everything else, but near things are more related than distant things. To make use of the spatial interaction between pixels, the cellular automata method can be employed to improve the accuracy of image classification. In cellular automata theory, the state of a cell at the next moment is determined by its current state and that of its neighbours. In traditional cellular automata methods, which are based on a standard neighbour configuration, even if the influence of neighbouring cells on the central cell is measured, the weights of these influences are the same. Hence, this article proposes an improved cellular automata method for image classification by allowing the cellular automata to diffuse in a geometrical circle, and by measuring the influence of the neighbouring cells using a fuzzy membership function. The proposed classifier was tested with typical Landsat Enhanced Thematic Mapper Plus (ETM+) and high-resolution images. The experiments reveal that the new classifier can achieve better results, in terms of overall accuracy and kappa coefficient, than cellular automata classifier based on Moore type (CAS), KM, and fuzzy c-means.     

Synthetic satellite imagery for current and future environmental satellites

During the next decade, data from a new generation of US geostationary and polar orbiting satellites will become available. To prepare for these data, representative imagery of these satellites is desirable. Two independent methods have been developed to create imagery from future satellites before they are placed into orbit. One method uses data from current operational and experimental satellites. Data obtained this way are referred to as simulated imagery. Another method generates satellite imagery by using numerical models. Data obtained by this method are referred to as synthetic imagery. Each method has some weaknesses that can be overcome by using both methods together. Synthetic imagery for two future US sensors is introduced in this paper. Emphasis is placed on a severe thunderstorm event.     

Effective compression of hyperspectral imagery using an improved 3D DCT approach for land-cover analysis in remote-sensing applications

Although hyperspectral imagery (HSI), which has been applied in a wide range of applications, suffers from very large volumes of data, its uncompressed representation is still preferred to avoid compression loss for accurate data analysis. In this paper, we focus on quality-assured lossy compression of HSI, where the accuracy of analysis from decoded data is taken as a key criterion to assess the efficacy of coding. An improved 3D discrete cosine transform-based approach is proposed, where a support vector machine (SVM) is applied to optimally determine the weighting of inter-band correlation within the quantization matrix. In addition to the conventional quantitative metrics signal-to-noise ratio and structural similarity for performance assessment, the classification accuracy on decoded data from the SVM is adopted for quality-assured evaluation, where the set partitioning in hierarchical trees (SPIHT) method with 3D discrete wavelet transform is used for benchmarking. Results on four publically available HSI data sets have indicated that our approach outperforms SPIHT in both subjective (qualitative) and objective (quantitative) assessments for land-cover analysis in remote-sensing applications. Moreover, our approach is more efficient and generates much reduced degradation for subsequent data classification, hence providing a more efficient and quality-assured solution in effective compression of HSI.     

Statistical characterization of the sea ice extent during different winter scenarios in the Gulf of Riga (Baltic Sea) using optical remote-sensing imagery

This study focuses on the statistical characterization of ice conditions (extent, sea ice occurrence probability (SIOP), and length of ice season) in the Gulf of Riga, Baltic Sea, using remote-sensing data. The optical remote-sensing data with 250 m resolution acquired by a Moderate Resolution Imaging Spectroradiometer (MODIS) during 2002–2011 were used for statistical characterization of sea ice. A method based on bimodal histogram analysis of remote-sensing reflectance data was developed to discriminate ice from water. In general, ice extent information obtained from MODIS data agrees with the official ice chart data (synthetic aperture radar (SAR) and in situ measurements) and multi-sensor product containing data from microwave and infrared instruments (R² >0.83). However, in case of severe winters and extremely mild winters there are differences in the dates when maximum ice extent is registered. MODIS data can be used for detailed analysis of ice extent in specific basins of Baltic Sea. Depending on the year, the ice season length in the Gulf of Riga ranged from 68 to 146 days, and the maximum ice extent varied greatly from 329 to 15,350 km². SIOP and number of ice days increased significantly in areas where the depth is less than 15 m. Based on negative-degree days and ice cover characteristics (SIOP and ice season length), three winter scenarios were defined: severe (2003, 2006, 2010, and 2011), medium (2004 and 2005), and mild (2007, 2008, and 2009).     

Multi-layer sparse coding model-based ship detection for optical remote-sensing images

Ship detection plays an important role in remote-sensing image processing. In this article, we propose a multi-layer sparse coding model-based ship detection (MSCMSD) method, integrating bottom-up and top-down mechanisms, for ship detection with high-resolution remote-sensing images. The multi-layer sparse coding model was designed to reveal the way how information is processed by human visual system. It is adopted in MSCMSD to detect candidate regions containing ships before any further processing. To detect ships from candidate regions, an omnidirectional solution is also proposed for deformable parts model-based ship detection. As demonstrated in the experiments, MSCMSD can detect ships from optical remote-sensing images with a higher accuracy than other state-of-the-art algorithms.     

A modified mean filter for improving the classification performance of very high-resolution remote-sensing imagery

Very high resolution (VHR) remote-sensing imagery can reveal ground objects in great detail, depicting the colour, shape, size and structure of the objects. However, VHR also leads to a large amount of noise in the spectra, which may reduce the reliability of the classification result. This article presents an extension of the mean filter (MF), which is named ‘modified mean filter (MMF)’, for smoothing the noise of VHR imagery. First, the MMF is a shape-adaptive filter that is constructed by gradually detecting the spectral similarity between a kernel-anchored pixel and its contextual pixels through an extension detector with eight neighbouring pixels. Then, because pixels of an objective are usually homogeneous with spatial continuity, the pixels located at the hollow area within an extended region are rectified to enhance the smoothing effect. Finally, the spectral value of the kernel-anchored pixel is determined by the mean of the group of pixels within the adaptive region. Despite the proposed filter is a simple extension of MF, it has an advantage in preserving the edge between different classes, and smoothing the noise of intra-class. The MMF approach is investigated through comparing with the classification of VHR images based on filter processing, including the traditional mean filter (MF), the median filter (MedF) and the recursive filter (RF) which has been proposed for image classification in Kang, Li, and Benediktsson (2014). The experimental results obtained by considering two VHR images show the effectiveness of the proposed of MMF, which improves the performance of the classification and implies more potential applications.     

Orbit determination using incremental phase and TDOA of X-ray pulsar

X-ray pulsars offer stable, periodic X-ray pulse sequences that can be used in spacecraft positioning systems. A method using X-ray pulsars to determine the initial orbit of a satellite is presented in this paper. This method suggests only one detector to be equipped on the satellite and assumes that the detector observes three pulsars in turn. To improve the performance, the use of incremental phase in one observation duration is proposed, and the incremental phase is combined with the time difference of arrival (TDOA). Then, a weighted least squares (WLS) algorithm is formulated to calculate the initial orbit. Numerical simulations are performed to assess the proposed orbit determination method.     

A modified object-oriented classification algorithm and its application in high-resolution remote-sensing imagery

High-resolution satellite images offer abundant information on the Earth's surface for remote-sensing applications. The traditional pixel-based image classification method only used by spectral information has been proved to have several drawbacks. To satisfactorily interpret high-resolution imagery, other important information such as geometry, texture and semantics must be used, which are represented not only in single pixels but in meaningful image objects. So, a modified high-resolution image classification algorithm with multi-characteristics based on objects is presented in this article. First, image objects are extracted by multi-scale multi-characteristic segmentation. Second, characteristics such as spectral information, geometry, texture and semantics are extracted by the corresponding extraction algorithm. Finally, the image objects are classified by means of fuzzy-logic classification with a weighted average calculation method. Preliminary results show promise in terms of classification quality and accuracy.     

Automatic on-orbit geometric calibration framework for geostationary optical satellite imagery using open access data

Due to a variety of factors, long-term on-orbit geometric calibrations must be performed on the geostationary optical satellite to meet the subsequent high-precision geometric processing requirements. Designing a fully automatic on-orbit geometric inspection and calibration process has great application value. In this paper, we use open-access geographic information data to achieve a more robust automatic on-orbit geometric calibration for the imaging characteristics of the geostationary optical satellite. Experiments with the high-resolution geostationary optical satellite GaoFen4. Results show that the process designed in this paper enables automatic on-orbit geometric calibration of the geostationary optical satellite and obtain high-accuracy calibration parameters, thus effectively improving the geometric positioning accuracy of satellite imagery.