Search

There are significant nonlinear intensity differences between multi-modal images. Moreover, the noise in these images will cause image degradation. Therefore, the automatic registration of multi-modal images is a challenging task. To address the two problems, this paper proposes a multi-modal image automatic registration method, which is divided into two stages: pre-registration and fine registration. In the pre-registration stage, an improved SIFT algorithm is used to roughly align multi-modal images. In the fine registration stage, the block Harris detector is first used to extract evenly distributed feature points on the pre-registered reference image. Then, the structure information in the multi-modal images is captured by the anisotropic structure tensor to construct a feature descriptor, which is robust to noise. Furthermore, a similarity criterion named TOMI (tensor orientation and mutual information) is proposed combining the tensor orientation parallelism and gradient mutual information. Finally, Multi-modal images (including Optical, LiDAR, SAR, and Map data) are used to evaluate the proposed algorithm. The experimental results show that the method proposed in this paper is robust to nonlinear intensity differences and noise, and the matching effect is superior.

Because of the lack of relationships between matching line and adjacent lines in the process of individual line matching, and the weak reliability of the individual line descriptor facing on discontinue texture, this paper presents a reliable line matching algorithm for stereo images with topological relationship. The algorithm firstly generates grouped line pairs from lines extracted from the reference image and searching image according to the basic topological relationships such as distance and angle between the lines. Then it takes the grouped line pairs as matching primitives, and matches these grouped line pairs by using epipolar constraint, homography constraint, quadrant constraint and gray correlation constraint of irregular triangle in order. And finally, it resolves the corresponding line pairs into two pairs of corresponding individual lines, and obtains one to one matching results after the post-processing of integrating, fitting, and checking. This paper adopts digital aerial images and close-range images with typical texture features to deal with the parameter analysis and line matching, and the experiment results demonstrate that the proposed algorithm in this paper can obtain reliable line matching results.

This paper introduces the extended collinearity equations into aerial triangulation of the vehicle-borne multi-camera rig images to improve the positioning accuracy. The cameras in a multi-camera rig are rigidly fixed and the relative position and orientation parameters among the mono cameras of multi-camera rig can be calibrated accurately, so the extended collinearity equations can be used to extend the imaging unit from a mono camera image to multiple images of multi-camera rigs. Compared with the existing spherical models, including the spherical ideal model and the spherical rigorous model, the extended collinearity equations used in this paper avoid the spherical projection error and fusion error caused by the misalignment of projection centers. Experimental results show that the method omits the processing procedure of model projection and fusion of overlap areas, which avoids the precision loss and complicated processing procedure, and finally obtains more robustness triangulation net, more precise and robust position accuracy.

Spherical panoramic imaging can overcome the limitations of perspective imaging's range of view and achieve three-dimensional reconstruction and measurement with full coverage.The EPnP(efficient perspective-n-point) algorithm fit for ordinary image's position and pose estimation is improved and extended by this paper to put forward a robust and fast method to estimate spherical panoramic image's position and pose. Firstly,we construct the projection model of spherical panoramic image to extend the perspective plane imaging model of EPnP algorithm to the spherical imaging model;then with the improved EPnP algorithm basing on the condition equation that panoramic sphere center,image point and control point are collinear, we obtain the control points' coordinates in spherical panoramic image space; finally, we solve the spherical panoramic image's position and pose directly with the Horn absolute positioning algorithm. Compared with the position and pose estimation method of spherical panoramic image with the resection algorithm, the experiment results show that the method proposed in this paper can achieve higher robustness, higher efficiency without going through an iterative solution, and it can also achieve high accuracy with a few control points.Based on the panoramic camera stitching with non-strict center, the reprojection error can be controlled around 3.00 pixel level.

Island and coastal image segmentation is of great importance for the subsequent coastline extraction, terrain inversion for intertidal zone, analysis of the situation for shore evolution, and so on. Firstly, the advantages and disadvantages of quadtree, geodesic active contour (GAC) model and Canny edge detector used in the island and coastal image segmentation are analyzed. Secondly, an island and coastal image segmentation method is proposed by integrating quadtree, GAC model and Canny edge detector. The advantages of these three kinds of method are taken in the method proposed in this paper. The method introduces the results of Canny edge detector into edge indicator function of geodesic active contour model based on quadtree segmentation, evolutes the level set equation, and realizes island and coastal image segmentation.The experimental results show that the method proposed in this paper is of high speed, precision, reliability and automation for island and coastal image segmentation, even in the weak edges and serious concave edges.

To solve the problem of matching difficulty caused by the significant nonlinear grayscale differences between SAR and optical images, this paper proposes a fast matching algorithm based on image structural properties named SOFM(SAR-to-optical fast matching algorithm).The traditional methods based on image grayscale are generally difficult to resist the nonlinear grayscale differences between SAR and optical images, but the geometric constructs and shape features can exist stably among different types of images, so in our the proposed method both the magnitude and orientation information of image gradient are used to build a geometric structural feature descriptor named AWOG(angular weighted orientated gradients), then based on the template matching strategy, the sum of squared difference of the descriptors is used to define the similarity metric for matching and then the image matching function expressed in the frequency domain is given. A complete set of image matching process is established based on SOFM, and has been validated using multiple pairs of SAR and optical images, the results show that the proposed method can effectively resist the nonlinear grayscale differences between SAR and optical images, and outperforms the traditional classical image grayscale-based methods and existing image structural-based methods in matching performance and precision.

In order to solve the problem that the parameters of pulse-coupled neural network can't be adjusted adaptively in pan-sharpening image fusion, a non-subsampled shearlet transform remote sensing image fusion method based on the combination of parametric-adaptive pulse coupled neural network model and energy-attributing fusion strategy is proposed. First, the high and low frequency coefficients are obtained by extracting the Y luminance component of the multispectral image YUV color space transform and transforming it with the panchromatic image. Then, aiming at the low-frequency sub-band coefficients are fused by the EA method, the high-frequency sub-band coefficients are obtained by the PA-PCNN model to determine the optimal PCNN model, and then the high-frequency sub-band coefficients are fused; finally, the fusion image is obtained by inverse transformation of NSST and YUV. In this paper, six objective quality indexes, such as spatial frequency, relative dimensionless global error, ERGAS, correlation coefficient, visual information fidelity for fusion, gradient-based fusion performance and structural similarity index, are selected to evaluate the spectral and spatial detail information of the fused images, compared with SE, DGIF, COF and PA-PCNN fusion methods, the proposed method is validated by using multiple sets of high-and low-resolution panchromatic and multispectral remote sensing images, the results show that this method is generally superior to the traditional fusion method of panchromatic and multispectral remote sensing images in objective evaluation and visual perception.

Denoising fitting of airborne laser bathymetry data is a key step in extracting the bottom terrain. The algorithm effects of wavelet adaptive threshold denoising, empirical model denoising (EMD) and joint denoising are compared in this paper, and then multivariate Gaussian fitting is used to test the denoising effect. The optimal denoising algorithm and parameter selection are obtained by comparison, and it is realized that the high-precision extraction of seabed features. This study has shown that: when the sounding data is denoised by wavelet threshold, the fixed threshold wavelet denoising effect is superior to other denoising effects, and the denoising decomposition level is more than 6 layers, which tends to be stable. The average accuracy of the algorithm reaches 8.218 2 after the fifth-order Gaussian fitting of the denoising data. The algorithm has strong robustness, it can meet the technical requirements of blue-green laser practical application, and provides a reference for accurately extracting seafloor feature information.

Aiming at the problems of nonlinear gray difference, speckle noise and different imaging viewpoints in SAR and optical image registration, this paper presents a SAR and optical images registration using uniform distribution and structure description-based ASIFT. In the proposed algorithm, firstly, the guided scale space is constructed by guided filter to achieve noise suppression and edge preservation. In the feature extraction stage, the phase congruency is utilized due to the nonlinear gray difference, and combined with scale space gridding to extract from images for the uniform feature points. In the feature description stage, the consistency gradient magnitude and orientation of SAR and optical image are calculated by extended phase congruency method, which improves the accuracy of the main orientation and descriptor. At last, Optimal-RANSAC is used to establish feature descriptor matching to achieve effective registration. The simulation experiment and analysis on four pairs of real images show that the proposed algorithm has more accurate registration accuracy than SAR-SIFT and traditional ASIFT.

Spectral library-based hyperspectral sparse unmixing technology has received attention in recent years, which uses spectral samples in the spectral library as endmembers and transforms the unmixing problem into a sparse representation problem. However, due to differences in the measurement environment, the actual endmembers of the hyperspectral image to be unmixed tend to differ from the corresponding spectral signatures in the spectral library. In this paper, an unmixing algorithm named spectral difference sparse constrained collaborative sparse regression is proposed. Firstly, we assume that the spectral differences have sparse property, and a spectral library correction model is established, which can make the spectral library be adaptively adjusted during the unmixing process; Then, the spectral library correction model is combined with the collaborative sparse regression unmixing model to establish a sparse unmixing model considering spectral differences; Finally, an iterative optimization solution based on the alternating direction method of multipliers is given. Synthetic and real hyperspectral data are used to verify the performance of different algorithms. The results show that the proposed algorithm is more effective than the compared algorithms in the presence of spectral library mismatches.

Hyperspectral remote sensing image has the characteristics of rich spectral information and combining image with spectrum, which has been widely applied in the earth observation. Most of traditional hyperspectral image classification models don't make fully use of spatial feature information, rely too much on the spectral imformation, making the classification accuracy still have a lot of room to improve. Conditional random field (CRF) is a kind of probability mode that can better integrate spatial context information. It plays a more and more important role in hyperspectral image classification. However, most CRF models have the problem of excess smoothness, which will result in the loss of detail information. Aiming at this problem, this paper proposed a hyperspectral image classification method based on space-spectral fusion conditional random field. The proposed method designs suitable potential functions in a pairwise conditional random field model, fusing the spectral and spatial features to consider the spatial feature information and retain the details in each class. The experiments on two sets of hyperspectral image showed that, compared with the traditional methods, the proposed classification method can effectively improve the classification accuracy, protect the edges and shapes of the features, and relieve excessive smoothing, while retaining detailed information.

This paper presents a review of the advances, products and applications of lunar photogram-metric mapping using orbital images. It mainly introduces the key techniques such as construction and refinement of geometric models of lunar orbital images, co-registration of lunar orbital image and digital elevation model, optimal selection of multiple images, and large area mapping. Engineering and science applications of lunar photogrammetric mapping products are described, with more emphases on the Chang'E lunar exploration missions. Finally, the future research directions are discussed.

With the development of radar imaging technology and the diversification of imaging modes, the accuracy of coregistration in the direction of azimuth required by SAR interferometry is different. At present, due to the strict theoretical model and the high accuracy, the coregistration scheme with the image information based on geometric coregistration under the condition of precise orbits become the first choice for interference processing. In this paper, TerraSAR-X images have been taken as an example to demonstrate the accuracy of interferometric coregistration and satellite orbit required by different imaging modes. Furthermore, theoretical analysis and experimental validation have also been applied. It is proved that under the condition of precise orbits, SAR interferometric processing of strip-mode image of TerraSAR-X and other satellites can be achieved by geometric registration. While, spotlight imaging mode requires image coherence or spectral diversity to further optimization of the geometric coregistration results. Since the ESD (Enhanced Spectral Diversity) offset estimation method offers the highest accuracy. It has been used to estimate the geometric coregistration errors of Sentinel-1 satellite images with different orbit and DEM conditions. The results suggest that geometric coregistration error is mainly caused by the tangential error of the satellite orbit, and the difference of geometric corregistration of three kinds of DEM is much less than 0.001 pixels, which can meet the needs of Sentinel-1 image interference registration.

Multimodal image registration method based on feature matching can't satisfy the demands of pixel level registration precision.This paper proposes a multimodal image registration algorithm considering grayscale and gradient information.The nonparametric registration model based on Markov random field (MRF) makes full use of the image information of multimodal image to measure the similarity which considers the grayscale and the gradient statistical information are considered,and the value space is discretized to improve the convergence speed.The algorithm is validated both qualitatively and quantitatively demonstrating its potentials on three groups of multimodal image registration experiments.The result indicates that the proposed algorithm is superior to the polynomial model registration based on manual selection and the multimodal image registration only with gray information only.At the same time,this algorithm has some applicability for multimodal image registration of large deformation.In terms of spatial accuracy,the average registration error is less than 1 pixel and the maximum registration error is less than 2 pixels.

For a large collection of satellite images,because of the differences in season,light,atmospheric conditions and so on,adjacent satellite images may have different color and there will be obviously "seam-line" in mosaic satellite image.In this paper,a method of satellite image color normalization was proposed,it was implemented to correct the color of image automatically based on better color low resolution satellite imagery which covered the mapping area.We selected a large collection and long time interval GF-1 satellite images as experiment data,results show that the mosaic image have a good visual effect,the color transition of two images smoothly,statistical indicators of overlap area obviously improved,all of those verified the validity and reliability of the algorithm.

This paper improves the method of the traditional 5-point relative pose estimation algorithm, and proposes a relative pose estimation algorithm which is suitable for spherical panoramic images. The algorithm firstly computes the essential matrix, then decomposes the essential matrix to obtain the rotation matrix and the translation vector using SVD, and finally the reconstructed three-dimensional points are used to eliminate the error solution. The innovation of the algorithm lies the derivation of panorama epipolar formula and the use of the spherical distance from the point to the epipolar plane as the error term for the spherical panorama co-planarity function. The simulation experiment shows that when the random noise of the image feature points is within the range of pixel, the error of the three Euler angles is about 0.1°, and the error between the relative translational displacement and the simulated value is about 1.5°. The result of the experiment using the data obtained by the vehicle panorama camera and the POS shows that:the error of the roll angle and pitch angle can be within 0.2°, the error of the heading angle can be within 0.4°, and the error between the relative translational displacement and the POS can be within 2°. The result of our relative pose estimation algorithm is used to generate the spherical panoramic epipolar images, then we extract the key points between the spherical panoramic images and calculate the errors in the column direction. The result shows that the errors is less than 1 pixel.

Due to the noise sensitivity and limited directivity of extracted edge presented in current edge detection algorithms, it is difficult to effectively extract the edges with any direction between the two regions with similar intensities from SAR images. In this paper, an edge extraction algorithm of SAR image using two symmetric windows is proposed. The position of grid point of any pixel in SAR image is employed as a symmetric center, then symmetric windows in any direction are constructed by the symmetric center. The kernel function of distances from the central pixel to pixels in each window is defined, then the weighted averages of pixel spectral measurements are calculated for the two symmetric windows, respectively. The absolute value of difference between above averages is employed as edge degree of the central pixel on this direction, and maximum degree from all directions is selected to judge the pixel as an edge pixel. To delete error edge pixels extracted, post-processing procedure based on filtering operation is designed. The interferences of speckle noises are overcome to some extent and edges in random direction are extracted accurately by the proposed algorithm, respectively, which is shown by qualitative and quantitative analysis of the edge extraction results from analog images.

Image segmentation is the basic and key step of object-oriented remote sensing image analysis. Conventional image segmentation method is sensitive to image noise and hard to determine the correct segmentation scale. To solve these problems, a novel image segmentation method by combining superpixels with minimum spanning tree was proposed in this paper. First, the image is over-segmented by simple linear iterative clustering algorithm to obtain superpixels. Then, superpixels are firstly clustered by regionalization with dynamically constrained agglomerative clustering and partitioning algorithm using the initial segmentation number and the sum of squared deviations (SSD), local variance (LV), rate of LV change (ROC-LV) index of graphs corresponding to the segmentation number are obtained. So the suitable image segmentation number is determined according to the SSD, LV, ROC-LV index of graphs corresponding to segmentation number. Finally, superpixels are reclustered by regionalization with dynamically constrained agglomerative clustering and partitioning algorithm based on the suitable segmentation number. The experimental results showed that the proposed method can obtain good segmentation results.

In this paper, a new cloud removal method in remote sensing images is adopted.Based on the theory of compressive sensing,this method combines K-SVD dictionary learning with the orthogonal matching pursuit(OMP) algorithm of sparse representation.At the same time, a specific sorting rule is added to the process of dictionary atoms training, so that each image dictionary has its own image properties while its atoms also have a similar arrangement order to reduce the interference between image differences.In this method,the good effect of reconstruction of the contaminated region by clouds and shadows in remote sensing images is achieved.To illustrate the performance of the proposed method,experiments on two sets of data of multitemporal ZY-3 images at the same area are discussed.

With the rise of virtual reality (VR) technology, panoramic images are used more widely, which obtained by multi-camera stitching and take advantage of homography matrix and image transformation, however, this method will destroy the collinear condition, make it's difficult to 3D reconstruction and other work. This paper proposes a new method for cylindrical panoramic image mosaic, which set the number of mosaic camera, imaging focal length, imaging position and imaging attitude, simulate the mapping process of multi-camera and construct cylindrical imaging equation from 3D points to 2D image based on photogrammetric collinearity equations. This cylindrical imaging equation can not only be used for panoramic stitching, but also be used for precision analysis, test results show: ①this method can be used for panoramic stitching under the condition of multi-camera and incline imaging; ②the accuracy of panoramic stitching is affected by 3 kinds of parameter errors including focus, displacement and rotation angle, in which focus error can be corrected by image resampling, displacement error is closely related to object distance and rotation angle error is affected mainly by the number of cameras.

In order to solve the problem of texture optimization in 3D city reconstruction by using multi-lens oblique images, the paper presents a method of seamless texture model reconstruction. At first, it corrects the radiation information of images by camera response functions and image dark channel. Then, according to the corresponding relevance between terrain triangular mesh surface model to image, implements occlusion detection by sparse triangulation method, and establishes the triangles' texture list of visible. Finally, combines with triangles' topology relationship in 3D triangular mesh surface model and means and variances of image, constructs a graph-cuts-based texture optimization algorithm under the framework of MRF(Markov random filed), to solve the discrete label problem of texture optimization selection and clustering, ensures the consistency of the adjacent triangles in texture mapping, achieves the seamless texture reconstruction of city. The experimental results verify the validity and superiority of our proposed method.

In this paper an automated camera self-calibration method based on large scale aerial images coplanarity constraint is proposed. The method uses stereo images corresponding points to compute camera inner parameters and the distortion coefficients based on coplanarity constraint. Firstly, aerial images corresponding points are matched and stereo images are constructed. Then the relative orientation of the camera is resolved by using the direct method and the iterative optimization based on the coplanarity constraint. Finally, the least square optimization method is used to calculate the inner parameters and the distortion coefficients of the camera. For large image the distortion of image boundary is more severe than center, in order to compute parameters more precisely mesh partition in arbitrary area of image is proposed. Compared with classical techniques which use expensive equipment or calibration field, the proposed technique can reflect the actual inner parameters of the camera in the real environment. Using all the corresponding points avoid the influence of choosing different feature points or control points on the calibration accuracy.Experimental results indicate that it is effective and flexible.The accuracy of the method is equivalent to that of calibration field, which can accurately reflect the camera parameters and the distortion coefficients of the image acquired by aerial photogrammetry.

Considering the correlationship of spectral content between anomaly and clutter background, inaccurate selection of background pixels induced estimation error of background model. In order to solve the above problems, a multi-aperture mapping based anomaly detector was proposed in this paper. Firstly, differing from background model which focused on feature extraction of background, multi-aperture mapping of hyperspectral data characterized the feature of whole hyperspectral data. According to constructed basis set of multi-aperture mapping, anomaly salience index of every test pixel was proposed to measure the relative statistic difference. Secondly, in order to analysis the moderate salience anomaly precisely, membership value was constructed to identify anomaly salience of test pixels continuously based on fuzzy logical theory. At same time, weighted iterative estimation of multi-aperture mapping was expected to converge adaptively with membership value as weight. Thirdly, classical defuzzification was proposed to fuse different detection results. Hyperspectral data was used in the experiments, and the robustness and sensitivity to anomaly with lower silence of proposed detector were tested.

After the characteristics of geodesic active contour model (GAC), Chan-Vese model(CV) and local binary fitting model(LBF) are analyzed, and the active contour model based on regions and edges is combined with image segmentation method based on quad-tree, a waterline extraction method based on quad-tree and multiple active contour model is proposed in this paper. Firstly, the method provides an initial contour according to quad-tree segmentation. Secondly, a new signed pressure force(SPF) function based on global image statistics information of CV model and local image statistics information of LBF model has been defined, and then ,the edge stopping function(ESF) is replaced by the proposed SPF function, which solves the problem such as evolution stopped in advance and excessive evolution. Finally, the selective binary and Gaussian filtering level set method is used to avoid reinitializing and regularization to improve the evolution efficiency. The experimental results show that this method can effectively extract the weak edges and serious concave edges, and owns some properties such as sub-pixel accuracy, high efficiency and reliability for waterline extraction.

Due to the problem of the existing image segmentation methods applied in side scan sonar (SSS) image often suffered from low efficiency or low accuracy, this paper proposed a novel SSS image thresholding segmentation method based on neutrosophic set (NS) and quantum-behaved particle swarm optimization (QPSO) algorithm. Firstly, the image gray co-occurrence matrix is constructed in NS domain, the fine texture of SSS image is expressed, and this can improve the accuracy of SSS image segmentation. Then, based on the two-dimensional maximum entropy theory, the optimal two-dimensional segmentation threshold vector is quickly and accurately obtained by QPSO algorithm, and this can improve the efficiency and accuracy of SSS image segmentation. Finally, the accurate and high efficient target segmentation of SSS image with high noises is realized. The effectiveness of the algorithm is verified by segmenting SSS image containing different targets.

Image fusion is one of the important steps to obtain high quality images.In this paper, the variation of signal frequency in image fusion is given according to the relationship between Nyquist frequency of high sampling rate,Nyquist frequency of low sampling rate and signal frequency.Then the frequency of the fused images is quantifying and the spatial resolution of the image is determined based on the the variation of signal frequency in image fusion.The high frequency information in the high resolution image is the information with the frequency between the Nyquist frequency of high sampling rate and the Nyquist frequency of low sampling rate.Finally, some fusion methods and remote sensing images are used to validate the proposed method. The experimental results show that the results obtained are consistent with the results of the experiment.

Cloud detection is always an arduous problem in satellite imagery processing, especially the thin cloud which has the similar spectral characteristics as ground surfacehas long been the obstacle of the production of imagery product. In this paper, an automatic cloud detection method for Chinese high resolution remote sensing satellite imagery is introduced to overcome this problem.Firstly, the image is transformed from RGB to HIS color space by an improved color transformation model. The basic cloud coverage figure is obtained by using the information of intensity and saturation,followed by getting the modified figure with the information of near-infrared band and hue. Methods of histogram equalization and bilateral filtering, combined with conditioned Otsu thresholding are adopted to generate texture information. Then the cloud seed figureis obtained by using texture information to eliminate the existed errors in the modified figure. Finally, cloud covered areas are accurately extracted by integration of intensity information from the HIS color space and cloud seed figure. Compared to the detection results of other automatic and interactive methods, the overall accuracy of our proposed method achieves nearly 10% improvement, and it is capable of improving the efficiency of cloud detection significantly.

Generally, spatial-contextual information would be used in change detection because there is significant speckle noise in synthetic aperture radar(SAR) images. In this paper, using the rich texture information of SAR images, an unsupervised change detection approach to high-resolution SAR images based on texture feature vector and maximum entropy principle is proposed. The difference image is generated by using the 32-dimensional texture feature vector of gray-level co-occurrence matrix(GLCM). And the automatic threshold is obtained by maximum entropy principle. In this method, the appropriate window size to change detection is 11×11 according to the regression analysis of window size and precision index. The experimental results show that the proposed approach is better could both reduce the influence of speckle noise and improve the detection accuracy of high-resolution SAR image effectively; and it is better than Markov random field.

There is an exterior orientation difference in each satellite video frame, and the corresponding points have different image locations in adjacent frames images which has geometric distortion. So the projection model, affine model and other classical image stabilization registration model cannot accurately describe the relationship between adjacent frames. This paper proposes a new satellite video image stabilization method with geometric distortion to solve the problem, based on the simulated satellite video, we verify the feasibility and accuracy of proposed satellite video stabilization method.

For a given pixel, fractional abundances predicted by spectral mixture analysis (SMA) are most accurate when only the endmembers that comprise it are used. This paper presents a support vector machines (SVM) method to achieve land use/land cover fractions of remote sensing image using two steps: ①defining the optimal per-pixel endmember set, which removes endmembers based on negative fractional abundances generated by SVM method; ②using SVM extended with pairwise coupling (PWC) to output probabilities as the abundance of landscape fractions. The performances of the proposed method were evaluated with the multiple endmember spectral mixture analysis (MESMA) method, which has been widely applied to map land cover for the goodness of the model fitting. The results obtained in this study were validated by real fractions generated from SPOT high resolution geometric (HRG) image. The best classification results were obtained by the proposed method indicated by the lower total mean absolute error, the higher overall accuracy, and the higher kappa. From this study, the proposed method is proved to be effective in obtaining abundance fractions that are physically realistic (sum close to one and nonnegative), and providing valuable application in selecting endmembers that occur within a pixel.

For the defect that harmonic analysis algorithm for hyperspectral image fusion(HAF) in image fusion regardless of spectral reflectance curves, the improved fusion algorithm for hyperspectral remote sensing image combined with harmonic analysis and Gram-Schmidt transform(GSHAF) is proposed in this paper. On the basis of completely retaining waveform of spectrum curve of fused image pixel, GSHAF algorithm can simplify hyperspectral image fusion to between the two-dimensional image by harmonic residual of each pixel spectral curve and high spatial resolution image. It is that the spectral curve of original hyperspectral image can be decomposed into harmonic residual, amplitude and phase, then GS transform with harmonic residual and high spatial resolution image, which can effectively amend spectral reflectance curve of fused image pixel. At last, this fusion image, harmonic amplitude and harmonic phase are inverse harmonic transformed. Finally, with Hyperion hyperspectral remote sensing image and ALI high spatial resolution image to analysis feasibility for GSHAF, then with HJ-1A and other satellite data to verify universality. The result shows that the GSHAF algorithm can not only completely retained the waveform of spectral curve, but also maked spectral reflectance curves of fused image more close to real situation.

A hyperspectral images classification method based on the weighted probabilistic fusion of multiple spectral-spatial features was proposed in this paper. First, the minimum noise fraction (MNF) approach was employed to reduce the dimension of hyperspectral image and extract the spectral feature from the image, then combined the spectral feature with the texture feature extracted based on gray level co-occurrence matrix (GLCM), the multi-scale morphological feature extracted based on OFC operator and the end member feature extracted based on sequential maximum angle convex cone (SMACC) method to form three spectral-spatial features. Afterwards, support vector machine (SVM) classifier was used for the classification of each spectral-spatial feature separately. Finally, we established the weighted probabilistic fusion model and applied the model to fuse the SVM outputs for the final classification result. In order to verify the proposed method, the ROSIS and AVIRIS image were used in our experiment and the overall accuracy reached 97.65% and 96.62% separately. The results indicate that the proposed method can not only overcome the limitations of traditional single-feature based hyperspectral image classification, but also be superior to conventional VS-SVM method and probabilistic fusion method. The classification accuracy of hyperspectral images was improved effectively.

In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification, a novel approach based on the combination of spatial-spectral feature and sparse representation is proposed in this paper. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first d principal components(PCs) into a vector representation, followed by a sorting scheme to make the vector invariant to local image rotation. Secondly, we learn the dictionary through a supervised method, and use it to code the features from test samples afterwards. Finally, we embed the resulting sparse feature coding into the support vector machine(SVM) for hyperspectral image classification. Experiments using three hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classification methods.

The process of super resolution image reconstruction is such a process that multiple observations are taken on the same target to obtain low resolution images, then the low resolution images are used to reconstruct the real image of the target, namely high resolution image. This process is similar to that in the field of surveying and mapping, in which the same target is observed repeatedly and the optimal values is calculated with surveying adjustment methods. In this paper, the method of surveying adjustment is applied into super resolution image reconstruction. A integral nonlinear adjustment model for super resolution image reconstruction is proposed at first. And then the model is parameterized with a quadratic function. Finally the model is solved with the least squares adjustment method. Based on the proposed adjustment method, the specific strategy of image reconstruction is presented. This method for super resolution image reconstruction can make quantitative analysis of the results, and avoid successfully ill-condition problem, etc. The results show that, compared to the traditional method of super resolution image reconstruction, this method has greatly improved the visual effects, and the PSNR and SSIM has also greatly improved, so the method is reliable and feasible.

In order to satisfy the requirement of identification and tracking the elliptical artificial targets fast and accurately for the image sequences from videogrammetric measurement for structural health monitoring, this paper proposes a systemic algorithm to identify and track the elliptical targets using the image block technique. The proposed method extracts the image block from original images to reduce the amount of data processing for the oval targets tracking. The mathematical morphology and elliptical geometric characteristics are integrated to eliminate the non-elliptical edge information to extract the elliptical contour in the range of image block. At last, the sub-pixel center location for elliptical artificial targets is acquired by the least square algorithm. The experimental results show that RMS error of 0.025 pixel can be achieved by the proposed method, furthermore, compared with the random Hough transform and template recognition algorithm, the tracking efficiency is improved over 5 times.

This paper proposed a quick, affine invariance matching method for oblique images. It calculated the initial affine matrix by making full use of the two estimated camera axis orientation parameters of an oblique image, then recovered the oblique image to a rectified image by doing the inverse affine transform, and left over by the SIFT method. We used the nearest neighbor distance ratio(NNDR), normalized cross correlation(NCC) measure constraints and consistency check to get the coarse matches, then used RANSAC method to calculate the fundamental matrix and the homography matrix. And we got the matches that they were interior points when calculating the homography matrix, then calculated the average value of the matches' principal direction differences. During the matching process, we got the initial matching features by the nearest neighbor(NN) matching strategy, then used the epipolar constrains, homography constrains, NCC measure constrains and consistency check of the initial matches' principal direction differences with the calculated average value of the interior matches' principal direction differences to eliminate false matches. Experiments conducted on three pairs of typical oblique images demonstrate that our method takes about the same time as SIFT to match a pair of oblique images with a plenty of corresponding points distributed evenly and an extremely low mismatching rate.

Automatic cloud detection for optical satellite remote sensing images is a significant step in the production system of satellite products. For the browse images cataloged by ZY-3 satellite, the tree discriminate structure is adopted to carry out cloud detection. The image was divided into sub-images and their features were extracted to perform classification between clouds and grounds. However, due to the high complexity of clouds and surfaces and the low resolution of browse images, the traditional classification algorithms based on image features are of great limitations. In view of the problem, a prior enhancement processing to original sub-images before classification was put forward in this paper to widen the texture difference between clouds and surfaces. Afterwards, with the secondary moment and first difference of the images, the feature vectors were extended in multi-scale space, and then the cloud proportion in the image was estimated through comprehensive analysis. The presented cloud detection algorithm has already been applied to the ZY-3 application system project, and the practical experiment results indicate that this algorithm is capable of promoting the accuracy of cloud detection significantly.