Advantages of exploiting projection structure for segmenting dense 3D point clouds

Timely and comprehensive scene segmentation is often a critical step for many high level mobile robotic tasks. This paper examines a projected area based neighbourhood lookup approach with the motivation towards faster unsupervised segmentation of dense 3D point clouds. The proposed algorithm exploits the projection geometry of a depth camera to find nearest neighbours which is time independent of the input data size. Points near depth discontinuations are also detected to reinforce object boundaries in the clustering process. The search method presented is evaluated using both indoor and outdoor dense depth images and demonstrates significant improvements in speed and precision compared to the commonly used Fast library for approximate nearest neighbour (FLANN) [Muja and Lowe, 2009].

Separable spatiotemporal priors for convex reconstruction of time-varying 3D point clouds

Reconstructing 3D motion data is highly under-constrained due to several common sources of data loss during measurement, such as projection, occlusion, or miscorrespondence. We present a statistical model of 3D motion data, based on the Kronecker structure of the spatiotemporal covariance of natural motion, as a prior on 3D motion. This prior is expressed as a matrix normal distribution, composed of separable and compact row and column covariances. We relate the marginals of the distribution to the shape, trajectory, and shape-trajectory models of prior art. When the marginal shape distribution is not available from training data, we show how placing a hierarchical prior over shapes results in a convex MAP solution in terms of the trace-norm. The matrix normal distribution, fit to a single sequence, outperforms state-of-the-art methods at reconstructing 3D motion data in the presence of significant data loss, while providing covariance estimates of the imputed points.

3D anthropometry : from the ergonomist's perspective

Since the availability of 3D full body scanners and the associated software systems for operations with large point clouds, 3D anthropometry has been marketed as a breakthrough and milestone in ergonomic design. The assumptions made by the representatives of the 3D paradigm need to be critically reviewed though. 3D anthropometry has advantages as well as shortfalls, which need to be carefully considered. While it is apparent that the measurement of a full body point cloud allows for easier storage of raw data and improves quality control, the difficulties in calculation of standardized measurements from the point cloud are widely underestimated. Early studies that made use of 3D point clouds to derive anthropometric dimensions have shown unacceptable deviations from the standardized results measured manually. While 3D human point clouds provide a valuable tool to replicate specific single persons for further virtual studies, or personalize garment, their use in ergonomic design must be critically assessed. Ergonomic, volumetric problems are defined by their 2-dimensional boundary or one dimensional sections. A 1D/2D approach is therefore sufficient to solve an ergonomic design problem. As a consequence, all modern 3D human manikins are defined by the underlying anthropometric girths (2D) and lengths/widths (1D), which can be measured efficiently using manual techniques. Traditionally, Ergonomists have taken a statistical approach to design for generalized percentiles of the population rather than for a single user. The underlying method is based on the distribution function of meaningful single and two-dimensional anthropometric variables. Compared to these variables, the distribution of human volume has no ergonomic relevance. On the other hand, if volume is to be seen as a two-dimensional integral or distribution function of length and girth, the calculation of combined percentiles – a common ergonomic requirement - is undefined. Consequently, we suggest to critically review the cost and use of 3D anthropometry. We also recommend making proper use of widely available single and 2-dimensional anthropometric data in ergonomic design.

LiDAR Augmented Optimal Path Planning for Unmanned Aerial Vehicle during Remote Sensing at Low Altitude and Network Sensor Data Acquisition

This technical report describes a Light Detection and Ranging (LiDAR) augmented optimal path planning at low level flight methodology for remote sensing and sampling Unmanned Aerial Vehicles (UAV). The UAV is used to perform remote air sampling and data acquisition from a network of sensors on the ground. The data that contains information on the terrain is in the form of a 3D point clouds maps is processed by the algorithms to find an optimal path. The results show that the method and algorithm are able to use the LiDAR data to avoid obstacles when planning a path from a start to a target point. The report compares the performance of the method as the resolution of the LIDAR map is increased and when a Digital Elevation Model (DEM) is included. From a practical point of view, the optimal path plan is loaded and works seemingly with the UAV ground station and also shows the UAV ground station software augmented with more accurate LIDAR data.

Measuring Visual Consistency in 3D Rendering Systems

One of the major challenges facing a present day game development company is the removal of bugs from such complex virtual environments. This work presents an approach for measuring the correctness of synthetic scenes generated by a rendering system of a 3D application, such as a computer game. Our approach builds a database of labelled point clouds representing the spatiotemporal colour distribution for the objects present in a sequence of bug-free frames. This is done by converting the position that the pixels take over time into the 3D equivalent points with associated colours. Once the space of labelled points is built, each new image produced from the same game by any rendering system can be analysed by measuring its visual inconsistency in terms of distance from the database. Objects within the scene can be relocated (manually or by the application engine); yet the algorithm is able to perform the image analysis in terms of the 3D structure and colour distribution of samples on the surface of the object. We applied our framework to the publicly available game RacingGame developed for Microsoft(R) Xna(R). Preliminary results show how this approach can be used to detect a variety of visual artifacts generated by the rendering system in a professional quality game engine.

An integrated approach for precise road reconstruction from aerial imagery and LiDAR data

Accurate and detailed road models play an important role in a number of geospatial applications, such as infrastructure planning, traffic monitoring, and driver assistance systems. In this thesis, an integrated approach for the automatic extraction of precise road features from high resolution aerial images and LiDAR point clouds is presented. A framework of road information modeling has been proposed, for rural and urban scenarios respectively, and an integrated system has been developed to deal with road feature extraction using image and LiDAR analysis. For road extraction in rural regions, a hierarchical image analysis is first performed to maximize the exploitation of road characteristics in different resolutions. The rough locations and directions of roads are provided by the road centerlines detected in low resolution images, both of which can be further employed to facilitate the road information generation in high resolution images. The histogram thresholding method is then chosen to classify road details in high resolution images, where color space transformation is used for data preparation. After the road surface detection, anisotropic Gaussian and Gabor filters are employed to enhance road pavement markings while constraining other ground objects, such as vegetation and houses. Afterwards, pavement markings are obtained from the filtered image using the Otsu's clustering method. The final road model is generated by superimposing the lane markings on the road surfaces, where the digital terrain model (DTM) produced by LiDAR data can also be combined to obtain the 3D road model. As the extraction of roads in urban areas is greatly affected by buildings, shadows, vehicles, and parking lots, we combine high resolution aerial images and dense LiDAR data to fully exploit the precise spectral and horizontal spatial resolution of aerial images and the accurate vertical information provided by airborne LiDAR. Objectoriented image analysis methods are employed to process the feature classiffcation and road detection in aerial images. In this process, we first utilize an adaptive mean shift (MS) segmentation algorithm to segment the original images into meaningful object-oriented clusters. Then the support vector machine (SVM) algorithm is further applied on the MS segmented image to extract road objects. Road surface detected in LiDAR intensity images is taken as a mask to remove the effects of shadows and trees. In addition, normalized DSM (nDSM) obtained from LiDAR is employed to filter out other above-ground objects, such as buildings and vehicles. The proposed road extraction approaches are tested using rural and urban datasets respectively. The rural road extraction method is performed using pan-sharpened aerial images of the Bruce Highway, Gympie, Queensland. The road extraction algorithm for urban regions is tested using the datasets of Bundaberg, which combine aerial imagery and LiDAR data. Quantitative evaluation of the extracted road information for both datasets has been carried out. The experiments and the evaluation results using Gympie datasets show that more than 96% of the road surfaces and over 90% of the lane markings are accurately reconstructed, and the false alarm rates for road surfaces and lane markings are below 3% and 2% respectively. For the urban test sites of Bundaberg, more than 93% of the road surface is correctly reconstructed, and the mis-detection rate is below 10%.

Lost in translation (and rotation) : rapid extrinsic calibration for 2D and 3D LIDARs

This paper describes a novel method for determining the extrinsic calibration parameters between 2D and 3D LIDAR sensors with respect to a vehicle base frame. To recover the calibration parameters we attempt to optimize the quality of a 3D point cloud produced by the vehicle as it traverses an unknown, unmodified environment. The point cloud quality metric is derived from Rényi Quadratic Entropy and quantifies the compactness of the point distribution using only a single tuning parameter. We also present a fast approximate method to reduce the computational requirements of the entropy evaluation, allowing unsupervised calibration in vast environments with millions of points. The algorithm is analyzed using real world data gathered in many locations, showing robust calibration performance and substantial speed improvements from the approximations.

Vision-only autonomous navigation using topometric maps

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph --- as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

Efficiently capturing large, complex cultural heritage sites with a handheld mobile 3D laser mapping system

Accurate three-dimensional representations of cultural heritage sites are highly valuable for scientific study, conservation, and educational purposes. In addition to their use for archival purposes, 3D models enable efficient and precise measurement of relevant natural and architectural features. Many cultural heritage sites are large and complex, consisting of multiple structures spatially distributed over tens of thousands of square metres. The process of effectively digitising such geometrically complex locations requires measurements to be acquired from a variety of viewpoints. While several technologies exist for capturing the 3D structure of objects and environments, none are ideally suited to complex, large-scale sites, mainly due to their limited coverage or acquisition efficiency. We explore the use of a recently developed handheld mobile mapping system called Zebedee in cultural heritage applications. The Zebedee system is capable of efficiently mapping an environment in three dimensions by continually acquiring data as an operator holding the device traverses through the site. The system was deployed at the former Peel Island Lazaret, a culturally significant site in Queensland, Australia, consisting of dozens of buildings of various sizes spread across an area of approximately 400 × 250 m. With the Zebedee system, the site was scanned in half a day, and a detailed 3D point cloud model (with over 520 million points) was generated from the 3.6 hours of acquired data in 2.6 hours. We present results demonstrating that Zebedee was able to accurately capture both site context and building detail comparable in accuracy to manual measurement techniques, and at a greatly increased level of efficiency and scope. The scan allowed us to record derelict buildings that previously could not be measured because of the scale and complexity of the site. The resulting 3D model captures both interior and exterior features of buildings, including structure, materials, and the contents of rooms.

BDNF gene effects on brain circuitry replicated in 455 twins

Brain-derived neurotrophic factor (BDNF) plays a key role in learning and memory, but its effects on the fiber architecture of the living brain are unknown. We genotyped 455 healthy adult twins and their non-twin siblings (188 males/267 females; age: 23.7 ± 2.1. years, mean ± SD) and scanned them with high angular resolution diffusion tensor imaging (DTI), to assess how the BDNF Val66Met polymorphism affects white matter microstructure. By applying genetic association analysis to every 3D point in the brain images, we found that the Val-BDNF genetic variant was associated with lower white matter integrity in the splenium of the corpus callosum, left optic radiation, inferior fronto-occipital fasciculus, and superior corona radiata. Normal BDNF variation influenced the association between subjects' performance intellectual ability (as measured by Object Assembly subtest) and fiber integrity (as measured by fractional anisotropy; FA) in the callosal splenium, and pons. BDNF gene may affect the intellectual performance by modulating the white matter development. This combination of genetic association analysis and large-scale diffusion imaging directly relates a specific gene to the fiber microstructure of the living brain and to human intelligence.

Multiview point cloud kernels for semisupervised learning [Lecture Notes]

In semisupervised learning (SSL), a predictive model is learn from a collection of labeled data and a typically much larger collection of unlabeled data. These paper presented a framework called multi-view point cloud regularization (MVPCR), which unifies and generalizes several semisupervised kernel methods that are based on data-dependent regularization in reproducing kernel Hilbert spaces (RKHSs). Special cases of MVPCR include coregularized least squares (CoRLS), manifold regularization (MR), and graph-based SSL. An accompanying theorem shows how to reduce any MVPCR problem to standard supervised learning with a new multi-view kernel.

3D reconstruction of long bones utilising magnetic resonance imaging (MRI)

The design of pre-contoured fracture fixation implants (plates and nails) that correctly fit the anatomy of a patient utilises 3D models of long bones with accurate geometric representation. 3D data is usually available from computed tomography (CT) scans of human cadavers that generally represent the above 60 year old age group. Thus, despite the fact that half of the seriously injured population comes from the 30 year age group and below, virtually no data exists from these younger age groups to inform the design of implants that optimally fit patients from these groups. Hence, relevant bone data from these age groups is required. The current gold standard for acquiring such data–CT–involves ionising radiation and cannot be used to scan healthy human volunteers. Magnetic resonance imaging (MRI) has been shown to be a potential alternative in the previous studies conducted using small bones (tarsal bones) and parts of the long bones. However, in order to use MRI effectively for 3D reconstruction of human long bones, further validations using long bones and appropriate reference standards are required. Accurate reconstruction of 3D models from CT or MRI data sets requires an accurate image segmentation method. Currently available sophisticated segmentation methods involve complex programming and mathematics that researchers are not trained to perform. Therefore, an accurate but relatively simple segmentation method is required for segmentation of CT and MRI data. Furthermore, some of the limitations of 1.5T MRI such as very long scanning times and poor contrast in articular regions can potentially be reduced by using higher field 3T MRI imaging. However, a quantification of the signal to noise ratio (SNR) gain at the bone - soft tissue interface should be performed; this is not reported in the literature. As MRI scanning of long bones has very long scanning times, the acquired images are more prone to motion artefacts due to random movements of the subject‟s limbs. One of the artefacts observed is the step artefact that is believed to occur from the random movements of the volunteer during a scan. This needs to be corrected before the models can be used for implant design. As the first aim, this study investigated two segmentation methods: intensity thresholding and Canny edge detection as accurate but simple segmentation methods for segmentation of MRI and CT data. The second aim was to investigate the usability of MRI as a radiation free imaging alternative to CT for reconstruction of 3D models of long bones. The third aim was to use 3T MRI to improve the poor contrast in articular regions and long scanning times of current MRI. The fourth and final aim was to minimise the step artefact using 3D modelling techniques. The segmentation methods were investigated using CT scans of five ovine femora. The single level thresholding was performed using a visually selected threshold level to segment the complete femur. For multilevel thresholding, multiple threshold levels calculated from the threshold selection method were used for the proximal, diaphyseal and distal regions of the femur. Canny edge detection was used by delineating the outer and inner contour of 2D images and then combining them to generate the 3D model. Models generated from these methods were compared to the reference standard generated using the mechanical contact scans of the denuded bone. The second aim was achieved using CT and MRI scans of five ovine femora and segmenting them using the multilevel threshold method. A surface geometric comparison was conducted between CT based, MRI based and reference models. To quantitatively compare the 1.5T images to the 3T MRI images, the right lower limbs of five healthy volunteers were scanned using scanners from the same manufacturer. The images obtained using the identical protocols were compared by means of SNR and contrast to noise ratio (CNR) of muscle, bone marrow and bone. In order to correct the step artefact in the final 3D models, the step was simulated in five ovine femora scanned with a 3T MRI scanner. The step was corrected using the iterative closest point (ICP) algorithm based aligning method. The present study demonstrated that the multi-threshold approach in combination with the threshold selection method can generate 3D models from long bones with an average deviation of 0.18 mm. The same was 0.24 mm of the single threshold method. There was a significant statistical difference between the accuracy of models generated by the two methods. In comparison, the Canny edge detection method generated average deviation of 0.20 mm. MRI based models exhibited 0.23 mm average deviation in comparison to the 0.18 mm average deviation of CT based models. The differences were not statistically significant. 3T MRI improved the contrast in the bone–muscle interfaces of most anatomical regions of femora and tibiae, potentially improving the inaccuracies conferred by poor contrast of the articular regions. Using the robust ICP algorithm to align the 3D surfaces, the step artefact that occurred by the volunteer moving the leg was corrected, generating errors of 0.32 ± 0.02 mm when compared with the reference standard. The study concludes that magnetic resonance imaging, together with simple multilevel thresholding segmentation, is able to produce 3D models of long bones with accurate geometric representations. The method is, therefore, a potential alternative to the current gold standard CT imaging.

A reproducible method for automated extraction of brain volumes from 3D human head MR images

An automated method for extracting brain volumes from three commonly acquired three-dimensional (3D) MR images (proton density, T1 weighted, and T2-weighted) of the human head is described. The procedure is divided into four levels: preprocessing, segmentation, scalp removal, and postprocessing. A user-provided reference point is the sole operator-dependent input required. The method's parameters were first optimized and then fixed and applied to 30 repeat data sets from 15 normal older adult subjects to investigate its reproducibility. Percent differences between total brain volumes (TBVs) for the subjects' repeated data sets ranged from .5% to 2.2%. We conclude that the method is both robust and reproducible and has the potential for wide application.

Suitability of diodes for point dose measurements in IMRT/VMAT beams

This study investigated a potential source of inaccuracy for diode measurements in modulated beams; the effect of diode housing asymmetry on measurement results. The possible effects of diode housing asymmetry on the measurement of steep dose gradients were evaluated by measuring 5x5 cm2 beam profiles, with three cylindrical diodes and two commonly used ionization chambers, with each dosimeter positioned in a 3D scanning water tank with its stem perpendicular to the beam axis (horizontal) and parallel to the direction of scanning. The resulting profiles were used to compare the penumbrae measured with the diode stem pointing into (equivalent to a “stem-first” setup) and out of the field (equivalent to a “stem-last” setup) in order to evaluate the effects of dosimeter alignment and thereby identify the effects of dosimeter asymmetry. The stem-first and stem-last orientations resulted in differences of up to 0.2 mm in the measured 20-80% penumbra widths and differences of up to 0.4 mm in the off axis position of the 90% isodose. These differences, which are smaller than previously reported for older model dosimeters, were apparent in the profile results for both diodes and small volume ionization chambers. As an extension to this study, the practical use of all five dosimeters was exemplified by measuring point doses in IMRT test beams. These measurements showed good agreement (within 2%) between the diodes and the small volume ionization chamber, with all of these dosimeters being able to identify a region 3% under-dosage which was not identified by a larger volume (6 mm diameter) ionization chamber. The results of this work should help to remove some of the barriers to the use of diodes for modulated radiotherapy dosimetry in the future.