In this work we address the problem of object recognition and localization from sparse range data. The method is based upon comparing the 7-D error surfaces of objects in various poses, which result from the registration error function between two convolved surfaces. The objects and their pose values are encoded by a small set of feature vectors extracted from the minima of the error surfaces. The problem of object recognition is thus reduced to comparing these feature vectors to find the corresponding error surfaces between the runtime data and a preprocessed database. Specifically, we present a new approach to the problems of pose determination, object recognition and object class recognition. The algorithm has been implemented and tested on both simulated and real data. The experimental results demonstrate the technique to be both effective and efficient, executing at 122 frames per second on standard hardware and with recognition rates exceeding 97% for a database of 60 objects. The performance of the proposed potential well space embedding (PWSE) approach on large size databases was also evaluated on the Princeton Shape Bench- mark containing 1,814 objects. In experiments of object class recognition with the Princeton Shape Benchmark, PWSE is able to provide better classification rates than the previous methods in terms of nearest neighbour classification. In addition, PWSE is shown to (i) operate with very sparse data, e.g., comprising only hundreds of points per image, and (ii) is robust to measurement error and outliers. / Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2010-01-24 23:07:30.108

The main goal of this research is the automatic construction of a computer model of 3D solid objects from a single range image. This research has many real world applications, including robotic environments and the inspection of industry parts. The most common methods for 3D-object extraction are based on stereo reconstruction and structured light analysis. The first approach encounters the difficulty of finding a correspondence of points between two images for the same scene, which involves intensive computations. The latter, on the other hand, has limitations and difficulties in object extraction, namely, inferring information about 3D objects from a 2D image. In addition, research in 3D-object extraction up to this point has lacked a thorough treatment of overlapped (occluded) objects. This research has resulted in a system that can extract multiple polyhedral objects from a single range image. The system consists of several parts: edge detection, segmentation, initial vertex extraction, occlusion detection, grouping faces into objects, and object representation. The problem is difficult especially when occluded objects are present. The system that has been developed separates occluded objects by combining evidence of several types. In the edge detection algorithm, noise reduction for range images is treated first by implementing a statistically robust technique based on the least median of squares. Three approaches to edge detection are presented. One that detects change in gradient orientation is a novel approach, which is implemented in the algorithm due to its superior performance, and the other two are extensions of work by other researchers. In general, the performance of these edge detection methods is considerably better than many others in the domain of range image segmentation. A hybrid approach (region-edge based) is introduced to achieve a robust solution for a single range image segmentation. The segmentation process depends on collaborating edge and region techniques where they give complementary information about the scene. Region boundaries are improved using iterative refinement. A novel approach for initial vertex extraction is presented to find the vertices of the polyhedral objects. The 3D vertex locations for the objects are obtained through an analysis of two-dimensional (2D) region shape and corner proximity, and the vertices of the polyhedra are extracted from the individual faces. There are two major approaches for dealing with occlusion. The first is an automatic identification of layers of 3D solid objects within a single range image. In this novel approach, a histogram of the distance values from a given range image is clustered into separate modes. Ideally, each mode of the histogram will be associated with one or more surfaces having approximately the same distance from the sensor. This approach works well when the objects are lying at different distances from the sensor, but when two or more objects are overlapped and lying at the same distance from the sensor, this approach has difficulty in detecting occlusion. The second approach for occlusion detection is considered the major contribution of this work. It detects occlusion of 3D solid objects from a single range image using multiple sources of evidence. This technique is based on detecting occlusion that may be present between each pair of adjacent faces associated with the estimated vertices of the 3D objects. This approach is not based on vertex and line labeling as other approaches are; it utilizes the topology and geometrical information of the 3D objects. After occlusion detection, faces are grouped into objects according to their adjacency relations and the absence or presence of occlusion between them. The initial vertex estimates are improved significantly through a global optimization procedure. Finally, models of the 3D objects are represented using the boundary representation technique that makes use of the region adjacency graph (RAG) paradigm. The experimental results of this research were obtained using real range images obtained from the CESAR lab at Oak Ridge National Laboratory. These images were obtained using a Perceptron laser range finder. These images contain single and multiple polyhedral objects, and they have a size of 512x512 pixels and a quantization of 12 bits per pixel. A quantitative evaluation of the construction algorithms is given. Part of this evaluation depends on the comparison between the results of the proposed segmentation technique and the ground truth database for these range images. The other part is to compare the results of the implemented algorithms with the results of other researchers, and it is found that the system developed here exhibits better performance in terms of the accuracy of the boundaries for the regions of the segmented images. A subjective comparison of the new edge detection methods with some traditional approaches is also provided for the set of range images. An evaluation of the new approach to occlusion detection is also presented. A recommendation for future work is to extend this system to involve images contain objects with curved surfaces. With some modifications to the multiple evidence-based approach of occlusion detection, the curved objects could be addressed. In addition, the model could be updated to include representation of the hidden surfaces for the 3D objects. This could be achieved by using multiple views for the same scene, or through assumptions such as symmetry to infer the shape of the hidden portion of the objects. / Ph. D.

This dissertation presents an automated detection algorithm that identifies severe external defects on the surfaces of barked hardwood logs and stems. The defects detected are at least 0.5 inch in height and at least 3 inches in diameter, which are severe, medium to large in size, and have external surface rises. Hundreds of real log defect samples were measured, photographed, and categorized to summarize the main defect features and to build a defect knowledge base. Three-dimensional laser-scanned range data capture the external log shapes and portray bark pattern, defective knobs, and depressions. The log data are extremely noisy, have missing data, and include severe outliers induced by loose bark that dangles from the log trunk. Because the circle model is nonlinear and presents both additive and non-additive errors, a new robust generalized M-estimator has been developed that is different from the ones proposed in the statistical literature for linear regression. Circle fitting is performed by standardizing the residuals via scale estimates calculated by means of projection statistics and incorporated in the Huber objective function to bound the influence of the outliers in the estimates. The projection statistics are based on 2-D radial-vector coordinates instead of the row vectors of the Jacobian matrix as proposed in the statistical literature dealing with linear regression. This approach proves effective in that it makes the GM-estimator to be influence bounded and thereby, robust against outliers. Severe defects are identified through the analysis of 3-D log data using decision rules obtained from analyzing the knowledge base. Contour curves are generated from radial distances, which are determined by robust 2-D circle fitting to the log-data cross sections. The algorithm detected 63 from a total of 68 severe defects. There were 10 non-defective regions falsely identified as defects. When these were calculated as areas, the algorithm locates 97.6% of the defect area, and falsely identifies 1.5% of the total clear area as defective. / Ph. D.

3D cameras delivering height data can be used for quality inspection of goods on a conveyor. It is then of interest to distinguish the important parts of the image from background and noise and further to divide these interesting parts into segments that have a strong correlation to objects on the conveyor belt. Segmentation can easily be done by thresholding in the simple case. However, in more complex situations, for example when objects touch or overlap, this does not work well. In this thesis, research and evaluation of a few different methods for segmentation of height image data are presented. The focus is to find an accurate method for segmentation of smooth irregularly shaped organic objects such as vegetables or shellfish. For evaluative purposes a database consisting of height images depicting a variety of such organic objects has been collected. We show in the thesis that a conventional gradient magnitude method is hard to beat in the general case. If, however, the objects to be segmented are heavily non-convex with a lot of crests and valleys within themselves one could be better off choosing a normalized least squares method. / 3D-kameror som levererar höjddata kan användas för kvalitetskontroll av varor på ett löpande band. Det är då av intresse att urskilja de viktiga delarna av bilden från bakgrund och brus samt även att dela upp dessa intressanta delar i segment med stark korrelans till objekten på bandet. Segmentering kan utföras genom tröskling i det enkla fallet. I mer komplexa situationer då objekt vidrör eller överlappar varandra blir det svårare. I detta examensarbete presenteras forskning och utvärdering av några olika metoder för segmentering av höjdbildsdata. Fokus ligger på att finna en noggrann metod för segmentering av mjuka släta oregelbundna objekt som grönsaker och skaldjur. I utvärderingssyfte har en databas bestående höjdbilder föreställande lite olika typer av sådana organiska objekt samlats in. Vi visar i uppstatsen att en konventionell gradientlängdsmetod är svår att slå i det generella fallet. Om objekten som ska segmenteras är kraftigt icke-konvexa å andra sidan, med en mängd krön och dalar inom varje objekt, kan man göra bättre i att välja en normaliserad minstakvadratfelsmetod.

A commercially available, tripod mounted, ground-based laser scanner was used to assess forest canopies and measure individual tree parameters. The instrument is comparable to scanning airborne light detection and ranging (lidar) technology but gathers data at higher resolution over a more limited scale. The raw data consist of a series of range measurements to visible surfaces taken at known angles relative to the scanner. Data were translated into three dimensional (3D) point clouds with points corresponding to surfaces visible from the scanner vantage point. A 20 m x 40 m permanent plot located in upland deciduous forest at Coweeta, NC was assessed with 41 and 45 scans gathered during periods of leaf-on and leaf-off, respectively. Data management and summary needs were addressed, focusing on the development of registration methods to align point clouds collected from multiple vantage points and minimize the volume of the plot canopy occluded from the scanner's view. Automated algorithms were developed to extract points representing tree bole surfaces, bole centers and ground surfaces. The extracted points served as the control surfaces necessary for registration. Occlusion was minimized by combining aligned point clouds captured from multiple vantage points with 0.1% and 0.34% of the volume scanned being occluded from view under leaf-off and leaf-on conditions, respectively. The point cloud data were summarized to estimate individual tree parameters including diameter at breast height (dbh), upper stem diameters, branch heights and XY positions of trees on the plot. Estimated tree positions were, on average, within 0.4 m of tree positions measured independently on the plot. Canopy height models, digital terrain models and 3D maps of the density of canopy surfaces were created using aligned point cloud data. Finally spatially explicit models of the horizontal and vertical distribution of plant area index (PAI) and leaf area index (LAI) were generated as examples of useful data summaries that cannot be practically collected using existing methods. / Ph. D.

L'intérêt toujours grandissant pour les données cartographiques fiables, notamment en milieu urbain, a motivé le développement de systèmes de cartographie mobiles terrestres. Ces systèmes sont conçus pour l'acquisition de données de très haute précision, telles que des nuages de points LiDAR 3D et des images optiques. La multitude de données, ainsi que leur diversité, rendent complexe le traitement des données issues de ce type de systèmes. Cette thèse se place dans le contexte du traitement de l'image appliqué au nuages de points LiDAR 3D issus de ce type de système.Premièrement, nous nous intéressons à des images issues de la projection de nuages de points LiDAR dans des grilles de pixels 2D régulières. Ces projections créent généralement des images éparses, dans lesquelles l'information de certains pixels n'est pas connue. Nous proposons alors différentes méthodes pour des applications telles que la génération d'orthoimages haute résolution, l'imagerie RGB-D et l'estimation de la visibilité des points d'un nuage.De plus, nous proposons d'exploiter la topologie d'acquisition des capteurs LiDAR pour produire des images de faible résolution: les range-images. Ces images offrent une représentation efficace et canonique du nuage de points, tout en étant directement accessibles à partir du nuage de points. Nous montrons comment ces images peuvent être utilisées pour simplifier, voire améliorer, des méthodes pour le recalage multi-modal, la segmentation, la désoccultation et la détection 3D. / The ever growing demand for reliable mapping data, especially in urban environments, has motivated the development of "close-range" Mobile Mapping Systems (MMS). These systems acquire high precision data, and in particular 3D LiDAR point clouds and optical images. The large amount of data, along with their diversity, make MMS data processing a very complex task. This thesis lies in the context of 2D image processing applied to 3D LiDAR point clouds acquired with MMS.First, we focus on the projection of the LiDAR point clouds onto 2D pixel grids to create images. Such projections are often sparse because some pixels do not carry any information. We use these projections for different applications such as high resolution orthoimage generation, RGB-D imaging and visibility estimation in point clouds.Moreover, we exploit the topology of LiDAR sensors in order to create low resolution images, named range-images. These images offer an efficient and canonical representation of the point cloud, while being directly accessible from the point cloud. We show how range-images can be used to simplify, and sometimes outperform, methods for multi-modal registration, segmentation, desocclusion and 3D detection.

One of the main objectives in digital imaging is to mimic the capabilities of the human eye, and perhaps, go beyond in certain aspects. However, the human visual system is so versatile, complex, and only partially understood that no up-to-date imaging technology has been able to accurately reproduce the capabilities of the it. The extraordinary capabilities of the human eye have become a crucial shortcoming in digital imaging, since digital photography, video recording, and computer vision applications have continued to demand more realistic and accurate imaging reproduction and analytic capabilities. Over decades, researchers have tried to solve the colour constancy problem, as well as extending the dynamic range of digital imaging devices by proposing a number of algorithms and instrumentation approaches. Nevertheless, no unique solution has been identified; this is partially due to the wide range of computer vision applications that require colour constancy and high dynamic range imaging, and the complexity of the human visual system to achieve effective colour constancy and dynamic range capabilities. The aim of the research presented in this thesis is to enhance the overall image quality within an image signal processor of digital cameras by achieving colour constancy and extending dynamic range capabilities. This is achieved by developing a set of advanced image-processing algorithms that are robust to a number of practical challenges and feasible to be implemented within an image signal processor used in consumer electronics imaging devises. The experiments conducted in this research show that the proposed algorithms supersede state-of-the-art methods in the fields of dynamic range and colour constancy. Moreover, this unique set of image processing algorithms show that if they are used within an image signal processor, they enable digital camera devices to mimic the human visual system s dynamic range and colour constancy capabilities; the ultimate goal of any state-of-the-art technique, or commercial imaging device.

<p>Digitizing objects and environments from real world has become an important part of creating realistic computer graphics. Through the use of structured lighting and laser time-of-flight measurements the capturing of geometric models is now a common process. The result are visualizations where viewers gain new possibilities for both visual and intellectual experiences. </p><p>This thesis presents the reconstruction of the Parthenon temple and its environment in Athens, Greece by using a 3D laser-scanning technique. </p><p>In order to reconstruct a realistic model using 3D scanning techniques there are various phases in which the acquired datasets have to be processed. The data has to be organized, registered and integrated in addition to pre and post processing. This thesis describes the development of a suitable and efficient data processing pipeline for the given data. </p><p>The approach differs from previous scanning projects considering digitizing this large scale object at very high resolution. In particular the issue managing and processing huge datasets is described. </p><p>Finally, the processing of the datasets in the different phases and the resulting 3D model of the Parthenon is presented and evaluated.</p>

The improvements in 3D scanning technologies have led the necessity for managing range image databases. Hence, the requirement of describing and indexing this type of data arises. Up to now, rather much work is achieved on capturing, transmission and visualization / however, there is still a gap in the 3D semantic analysis between the requirements of the applications and the obtained results. In this thesis we studied 3D semantic analysis of range data. Under this broad title we address segmentation of range scenes, correspondence matching of range images and the similarity retrieval of range models. Inputs are considered as single view depth images. First, possible research topics related to 3D semantic analysis are introduced. Planar structure detection in range scenes are analyzed and some modifications on available methods are proposed. Also, a novel algorithm to segment 3D point cloud (obtained via TOF camera) into objects by using the spatial information is presented. We proposed a novel local range image matching method that combines 3D surface properties with the 2D scale invariant feature transform. Next, our proposal for retrieving similar models where the query and the database both consist of only range models is presented. Finally, analysis of heat diffusion process on range data is presented. Challenges and some experimental results are presented.

Tone mapping operators aim to compress high dynamic range (HDR) images to low dynamic range ones so as to visualize HDR images on standard displays. Most existing works were demonstrated on specific examples without being thoroughly tested on well-established and subject-validated image quality assessment models. A recent tone mapped image quality index (TMQI) made the first attempt on objective quality assessment of tone mapped images. TMQI consists of two fundamental building blocks: structural fidelity and statistical naturalness. In this thesis, we propose an enhanced tone mapped image quality index (eTMQI) by 1) constructing an improved nonlinear mapping function to better account for the local contrast visibility of HDR images and 2) developing an image dependent statistical naturalness model to quantify the unnaturalness of tone mapped images based on a subjective study. Experiments show that the modified structural fidelity and statistical naturalness terms in eTMQI better correlate with subjective quality evaluations. Furthermore, we propose an iterative optimization algorithm for tone mapping. The advantages of this algorithm are twofold: 1) eTMQI and TMQI can be compared in a more straightforward way; 2) better quality tone mapped images can be automatically generated by using eTMQI as the optimization goal. Numerical and subjective experiments demonstrate that eTMQI is a superior objective quality assessment metric for tone mapped images and consistently outperforms TMQI.