Image super‐resolution via dynamic network

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.

RGB-guided hyperspectral image super-resolution with deep progressive learning

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal resolution.Recently,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image guidance.Previous approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted priors.Recently,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing data.In this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image guidance.Specif-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image guidance.Then,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing scenes.The proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial constraint.It has a good general-isation capability,especially for blind HS image super-resolution.Comprehensive experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

THE HIGH RESOLUTION SEISMIC TOMOGRAPHIC IMAGE IN QINGHAI—TIBET PLATEAU AND ITS DYNAMIC IMPLICATIONS

The Qinghai—Tibet plateau and its surrounding areas including Indian subcontinent, Xinjiang, Mongolia, is a largest lithosphere convergence place in the world, which characterized by continent\|continent collision with a thick crust and lithosphere. The high resolution seismic surface wave tomographic inversion has been conducted for studying the 3D velocity structure of crust and upper mantle in those areas. The seismic surface waveform data are from the archives of the CDSN, GSN and GEOSCOPE. About 2400 long period surface waveform recordings are available for both dispersion and waveform tomographic inversion. The block inversion by grid 1°×1°in Qinghai—Tibet plateau and 2°×2°in the surrounding areas were adapted. The resulting maps show the high resolution 3D shear wave velocity variation from earth’s surface to 400km depth.

Influences of Atmospheric Turbulence on Image Resolution of Airborne and Space-Borne Optical Remote Sensing System

A new way is proposed to evaluate the influence of atmospheric turbulence on image resolution of airborne and space-borne optical remote sensing system, which is called as arrival angle-method. Applying this method, some engineering examples are selected to analyze the turbulence influences on image resolution based on three different atmospheric turbulence models quantificationally, for the airborne remote sensing system, the resolution errors caused by the atmospheric turbulence are less than 1 cm, and for the space-borne remote sensing system, the errors are around 1 cm. The results are similar to that obtained by the previous Friedmethod. Compared with the Fried-method, the arrival angle-method is rather simple and can be easily used in engineering fields.

Automatic Road Extraction Using Particle Filters from High Resolution Images

Road extraction plays an important role in many applications such as car navigation, but the manual extraction of roads is a laborious, tedious task. To speed the extraction of roads, an approach based on particle filtering to extract automatically roads from high resolution imagery is proposed. Particle filtering provides a statistical framework for propagating sample-based approximations of posterior distributions and has almost no restriction on the ingredients of the model. We integrate the similarity of grey value and the edge point distribution of roads into particle filtering to deal with complex scenes. To handle road appearance changes the tracking algorithm is allowed to update the road model during temporally stable image observations. A fully automatic initialization strategy is used. Experimental results show that the proposed approach is a promising and fully automatic method for extracting roads from images, even in the presence of occlusions.

Road Vector Map Change Monitoring Based on High Resolution Remote Sensing Images

Some studies about road vector map change detection were done in this paper. Firstly, on the basis of old road vector data, the original high resolution remote sensing image was cut into segments. Then, gray analysis and edge extraction of those segments were done so that changes of roads could be detected. Finally, according to the vector data and gray information of roads which were not changed, road templates were extracted and saved automatically. This method was performed on the World View high resolution image of certain parts in the country. The detection result shows that detection correctness is 79.56% and completeness can reach 97.72%. Moreover, the extracted road templates are essentials for the template matching method of road extraction.

Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

Temporal sequence Object-based CNN(TS-OCNN) for crop classification from fine resolution remote sensing image time-series

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network(TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN(OCNN) model was adopted in the TS-OCNN to classify images at the object level(i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies(82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN(OCNN)(81.63% and85.88%), object-based image analysis(OBIA)(78.21% and 84.83%), and standard pixel-wise CNN(79.18%and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes(e.g., forest landscapes), with a wide application prospect.

Retrieval of High Resolution Satellite Images Using Texture Features

In this research, a content-based image retrieval （CBIR） system for high resolution satellite images has been developed by using texture features. The proposed approach uses the local binary pattern （LBP） texture feature and a block based scheme. The query and database images are divided into equally sized blocks, from which LBP histograms are extracted. The block histograms are then compared by using the Chi-square distance. Experimental results show that the LBP representation provides a powerful tool for high resolution satellite images （HRSI） retrieval.

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

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

Integrating cross-sensor high spatial resolution satellite images to detect subtle forest vegetation change in the Purple Mountains,a national scenic spot in Nanjing,China

Accurate information on the location and magnitude of vegetation change in scenic areas can guide the configuration of tourism facilities and the formulation of vegetation protection measures.High spatial resolution remote sensing images can be used to detect subtle vegetation changes.The major objective of this study was to map and quantify forest vegetation changes in a national scenic location,the Purple Mountains of Nanjing,China,using multi-temporal cross-sensor high spatial resolution satellite images to identify the main drivers of the vegetation changes and provide a reference for sustainable management.We used Quickbird images acquired in 2004,IKONOS images acquired in 2009,and WorldView2 images acquired in 2015.Four pixel-based direct change detection methods including the normalized difference vegetation index difference method,multi-index integrated change analysis(MIICA),principal component analysis,and spectral gradient difference analysis were compared in terms of their change detection performances.Subsequently,the best pixel-based detection method in conjunction with object-oriented image analysis was used to extract subtle forest vegetation changes.An accuracy assessment using the stratified random sampling points was conducted to evaluate the performance of the change detection results.The results showed that the MIICA method was the best pixel-based change detection method.And the object-oriented MIICA with an overall accuracy of 0.907 and a kappa coefficient of 0.846 was superior to the pixel-based MIICA.From 2004 to 2009,areas of vegetation gain mainly occurred around the periphery of the study area,while areas of vegetation loss were observed in the interior and along the boundary of the study area due to construction activities,which contributed to 79%of the total area of vegetation loss.During 2009–2015,the greening initiatives around the construction areas increased the forest vegetation coverage,accounting for 84%of the total area of vegetation gain.In spite of this,vegetation loss occurred in the interior of the Purple Mountains due to infrastructure development that caused conversion from vegetation to impervious areas.We recommend that:(1)a local multi-agency team inspect and assess law enforcement regarding natural resource utilization;and(2)strengthen environmental awareness education.

Spatial resolution and image processing for pinhole camera-based X-ray fluorescence imaging: a simulation study

Spatial resolution and image-processing methods for full-field X-ray fluorescence(FF-XRF)imaging using X-ray pinhole cameras were studied using Geant4simulations with different geometries and algorithms for image reconstruction.The main objectives were:(1)calculating the quantum efficiency curves of specific cameras,(2)studying the relationships between the spatial resolution and the pinhole diameter,magnification,and camera binning value,and(3)comparing image-processing methods for pinhole camera systems.Several results were obtained using a point and plane source as the X-ray fluorescence emitter and an array of 100×100 silicon pixel detectors as the X-ray camera.The quantum efficiency of a back-illuminated deep depletion(BI-DD)structure was above 30%for the XRF energies in the 0.8–9 keV range,with the maximum of 93.7%at 4 keV.The best spatial resolution of the pinhole camera was 24.7μm and 31.3 lp/mm when measured using the profile function of the point source,with the diameter of 20μm,magnification of 3.16,and camera bin of 1.A blind deconvolution algorithm with Gaussian filtering performed better than the Wiener filter and Richardson iterative methods on FF-XRF images,with the signal-to-noise ratio of 7.81 dB and improved signalto-noise ratio of 7.24 dB at the diameter of 120μm,magnification of 1.0,and camera bin of 1.

High-resolution Solar Image Reconstruction Based on Non-rigid Alignment

Suppressing the interference of atmospheric turbulence and obtaining observation data with a high spatial resolution are an issue to be solved urgently for ground observations. One way to solve this problem is to perform a statistical reconstruction of short-exposure speckle images. Combining the rapidity of Shift-Add and the accuracy of speckle masking, this paper proposes a novel reconstruction algorithm-NASIR(Non-rigid Alignment based Solar Image Reconstruction). NASIR reconstructs the phase of the object image at each frequency by building a computational model between geometric distortion and intensity distribution and reconstructs the modulus of the object image on the aligned speckle images by speckle interferometry. We analyzed the performance of NASIR by using the correlation coefficient, power spectrum, and coefficient of variation of intensity profile in processing data obtained by the NVST(1 m New Vacuum Solar Telescope). The reconstruction experiments and analysis results show that the quality of images reconstructed by NASIR is close to speckle masking when the seeing is good, while NASIR has excellent robustness when the seeing condition becomes worse. Furthermore, NASIR reconstructs the entire field of view in parallel in one go, without phase recursion and block-by-block reconstruction, so its computation time is less than half that of speckle masking. Therefore, we consider NASIR is a robust and highquality fast reconstruction method that can serve as an effective tool for data filtering and quick look.

Multi-resolution image segmentation based on Gaussian mixture model

Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Ganssian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.

Research on High Resolution Satellite Image Classification Algorithm based on Convolution Neural Network

Artifi cial neural network is a kind of artificial intelligence method to simulate the function of human brain, and deep learning technology can establish a depth network model with hierarchical structure on the basis of artificial neural network. Deep learning brings new development direction to artificial neural network. Convolution neural network is a new artificial neural network method, which combines artificial neural network and deep learning technology, and this new neural network is widely used in many fields of computer vision. Modern image recognition algorithm requires classifi cation system to adapt to different types of tasks, and deep network and convolution neural network is a hot research topic in neural networks. According to the characteristics of satellite digital image, we use the convolution neural network to classify the image, which combines texture features with spectral features. The experimental results show that the convolution neural network algorithm can effectively classify the image.

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

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

Super-resolution Restoration of Remote-sensing Images

A novel image restoration scheme, which is super-resolution image restoration algorithm Poisson-maximum-afterword-probability based on Markvo constraint (MPMAP) combined with evaluating image detail parameter D, has been proposed. The advantage of super-resolution algorithm MPMAP incorporated with parameter D lies in the fact that super-resolution algorithm MPMAP model is discrete, which is in accordance with remote-sensing imaging model, and the algorithm MPMAP is proved applicable to linear and non-linear imaging models with a unique solution when noise is not severe. According to simulation experiments for practical images, super-resolution algorithm MPMAP can retain image details better than most of traditional restoration methods; at the same time, the proposed parameter D can help to identify real point spread function (PSF) value of degradation process. Processing result of practical remote-sensing images by MPMAP combined with parameter D are given, it illustrates that MPMAP restoration scheme combined PSF estimation has a better restoration result than that of Photoshop processing, based on the same original images. It is proved that the proposed scheme is helpful to offset the lack of resolution of the original remote-sensing images and has its extensive application foreground.

Use of high-resolution X-ray computed tomography and 3D image analysis to quantify mineral dissemination and pore space in oxide copper ore particles

Mineral dissemination and pore space distribution in ore particles are important features that influence heap leaching performance. To quantify the mineral dissemination and pore space distribution of an ore particle, a cylindrical copper oxide ore sample (I center dot 4.6 mm x 5.6 mm) was scanned using high-resolution X-ray computed tomography (HRXCT), a nondestructive imaging technology, at a spatial resolution of 4.85 mu m. Combined with three-dimensional (3D) image analysis techniques, the main mineral phases and pore space were segmented and the volume fraction of each phase was calculated. In addition, the mass fraction of each mineral phase was estimated and the result was validated with that obtained using traditional techniques. Furthermore, the pore phase features, including the pore size distribution, pore surface area, pore fractal dimension, pore centerline, and the pore connectivity, were investigated quantitatively. The pore space analysis results indicate that the pore size distribution closely fits a log-normal distribution and that the pore space morphology is complicated, with a large surface area and low connectivity. This study demonstrates that the combination of HRXCT and 3D image analysis is an effective tool for acquiring 3D mineralogical and pore structural data.

Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation

Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.

Radial Basis Function Neural Network Based Super- Resolution Restoration for an Undersampled Image

To achieve restoration of high frequency information for an undersampled and degraded low-resolution image, a nonlinear and real-time processing method-the radial basis function (RBF) neural network based super-resolution method of restoration is proposed. The RBF network configuration and processing method is suitable for a high resolution restoration from an undersampled low-resolution image. The soft-competition learning scheme based on the k-means algorithm is used, and can achieve higher mapping approximation accuracy without increase in the network size. Experiments showed that the proposed algorithm can achieve a super-resolution restored image from an undersampled and degraded low-resolution image, and requires a shorter training time when compared with the multiplayer perception (MLP) network.