Parallel computing approach for efficient 3-D X-ray-simulated image reconstruction

Accurate 3-dimensional(3-D)reconstruction technology for nondestructive testing based on digital radiography(DR)is of great importance for alleviating the drawbacks of the existing computed tomography(CT)-based method.The commonly used Monte Carlo simulation method ensures well-performing imaging results for DR.However,for 3-D reconstruction,it is limited by its high time consumption.To solve this problem,this study proposes a parallel computing method to accelerate Monte Carlo simulation for projection images with a parallel interface and a specific DR application.The images are utilized for 3-D reconstruction of the test model.We verify the accuracy of parallel computing for DR and evaluate the performance of two parallel computing modes-multithreaded applications(G4-MT)and message-passing interfaces(G4-MPI)-by assessing parallel speedup and efficiency.This study explores the scalability of the hybrid G4-MPI and G4-MT modes.The results show that the two parallel computing modes can significantly reduce the Monte Carlo simulation time because the parallel speedup increment of Monte Carlo simulations can be considered linear growth,and the parallel efficiency is maintained at a high level.The hybrid mode has strong scalability,as the overall run time of the 180 simulations using 320 threads is 15.35 h with 10 billion particles emitted,and the parallel speedup can be up to 151.36.The 3-D reconstruction of the model is achieved based on the filtered back projection(FBP)algorithm using 180 projection images obtained with the hybrid G4-MPI and G4-MT.The quality of the reconstructed sliced images is satisfactory because the images can reflect the internal structure of the test model.This method is applied to a complex model,and the quality of the reconstructed images is evaluated.

Image processing based three-dimensional model reconstruction for cross-platform numerical simulation

Numerical simulation is the most powerful computational and analysis tool for a large variety of engineering and physical problems.For a complex problem relating to multi-field,multi-process and multi-scale,different computing tools have to be developed so as to solve particular fields at different scales and for different processes.Therefore,the integration of different types of software is inevitable.However,it is difficult to perform the transfer of the meshes and simulated results among software packages because of the lack of shared data formats or encrypted data formats.An image processing based method for three-dimensional model reconstruction for numerical simulation was proposed,which presents a solution to the integration problem by a series of slice or projection images obtained by the post-processing modules of the numerical simulation software.By means of mapping image pixels to meshes of either finite difference or finite element models,the geometry contour can be extracted to export the stereolithography model.The values of results,represented by color,can be deduced and assigned to the meshes.All the models with data can be directly or indirectly integrated into other software as a continued or new numerical simulation.The three-dimensional reconstruction method has been validated in numerical simulation of castings and case studies were provided in this study.

An Improved High Precision 3D Semantic Mapping of Indoor Scenes from RGB-D Images

This paper proposes an improved high-precision 3D semantic mapping method for indoor scenes using RGB-D images.The current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time performance.To address these issues,we first adopt the Elastic Fusion algorithm to select key frames from indoor environment image sequences captured by the Kinect sensor and construct the indoor environment space model.Then,an indoor RGB-D image semantic segmentation network is proposed,which uses multi-scale feature fusion to quickly and accurately obtain object labeling information at the pixel level of the spatial point cloud model.Finally,Bayesian updating is used to conduct incremental semantic label fusion on the established spatial point cloud model.We also employ dense conditional random fields(CRF)to optimize the 3D semantic map model,resulting in a high-precision spatial semantic map of indoor scenes.Experimental results show that the proposed semantic mapping system can process image sequences collected by RGB-D sensors in real-time and output accurate semantic segmentation results of indoor scene images and the current local spatial semantic map.Finally,it constructs a globally consistent high-precision indoor scenes 3D semantic map.

Adaptive Window Based 3-D Feature Selection for Multispectral Image Classification Using Firefly Algorithm

Feature extraction is the most critical step in classification of multispectral image.The classification accuracy is mainly influenced by the feature sets that are selected to classify the image.In the past,handcrafted feature sets are used which are not adaptive for different image domains.To overcome this,an evolu-tionary learning method is developed to automatically learn the spatial-spectral features for classification.A modified Firefly Algorithm(FA)which achieves maximum classification accuracy with reduced size of feature set is proposed to gain the interest of feature selection for this purpose.For extracting the most effi-cient features from the data set,we have used 3-D discrete wavelet transform which decompose the multispectral image in all three dimensions.For selecting spatial and spectral features we have studied three different approaches namely overlapping window(OW-3DFS),non-overlapping window(NW-3DFS)adaptive window cube(AW-3DFS)and Pixel based technique.Fivefold Multiclass Support Vector Machine(MSVM)is used for classification purpose.Experiments con-ducted on Madurai LISS IV multispectral image exploited that the adaptive win-dow approach is used to increase the classification accuracy.

A novel technique of three-dimensional reconstruction segmentation and analysis for sliced images of biological tissues

A novel technique of three-dimensional (3D) reconstruction, segmentation, display and analysis of series slices of images including microscopic wide field optical sectioning by deconvolution method, cryo-electron microscope slices by Fou-rier-Bessel synthesis and electron tomography (ET), and a series of computed tomography (CT) was developed to perform si-multaneous measurement on the structure and function of biomedical samples. The paper presents the 3D reconstruction seg-mentation display and analysis results of pollen spore, chaperonin, virus, head, cervical bone, tibia and carpus. At the same time, it also puts forward some potential applications of the new technique in the biomedical realm.

3D Shape Reconstruction of Lumbar Vertebra From Two X-ray Images and a CT Model

Structure reconstruction of 3 D anatomy from biplanar X-ray images is a challenging topic. Traditionally, the elastic-model-based method was used to reconstruct 3 D shapes by deforming the control points on the elastic mesh. However, the reconstructed shape is not smooth because the limited control points are only distributed on the edge of the elastic mesh.Alternatively, statistical-model-based methods, which include shape-model-based and intensity-model-based methods, are introduced due to their smooth reconstruction. However, both suffer from limitations. With the shape-model-based method, only the boundary profile is considered, leading to the loss of valid intensity information. For the intensity-based-method, the computation speed is slow because it needs to calculate the intensity distribution in each iteration. To address these issues, we propose a new reconstruction method using X-ray images and a specimen’s CT data. Specifically, the CT data provides both the shape mesh and the intensity model of the vertebra. Intensity model is used to generate the deformation field from X-ray images, while the shape model is used to generate the patient specific model by applying the calculated deformation field.Experiments on the public synthetic dataset and clinical dataset show that the average reconstruction errors are 1.1 mm and1.2 mm, separately. The average reconstruction time is 3 minutes.

Deep-Learning-Empowered 3D Reconstruction for Dehazed Images in IoT-Enhanced Smart Cities

With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.

Three-Dimensional Model Reconstruction of Nonwovens from Multi-Focus Images

The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.

A 3D Model Reconstruction Method Using Slice Images

Abstract：reconstruction method using slice im-ages is proposed. Wanting to extract the outermost contours from slice images, the method of the improved GVF-Snake model with optimized force field and ray method is employed. And then, the 3D model is reconstructed by contour connection using the im-proved shortest diagonal method and judgment function of contour fracture. The results show that the accuracy of reconstruction 3D model is improved.

Novel registration algorithm for 3-D images captured from multiple views of object surface

A novel algorithm of 3-D surface image registration is proposed. It makes use of the array information of 3-D points and takes vector/vertex-like features as the basis of the matching. That array information of 3-D points can be easily obtained when capturing original 3-D images. The iterative least-mean-squared （LMS） algorithm is applied to optimizing adaptively the transformation matrix parameters. These can effectively improve the registration performance and hurry up the matching process. Experimental results show that it can reach a good subjective impression on aligned 3-D images. Although the algorithm focuses primarily on the human head model, it can also be used for other objects with small modifications.

Monitoring slope deformation using a 3-D laser image scanning system: a case study

An ILRIS-36D 3-D laser image scanning system was used to monitor the Anjialing strip mine slope on Pingshuo in Shanxi province. The basic working principles, performance indexes, features and data collection and processing methods are illus-trated. The point cloud results are analyzed in detail. The rescale range analysis method was used to analyze the deformation char-acteristics of the slope. The results show that the trend of slope displacement is stable and that the degree of landslide danger is low. This work indicates that 3-D laser image scanning can supply multi-parameter, high precision real time data over long distances. These data can be used to study the distortion of the slope quickly and accurately.

MULTI-SPECTRAL AND HYPERSPECTRAL IMAGE FUSION USING 3-D WAVELET TRANSFORM

Image fusion is performed between one band of multi-spectral image and two bands of hyperspectral image to produce fused image with the same spatial resolution as source multi-spectral image and the same spectral resolution as source hyperspeetral image. According to the characteristics and 3-Dimensional （3-D） feature analysis of multi-spectral and hyperspectral image data volume, the new fusion approach using 3-D wavelet based method is proposed. This approach is composed of four major procedures： Spatial and spectral resampling, 3-D wavelet transform, wavelet coefficient integration and 3-D inverse wavelet transform. Especially, a novel method, Ratio Image Based Spectral Resampling （RIBSR）method, is proposed to accomplish data resampling in spectral domain by utilizing the property of ratio image. And a new fusion rule, Average and Substitution （A＆S） rule, is employed as the fusion rule to accomplish wavelet coefficient integration. Experimental results illustrate that the fusion approach using 3-D wavelet transform can utilize both spatial and spectral characteristics of source images more adequately and produce fused image with higher quality and fewer artifacts than fusion approach using 2-D wavelet transform. It is also revealed that RIBSR method is capable of interpolating the missing data more effectively and correctly, and A＆S rule can integrate coefficients of source images in 3-D wavelet domain to preserve both spatial and spectral features of source images more properly.

Using on-site liver 3-D reconstruction and volumetric calculations in split liver transplantation

BACKGROUND： Split liver transplantation increases the number of grafts available for transplantation. Pre-recovery assessment of liver graft volume is essential for selecting suitable recipients. The purpose of this study was to determine the ability and feasibility of constructing a 3-D model to aid in surgical planning and to predict graft weight prior to an in situ division of the donor liver. METHODS： Over 11 months, 3-D volumetric reconstruction of 4 deceased donors was performed using Pathfinder Scout liver volumetric software. Demographic, laboratory, operative, perioperative and survival data for these patients along with donor demographic data were collected prospectively and analyzed retrospectively. RESULTS： The average predicted weight of the grafts from the adult donors obtained from an in situ split procedure were 1130 g （930-1458 g） for the extended right lobe donors and 312 g （222-396 g） for left lateral segment grafts. Actual adult graft weight was 92% of the predicted weight for both the extended right grafts and the left lateral segment grafts. The predicted and actual graft weights for the pediatric donors were 176 g and 210 g for the left lateral segment grafts and 308 g and 280 g for the extended right lobe grafts,respectively. All grafts were transplanted except for the right lobe from the pediatric donors due to the small graft weight.CONCLUSIONS： On-site volumetric assessment of donors provides useful information for the planning of an in situ split and for selection of recipients. This information may expand the donor pool to recipients previously felt to be unsuitable due to donor and/or recipient weight.

Segmentation-aided phase unwrapping for 3D reconstruction with airborne array-InSAR images

Unmanned aerial vehicle(UAV)array InSAR is a new type of single-flight 3D SAR imaging system with the advantages of high coherence and resolution.However,due to the low altitude of the platform,the elevation ambiguity of the system is smaller than the maximal terrain elevation.Since the spatial phase unwrapping is conducted based on the assumption of phase continuity,the inappropriate ambiguity will cause significant unwrapping errors.In this work,a 3D phase unwrapping algorithm assisted by image segmentation is proposed to address this issue.The Markov random field(MRF)is utilized for image segmentation.The optimal spatial phase unwrapping network is achieved based on the segmentation results.The asymptotic 3D phase unwrapping is adopted to get the refined 3D reconstruction.Results based on the real airborne array-InSAR data show that the proposed method effectively improves the elevation ambiguity.

PC-BASED SURFACE RECONSTRUCTION OF MEDICAL CT IMAGES

It is an active research area to reconstruct 3-D object and display its visible surfacesfrom cross-sectional images. In this paper, the methods of reconstructing 3-D object from medicalCT images and displaying the visible surfaces are discussed. A polygon approximation methodthat forms polygon with the same number of segment points and a fast interpolation method forcross-sectional contours are presented at first. Then the voxel set of a human liver is reconstructed.And then the liver voxel set is displayed using depth and gradient shading methods. The softwareis written in C programming language at a microcomputer image processing system with a PC/ATcomputer as the host and a PC-VISION board as the image processing unit. The result of theprocessing is satisfying.

3-D RECONSTRUCTION OF SHAPE AND STRUCTURE FOR THE SPACE OBJECT FROM SERIAL CROSS-SECTIONS

A new method for reconstructing a 3-dimensional object from serial cross-sectionsis presented in this paper.The method is based on the principle of sampling and considersevery point in cross-sections as a sampling point and performs the interpolating of nonlinearfunction with these sampling points.Compared with other methods,this method has manyadvantages such as higher precision and fewer requested known sampling points.The result ofreconstruction with this method is an“entity”which involves the exterior shape and interiorconstruction information of the object simultaneously.

A 3-D RECONSTRUCTION METHOD BASED ON THE CONSTRAINT OF EPIPOLAR GEOMETRY

This paper combines the least-square method and iteration method to get the fundamental matrix and develops a new evaluation function based on the epipolar geometry. During the iteration, with the evaluation function as a measurment, the points which bring larger noise are deleted, and the points with smaller noise are retained, thus the precision of our method is increased. The experiment results indicate the new method is precise in calculation, stable in performance and resistant to noise.

MODELING OF 3-D IMAGES AND SPACE MARKOV CUBIC MESH MODELS

Three-dimensional(3-D)Markov cubic random mesh models are presented andproved in the form of two theorems in details.Its applications to the modeling and description of3-D images are described.The model presented here is a appropriate mathematical tool for thesegmentation,modeling,classification and other processing.Finally,an example is given.

3-D Reconstruction and Visualization of Laser-Scanned Trees by Weighted Locally Optimal Projection and Accurate Modeling Method

This paper presents a method to reconstruct 3-D models of trees from terrestrial laser scan(TLS)point clouds.This method uses the weighted locally optimal projection(WLOP)and the AdTree method to reconstruct detailed 3-D tree models.To improve its representation accuracy,the WLOP algorithm is introduced to consolidate the point cloud.Its reconstruction accuracy is tested using a dataset of ten trees,and the one-sided Hausdorff distances between the input point clouds and the resulting 3-D models are measured.The experimental results show that the optimal projection modeling method has an average one-sided Hausdorff distance(mean)lower by 30.74%and 6.43%compared with AdTree and AdQSM methods,respectively.Furthermore,it has an average one-sided Hausdorff distance(RMS)lower by 29.95%and 12.28%compared with AdTree and AdQSM methods.Results show that the 3-D model generated fits closely to the input point cloud data and ensures a high geometrical accuracy.

3-D Visualization of Medical Images with Arbitrary Sections

In this paper, with the general retrospect to the research on surface reconstruction and the marching cubes algorithm, we gave detailed description of an algorithm on the construction of object surfaces. The possible ambiguity problem in the original marching cubes algorithm was eliminated by its index mechanism. Some results on the MRI images were presented. Based on extracting and clipping contours from a set of medial slice images and setting the patch vertices values according to the gray images, this algorithm may be applied to form the arbitrary section images with three dimensional effects. It can also enhance the visual effect and interpretation of medical data.