Spark-based in-memory DEM creation from 3D LiDAR point clouds

The significant performance improvement obtained by using Spark in-memory processing for iterative processes has led many researchers in various fields to implement their applications with Spark. In this study, we investigated the use of in-memory processing with Spark for creating a digital elevation model from massive light detection and ranging (LiDAR) point clouds, which can be considered an iterative process. We conducted our experiments on large high-density LiDAR data sets using two well-known interpolation methods: inverse distance weighting (IDW) and Kriging. Here, we designed our in-memory processing to parallelize those methods, and compared our results with the popularly used Hadoop MapReduce-based implementation. Our experiments ran on six servers under a medium-sized high-performance cloud computing environment. The results demonstrated that our Spark-based in-memory computing yielded better performance compared with Hadoop MapReduce, with an average 5.4 times speed increase in IDW, and 4.8 times improvement in Kriging. In addition, we evaluated the characteristics of our method in terms of central processing unit, memory usage, and network activities.     

A new method for shoreline extraction from airborne LiDAR point clouds

This work proposes a method for the extraction of shorelines from airborne LiDAR (light detection and ranging) point clouds. In the beginning, water bodies are removed based on the flatness clue. Then, boundaries of lands are extracted by using a new minimum-cost boundary model. Finally, false boundaries caused by man-made objects and vegetations are removed in the refinement step, and true boundaries are regarded as shorelines. The main contribution is that the cost of boundaries is calculated through an energy function and minimized by the proposed minimum-cost model globally. Evaluation on five experimental scenes shows that the proposed method achieves the completeness of 92.5% and correctness of 90.7%, which are promising results in the shoreline extraction.     

A new method for generating canopy height models from discrete-return LiDAR point clouds

Tree height underestimation and occurrence of visible data pits are two major problems in light detection and ranging (LiDAR)-derived digital surface models and canopy height models (CHMs) in forested areas. To address the two major problems, a new method is proposed for generating CHMs from discrete-return LiDAR point clouds using a selecting and sorting mechanism based on a circle centred at the target point, followed by spatial interpolation. Test results from simulated and real LiDAR point clouds show that the new method outperformed three other methods in terms of treetop approximation, crown surface representation and data pit removal.     

Segmentation of building roofs from airborne LiDAR point clouds using robust voxel-based region growing

The research herein presents a new approach for extracting building roofs using a robust voxel-based region growing segmentation method. The proposed approach exploits the fact that the roof of the building consists of planar surfaces and has distinctive geometric features than other kinds of objects. Based on this assumption, we present a method using voxel structure and region growing strategy with robust principal component analysis (RPCA). The voxels is clustered by a region growing process, utilizing the smoothness, continuity, and convexity as geometric cues. RPCA is introduced to estimate the attribute of voxels. Roofs are recognized from the segments by using the object-based spectral clustering. Our approach has been validated by different airborne laser scanning (ALS) point clouds. Qualitative and quantitative results reveal that our method outperforms some representative algorithms in segmentation using our testing datasets under a complex situation, with overall quality measure better than 0.7 and 0.6.     

Vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features

The object-based point cloud analysis (OBPCA) method has been used for vehicle detection from airborne light detection and ranging (LiDAR) point clouds with a relatively simple process and exhibits a degree of accuracy as high as that of a three-dimensional point cloud-based detection scheme. However, it only utilizes horizontal features of the segmented point clouds, and it uses thresholds established by heuristic observation and experience. In this article, we present a novel method for vehicle detection from airborne LiDAR point clouds based on a decision tree algorithm with horizontal and vertical features. It calculates the horizontal and vertical features for segments created by the filtering and segmentation processes, and it establishes a vehicle detection model by training a decision tree classifier with horizontal and vertical features of the segments. Our experiment shows that our proposed method outperforms the previous method in terms of recall and precision by 13.14% and 30.02%, respectively.     

The potential for using 3D visualization for data exploration,error correction and analysis of LiDAR point clouds

Instead of viewing Light Detection and Ranging (LiDAR) data via a standard two-dimensional screen, we developed prototype software that displays point cloud data, collected terrestrially and aerially from a rural setting, and allows data exploration in an immersive three-dimensional (3D) virtual reality (VR) environment. A head-mounted display (HMD) is used for stereoscopic viewing and a joystick for user navigation. Seventeen remote-sensing specialists took part in interactive trials and they expressed their opinion on the benefits and shortcomings of the prototype for a variety of potential processing activities, which we present in this article. The virtual environment was thought to be ideal for carrying out 3D geometric analysis and good for scrutinizing data errors. Participants felt that the usefulness of data integration depends on user needs and suggested that the interpolation of the cloud would assist interpretation for non-experts.     

Change detection of mountain birch using multi-temporal ALS point clouds

The use of multi-temporal laser scanner data is potentially an efficient method for monitoring of vegetation changes, for example, at the alpine treeline. Methods for relative calibration of multi-temporal airborne laser scanning (ALS) data sets and detection of experimental changes of tree cover in the forest–tundra ecotone was tested in northern Sweden (68° 20′ N, 19° 01′ E). Trees were either partly or totally removed on 6 m radius sample plots to simulate two classes of biomass change. Histogram matching was successfully used to calibrate the laser metrics from the two data sets and sample plots were then classified into three change classes. The proportion of vegetation returns from the canopy was the most important explanatory variable, which provided an overall accuracy of 88%. The classification accuracy was clearly dependent on the density of the forest.     

Liver tumors segmentation from CTA images using voxels classification and affinity constraint propagation

Objective   

We present a method and a validation study for the nearly automatic segmentation of liver tumors in CTA scans.     

Automated extraction of ground surface along urban roads from mobile laser scanning point clouds

Extracting ground surface from high-density point clouds collected by Mobile Laser Scanning (MLS) systems is of vital importance in urban planning and digital city mapping. This article proposes a novel approach for automated extraction of ground surface along urban roads from MLS point clouds. The approach, which was designed to handle both ordered and unordered MLS point clouds, consists of three key steps: constructing vertical profile from MLS point clouds along the vehicle trajectory; extracting candidate ground points using an adaptive alpha shapes algorithm; refining the candidate ground points with an elevation variance filter. To evaluate the performance of the proposed method, experiments were conducted using two types of urban street-scene point clouds. The results reveal that the ground points can be detected with an error rate of as low as 1.9%, proving that our proposed method offers a promising solution for automated extraction of ground surface from MLS point clouds.     

High-resolution computerized color transformation of real-time gray scale ultrasound images

Contemporary real-time ultrasound images are constructed of graduated shades of gray. The practical range of echo contrast than can be depicted is therefore limited. The use of color as well as intensity would potentially increase the amount of information available and possibly augment tissue texture contrast. Previous efforts to color encode ultrasound images have not been of adequate visual resolution, and have not produced simultaneous or real-time results. Described and illustrated here is a microcomputer-based system that successfully produces high-resolution simultaneous real-time pseudocolor transformation of real-time ultrasound images. The system accepts the composite video output in any ultrasound machine, and the specific color scheme may be chosen to suit the operator. It is proposed that such color enhancement improves visual clarity of fine fetal anatomy by highlighting tissue-tissue contrast and tissue-fluid interfaces.     

Geometric and morphological changes of the intervertebral disc under fatigue testing

OBJECTIVE: To understand the injury mechanism of the intervertebral disc at different loading rates and to explore the anatomic and histological changes of intervertebral discs. DESIGN: Fresh porcine lumbar spines were used for fatigue testing to study the morphological changes of the intervertebral disc. BACKGROUND: Intervertebral disc problem is one of the most common causes that lead to low back pain. Slow repetitive loading was considered to be the critical factor of spine and disc injuries. METHODS: Twenty-four lumbar functional units were subjected to cyclic loading at three different loading rates. The geometric measurements and magnetic resonance image observations were conducted for the comprehension of morphological changes. The detail observation was taken through a stereomicroscope. RESULTS: There was no significance in geometric changes between different loading rates. For magnetic resonance imagings, morphological changes included the changes of nucleus pulposus shape, bulge of anterior and posterior longitudinal ligaments, and dehydration in annulus fibrosus. CONCLUSION: The morphological changes of intervertebral disc were revealed in certain kinds of lesions. The results imply that fatigue failure and degeneration or instability are strongly linked. The correlation of magnetic resonance imaging and anatomic observation showed a high correspondence in the comparison of shape and position of the nucleus pulpasus. RELEVANCE: The changes of geometric measurements and relationship between anatomic observation and magnetic resonance imaging finding had been analyzed. It could help in understanding the mechanism of triggering cause in the early stage of disc degeneration.     

Evaluating the robustness of point clouds from small format aerial photography over a Pinus radiata plantation

Extensive research and operational trials over the past 20 years have led to the operational implementation of airborne laser scanning (ALS)-based forest inventory becoming increasingly common. More recently, digital aerial photography (AP), processed using Structure from Motion Multiview Stereopsis (SfM-MVS) photogrammetry, is emerging as an alternative to ALS. Aerial photography may provide some advantages compared with ALS, including lower deployment and data collection costs, easier access to a variety of platforms and sensors, and the opportunity for forest managers to capture and process the data in-house. This study presents an analysis of point-cloud data derived from airborne small format digital AP, and a comparison with ALS data for a Pinus radiata plantation located in north-east Tasmania. The AP was processed using commercially available photogrammetric software and three different processing strategies. The influence of processing strategy, terrain slope, canopy occlusion, canopy cover, photo-overlap and camera location are investigated in order to characterise the point clouds generated using these methods, and to assess the robustness of the photogrammetric solution to these variables. Our analysis provides strong evidence of the robustness of small format AP-based point clouds in this type of forest: characteristics of the dense point cloud are shown to be largely robust to different photogrammetric processing strategies. Observations regarding the influence of terrain slope, photo-overlap, canopy occlusions, canopy cover and camera location can be used to optimise flight planning and photo-acquisition.     

Refined segmentation of ship target in SAR images based on GVF snake with elliptical constraint

Ocean surveillance is an important application of synthetic aperture radar (SAR) image interpretation. In the ocean, the ship target usually attracts the attention of researchers, hence many interpretation works focus on it. The precise ship segmentation can facilitate further processing, such as feature extraction and target recognition. This paper proposes a refined segmentation method for ship target, in which the ratio of exponentially weighted averages (ROEWA) operator is used to produce the edge map and the elliptical constraint (EC) is incorporated into the energy function of the gradient vector flow (GVF) snake model to extract the ship target precisely. With this prior shape constraint, the snake contour can overcome unexpected distortions stemming from speckle noise and side lobe effect, etc. experimental results based on TerraSAR X-band and RADARSAT-2 C-band data illustrate the effective performance of the proposed method on refined segmentation for ship targets.     

高频超声影像肝脏包膜几何特征定量评价患者肝硬化程度

目的 探讨基于高频超声图像的肝脏包膜线几何特征定量评价乙型肝炎肝硬化程度的可行性。方法 收集48例轻、中、重度乙型肝炎肝硬化患者(轻度肝硬化组、中度肝硬化组、重度肝硬化组)及20名正常志愿者(正常对照组)肝包膜的二维高频声像图,结合人工监督与梯度优化方法获取包膜线及其形状控制点,提取包膜线的连续线段数、形状控制点的夹角均值及夹角方差3个参数,分别评估肝包膜轮廓线的连续性和平滑度。结果 随着肝硬化程度的逐渐加重,连续线段长度和达到成像切面总宽度的80%时所需要的线段数量逐渐增多,夹角均值和方差也逐渐增大;除中、重度肝硬化组间的线段数量差异无统计学意义外(P=0.149),其余组别各参数的比较差异均有统计学意义(P<0.05)。结论 肝包膜的几何特征分析可较准确地诊断不同程度肝硬化,可望为肝硬化的非侵入性评估提供一种量化处理方法。     

Registration of medical images using an interpolated closest point transform: method and validation

Image registration is an important procedure for medical diagnosis. Since the large inter-site retrospective validation study led by Fitzpatrick at Vanderbilt University, voxel-based methods and more specifically mutual information-based registration methods (see for instance [IEEE Trans. Med. Imag. 22 (8) (2003) 986] for a review on these methods) have been regarded as the method of choice for rigid-body intra-subject registration problems. In this study we propose a method that is based on the Iterative Closest Point algorithm and a pre-computed closest point map obtained with a slight modification of the fast marching method proposed by Sethian. Pre-computing the closest point map speeds up the process because at each iteration point correspondence can be established by table lookup. We also show that because the closest point map is defined on a regular grid it introduces a registration error and we propose an interpolation scheme that addresses this issue. The method has been tested both on synthetic and real images, and registration results have been assessed quantitatively using the data set provided by the Retrospective Registration Evaluation Project. For these volumes, MR and CT head surfaces were extracted automatically using a level-set technique. Results show that on these data sets this registration method leads to accuracy numbers that are comparable to those obtained with voxel-based methods.     

Integrating watersheds and critical point analysis for object detection in discrete 2D images

This paper presents an improved method for the detection of "significant" low-level objects in medical images. The method overcomes topological problems where multiple redundant saddle points are detected in digital images. Information derived from watershed regions is used to select and refine saddle points in the discrete domain and to construct the watersheds and watercourses (ridges and valleys). We also demonstrate an improved method of pruning the tessellation by which to define low level objects in zero order images. The algorithm was applied on a set of medical images with promising results. Evaluation was based on theoretical analysis and human observer experiments.     

FocusNetv2: Imbalanced large and small organ segmentation with adversarial shape constraint for head and neck CT images

Radiotherapy is a treatment where radiation is used to eliminate cancer cells. The delineation of organs-at-risk (OARs) is a vital step in radiotherapy treatment planning to avoid damage to healthy organs. For nasopharyngeal cancer, more than 20 OARs are needed to be precisely segmented in advance. The challenge of this task lies in complex anatomical structure, low-contrast organ contours, and the extremely imbalanced size between large and small organs. Common segmentation methods that treat them equally would generally lead to inaccurate small-organ labeling. We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation. In addition to our original FocusNet, we employ a novel adversarial shape constraint on small organs to ensure the consistency between estimated small-organ shapes and organ shape prior knowledge. Our proposed framework is extensively tested on both self-collected dataset of 1,164 CT scans and the MICCAI Head and Neck Auto Segmentation Challenge 2015 dataset, which shows superior performance compared with state-of-the-art head and neck OAR segmentation methods.     

Calculation of the confidence intervals for transformation parameters in the registration of medical images

Images from different individuals typically cannot be registered precisely because anatomical features within the images differ across the people imaged and because the current methods for image registration have inherent technological limitations that interfere with perfect registration. Quantifying the inevitable error in image registration is therefore of crucial importance in assessing the effects that image misregistration may have on subsequent analyses in an imaging study. We have developed a mathematical framework for quantifying errors in registration by computing the confidence intervals of the estimated parameters (3 translations, 3 rotations, and 1 global scale) for the similarity transformation.The presence of noise in images and the variability in anatomy across individuals ensures that estimated registration parameters are always random variables. We assume a functional relation among intensities across voxels in the images, and we use the theory of nonlinear, least-squares estimation to show that the parameters are multivariate Gaussian distributed. We then use the covariance matrix of this distribution to compute the confidence intervals of the transformation parameters. These confidence intervals provide a quantitative assessment of the registration error across the images. Because transformation parameters are nonlinearly related to the coordinates of landmark points in the brain, we subsequently show that the coordinates of those landmark points are also multivariate Gaussian distributed. Using these distributions, we then compute the confidence intervals of the coordinates for landmark points in the image. Each of these confidence intervals in turn provides a quantitative assessment of the registration error at a particular landmark point. Because our method is computationally intensive, however, its current implementation is limited to assessing the error of the parameters in the similarity transformation across images.We assessed the performance of our method in computing the error in estimated similarity parameters by applying that method to real world dataset. Our results showed that the size of the confidence intervals computed using our method decreased – i.e. our confidence in the registration of images from different individuals increased – for increasing amounts of blur in the images. Moreover, the size of the confidence intervals increased for increasing amounts of noise, misregistration, and differing anatomy. Thus, our method precisely quantified confidence in the registration of images that contain varying amounts of misregistration and varying anatomy across individuals.