Visual object classifcation and detection are major problems in contemporary com- puter vision. State-of-art algorithms allow thousands of visual objects to be learned and recognized, under a wide range of variations including lighting changes, occlusion and point of view etc. However, only a small fraction of the literature addresses the problem of variation in depictive styles (photographs, drawings, paintings etc.). This is a challenging gap but the ability to process images of all depictive styles and not just photographs has potential value across many applications. This thesis aims to narrow this gap. Our studies begin with primitive shapes. We provide experimental evidence that primitives shapes such as `triangle', `square', or `circle' can be found and used to fit regions in segmentations. These shapes corresponds to those used by artists as they draw. We then assume that an object class can be characterised by the qualitative shape of object parts and their structural arrangement. Hence, a novel hierarchical graph representation labeled with primitive shapes is proposed. The model is learnable and is able to classify over a broad range of depictive styles. However, as more depictive styles join, how to capture the wide variation in visual appearance exhibited by visual objects across them is still an open question. We believe that the use of a graph with multi-labels to represent visual words that exists in possibly discontinuous regions of a feature space can be helpful.

Wang, Guangyu. / Thesis submitted in: December 2003. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 70-75). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- BDCT Compression Artifacts --- p.1 / Chapter 1.2 --- Previous Artifact Removal Methods --- p.3 / Chapter 1.3 --- Our Method --- p.4 / Chapter 1.4 --- Structure of the Thesis --- p.4 / Chapter 2 --- Related Work --- p.6 / Chapter 2.1 --- Image Compression --- p.6 / Chapter 2.2 --- A Typical BDCT Compression: Baseline JPEG --- p.7 / Chapter 2.3 --- Existing Artifact Removal Methods --- p.10 / Chapter 2.3.1 --- Post-Filtering --- p.10 / Chapter 2.3.2 --- Projection onto Convex Sets --- p.12 / Chapter 2.3.3 --- Learning by Examples --- p.13 / Chapter 2.4 --- Other Related Work --- p.14 / Chapter 3 --- Contamination as Markov Random Field --- p.17 / Chapter 3.1 --- Markov Random Field --- p.17 / Chapter 3.2 --- Contamination as MRF --- p.18 / Chapter 4 --- Training Set Preparation --- p.22 / Chapter 4.1 --- Training Images Selection --- p.22 / Chapter 4.2 --- Bit Rate --- p.23 / Chapter 5 --- Artifact Vectors --- p.26 / Chapter 5.1 --- Formation of Artifact Vectors --- p.26 / Chapter 5.2 --- Luminance Remapping --- p.29 / Chapter 5.3 --- Dominant Implication --- p.29 / Chapter 6 --- Tree-Structured Vector Quantization --- p.32 / Chapter 6.1 --- Background --- p.32 / Chapter 6.1.1 --- Vector Quantization --- p.32 / Chapter 6.1.2 --- Tree-Structured Vector Quantization --- p.33 / Chapter 6.1.3 --- K-Means Clustering --- p.34 / Chapter 6.2 --- TSVQ in Artifact Removal --- p.35 / Chapter 7 --- Synthesis --- p.39 / Chapter 7.1 --- Color Processing --- p.39 / Chapter 7.2 --- Artifact Removal --- p.40 / Chapter 7.3 --- Selective Rejection of Synthesized Values --- p.42 / Chapter 8 --- Experimental Results --- p.48 / Chapter 8.1 --- Image Quality Assessments --- p.48 / Chapter 8.1.1 --- Peak Signal-Noise Ratio --- p.48 / Chapter 8.1.2 --- Mean Structural SIMilarity --- p.49 / Chapter 8.2 --- Performance --- p.50 / Chapter 8.3 --- How Size of Training Set Affects the Performance --- p.52 / Chapter 8.4 --- How Bit Rates Affect the Performance --- p.54 / Chapter 8.5 --- Comparisons --- p.56 / Chapter 9 --- Conclusion --- p.61 / Chapter A --- Color Transformation --- p.63 / Chapter B --- Image Quality --- p.64 / Chapter B.1 --- Image Quality vs. Quantization Table --- p.64 / Chapter B.2 --- Image Quality vs. Bit Rate --- p.66 / Chapter C --- Arti User's Manual --- p.68 / Bibliography --- p.70

by Yuan, Ding. / Thesis submitted in: December 2003. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 69-71). / Abstracts in English and Chinese. / ABSTRACT --- p.i / 摘要 --- p.iii / ACKNOWLEDGEMENTS --- p.v / TABLE OF CONTENTS --- p.vi / LIST OF FIGURES --- p.viii / LIST OF TABLES --- p.xii / Chapter 1 --- INTRODUCTION --- p.1 / Chapter 2 --- PREVIOUS WORK --- p.5 / Chapter 2.1 --- Traditional Stereo Vision --- p.5 / Chapter 2.1.1 --- Epipolar Constraint --- p.7 / Chapter 2.1.2 --- Some Constraints Based on Properties of Scene Objects --- p.9 / Chapter 2.1.3 --- Two Classes of Algorithms for Correspondence Establishment --- p.10 / Chapter 2.2 --- Correspondenceless Stereo Vision Algorithm for Single Planar Surface Recovery under Parallel-axis Stereo Geometry --- p.13 / Chapter 3 --- CORRESPONDENCE-FREE STEREO VISION UNDER GENERAL STEREO SETUP --- p.19 / Chapter 3.1 --- Correspondence-free Stereo Vision Algorithm for Single Planar Surface Recovery under General Stereo Geometry --- p.20 / Chapter 3.1.1 --- Algorithm in Its Basic Form --- p.21 / Chapter 3.1.2 --- Algorithm Combined with Epipolar Constraint --- p.25 / Chapter 3.1.3 --- Algorithm Combined with SVD And Robust Estimation --- p.36 / Chapter 3.2 --- Correspondence-free Stereo Vision Algorithm for Multiple Planar Surface Recovery --- p.45 / Chapter 3.2.1 --- Plane Hypothesis --- p.46 / Chapter 3.2.2 --- Plane Confirmation And 3D Reconstruction --- p.48 / Chapter 3.2.3 --- Experimental Results --- p.50 / Chapter 3.3 --- Experimental Results on Correspondence-free Vs. Correspondence Based Methods --- p.60 / Chapter 4 --- CONCLUSION AND FUTURE WORK --- p.65 / APPENDIX --- p.67 / BIBLIOGRAPHY --- p.69

by Chor-Tung Yau. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1996. / Includes bibliographical references (leaves 106-110). / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Objectives --- p.1 / Chapter 1.2 --- Factors of Depth Perception in Human Visual System --- p.2 / Chapter 1.2.1 --- Oculomotor Cues --- p.2 / Chapter 1.2.2 --- Pictorial Cues --- p.3 / Chapter 1.2.3 --- Movement-Produced Cues --- p.4 / Chapter 1.2.4 --- Binocular Disparity --- p.5 / Chapter 1.3 --- What Cues to Use in Computer Vision? --- p.6 / Chapter 1.4 --- The Process of Stereo Vision --- p.8 / Chapter 1.4.1 --- Depth and Disparity --- p.8 / Chapter 1.4.2 --- The Stereo Correspondence Problem --- p.10 / Chapter 1.4.3 --- Parallel and Nonparallel Axis Stereo Geometry --- p.11 / Chapter 1.4.4 --- Feature-based and Area-based Stereo Matching --- p.12 / Chapter 1.4.5 --- Constraints --- p.13 / Chapter 1.5 --- Organization of this thesis --- p.16 / Chapter 2 --- Related Work --- p.18 / Chapter 2.1 --- Marr and Poggio's Computational Theory --- p.18 / Chapter 2.2 --- Cooperative Methods --- p.19 / Chapter 2.3 --- Dynamic Programming --- p.21 / Chapter 2.4 --- Feature-based Methods --- p.24 / Chapter 2.5 --- Area-based Methods --- p.26 / Chapter 3 --- Overview of the Method --- p.30 / Chapter 3.1 --- Considerations --- p.31 / Chapter 3.2 --- Brief Description of the Method --- p.33 / Chapter 4 --- Preprocessing of Images --- p.35 / Chapter 4.1 --- Edge Detection --- p.35 / Chapter 4.1.1 --- The Laplacian of Gaussian (∇2G) operator --- p.37 / Chapter 4.1.2 --- The Canny edge detector --- p.40 / Chapter 4.2 --- Extraction of Horizontal Line Segments for Matching --- p.42 / Chapter 5 --- The Matching Process --- p.45 / Chapter 5.1 --- Reducing the Search Space --- p.45 / Chapter 5.2 --- Similarity Measure --- p.47 / Chapter 5.3 --- Treating Inclined Surfaces --- p.49 / Chapter 5.4 --- Ambiguity Caused By Occlusion --- p.51 / Chapter 5.5 --- Matching Segments of Different Length --- p.53 / Chapter 5.5.1 --- Cases Without Partial Occlusion --- p.53 / Chapter 5.5.2 --- Cases With Partial Occlusion --- p.55 / Chapter 5.5.3 --- Matching Scheme To Handle All the Cases --- p.56 / Chapter 5.5.4 --- Matching Scheme for Segments of same length --- p.57 / Chapter 5.6 --- Assigning Disparity Values --- p.58 / Chapter 5.7 --- Another Case of Partial Occlusion Not Handled --- p.60 / Chapter 5.8 --- Matching in Two passes --- p.61 / Chapter 5.8.1 --- Problems encountered in the First pass --- p.61 / Chapter 5.8.2 --- Second pass of matching --- p.63 / Chapter 5.9 --- Refinement of Disparity Map --- p.64 / Chapter 6 --- Coarse-to-fine Matching --- p.67 / Chapter 6.1 --- The Wavelet Representation --- p.67 / Chapter 6.2 --- Coarse-to-fine Matching --- p.71 / Chapter 7 --- Experimental Results and Analysis --- p.74 / Chapter 7.1 --- Experimental Results --- p.74 / Chapter 7.1.1 --- Image Pair 1 - The Pentagon Images --- p.74 / Chapter 7.1.2 --- Image Pair 2 - Random dot stereograms --- p.79 / Chapter 7.1.3 --- Image Pair 3 ´ؤ The Rubik Block Images --- p.81 / Chapter 7.1.4 --- Image Pair 4 - The Stack of Books Images --- p.85 / Chapter 7.1.5 --- Image Pair 5 - The Staple Box Images --- p.87 / Chapter 7.1.6 --- Image Pair 6 - Circuit Board Image --- p.91 / Chapter 8 --- Conclusion --- p.94 / Chapter A --- The Wavelet Transform --- p.96 / Chapter A.l --- Fourier Transform and Wavelet Transform --- p.96 / Chapter A.2 --- Continuous wavelet Transform --- p.97 / Chapter A.3 --- Discrete Time Wavelet Transform --- p.99 / Chapter B --- Acknowledgements to Testing Images --- p.100 / Chapter B.l --- The Circuit Board Image --- p.100 / Chapter B.2 --- The Stack of Books Image --- p.101 / Chapter B.3 --- The Rubik Block Images --- p.104 / Bibliography --- p.106

Bird species are recognised as important biodiversity indicators: they are responsive to changes in sensitive ecosystems, whilst populations-level changes in behaviour are both visible and quantifiable. They are monitored by ecologists to determine factors causing population fluctuation and to help conserve and manage threatened and endangered species. Every five years, the health of bird population found in the UK are reviewed based on data collected from various surveys. Currently, techniques used in surveying species include manual counting, Bioacoustics and computer vision. The latter is still under development by researchers. Hitherto, no computer vision technique has fully been deployed in the field for counting species as these techniques use high-quality and detailed images of stationary birds, which make them impractical for deployment in the field, as most species in the field are in-flight and sometimes distant from the cameras field of view. Techniques such as manual and bioacoustics are the most frequently used but they can also become impractical, particularly when counting densely populated migratory species. Manual techniques are labour intensive whilst bioacoustics may be unusable when deployed for species that emit little or no sound. There is the need for automated systems for identifying species using computer vision and machine learning techniques, specifically for surveying densely populated migratory species. However, currently, most systems are not fully automated and use only appearance-based features for identification of species. Moreover, in the field, appearance-based features like colour may fade at a distance whilst motion-based features will remain discernible. Thus to achieve full automation, existing systems will have to combine both appearance and motion features. The aim of this thesis is to contribute to this problem by developing computer vision techniques which combine appearance and motion features to robustly classify species, whilst in flight. It is believed that once this is achieved, with additional development, it will be able to support the surveying of species and their behaviour studies. The first focus of this research was to refine appearance features previously used in other related works for use in automatic classification of species in flight. The bird appearances were described using a group of seven proposed appearance features, which have not previously been used for bird species classification. The proposed features improved the classification rate when compared to state-of-the-art systems that were based on appearance features alone (colour features). The second step was to extract motion features from videos of birds in flight, which were used for automatic classification. The motion of birds was described using a group of six features, which have not previously been used for bird species classification. The proposed motion features, when combined with the appearance features improved classification rates compared with only appearance or motion features. The classification rates were further improved using feature selection techniques. There was an increase of between 2-6% of correct classification rates across all classifiers, which may be attributable directly to the use of motion features. The only motion features selected are the wing beat frequency and vicinity features irrespective of the method used. This shows how important these groups of features were to species classification. Further analysis also revealed specific improvements in identifying species with similar visual appearance and that using the optimal motion features improve classification accuracy significantly. We attempt a further improvement in classification accuracy, using majority voting. This was used to aggregate classification results across a set of video sub-sequences, which improved classification rates considerably. The results using the combined features with majority voting outperform those without majority voting by 3% and 6% on the seven species and thirteen classes dataset respectively. Finally, a video dataset against which future work can be benchmarked has been collated. This data set enables the evaluation of work against a set of 13 species, enabling effective evaluation of automated species identification to date and a benchmark for further work in this area of research. The key contribution of this research is that a species classification system was developed, which combines motion and appearance features and evaluated it against existing appearance-only-based methods. This is not only the first work to combine features in this way but also the first to apply a voting technique to improve classification performance across an entire video sequence.

Wang, Huan. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (leaves 113-119). / Abstracts in English and Chinese. / Contents / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Learning Frameworks --- p.1 / Chapter 1.2 --- Sample Representation --- p.3 / Chapter 2 --- Background Study --- p.5 / Chapter 2.1 --- Tensor Algebra --- p.5 / Chapter 2.1.1 --- Tensor Unfolding (Flattening) --- p.6 / Chapter 2.1.2 --- Tensor Product --- p.6 / Chapter 2.2 --- Manifold Embedding and Dimensionality Reduction --- p.8 / Chapter 2.2.1 --- Principal Component Analysis (PCA) --- p.9 / Chapter 2.2.2 --- Metric Multidimensional Scaling (MDS) --- p.10 / Chapter 2.2.3 --- Isomap --- p.10 / Chapter 2.2.4 --- Locally Linear Embedding (LLE) --- p.11 / Chapter 2.2.5 --- Discriminant Analysis --- p.11 / Chapter 2.2.6 --- Laplacian Eigenmap --- p.14 / Chapter 2.2.7 --- Graph Embedding: A General Framework --- p.15 / Chapter 2.2.8 --- Maximum Variance Unfolding --- p.16 / Chapter 3 --- The Trace Ratio Optimization --- p.17 / Chapter 3.1 --- Introduction --- p.17 / Chapter 3.2 --- Dimensionality Reduction Formulations: Trace Ratio vs. Ratio Trace --- p.19 / Chapter 3.3 --- Efficient Solution of Trace Ratio Problem --- p.22 / Chapter 3.4 --- Proof of Convergency to Global Optimum --- p.23 / Chapter 3.4.1 --- Proof of the monotonic increase of λn --- p.23 / Chapter 3.4.2 --- Proof of Vn convergence and global optimum for λ --- p.24 / Chapter 3.5 --- Extension and Discussion --- p.27 / Chapter 3.5.1 --- Extension to General Constraints --- p.27 / Chapter 3.5.2 --- Discussion --- p.28 / Chapter 3.6 --- Experiments --- p.29 / Chapter 3.6.1 --- Dataset Preparation --- p.30 / Chapter 3.6.2 --- Convergence Speed --- p.31 / Chapter 3.6.3 --- Visualization of Projection Matrix --- p.31 / Chapter 3.6.4 --- Classification by Linear Trace Ratio Algorithms with Orthogonal Constraints --- p.33 / Chapter 3.6.5 --- Classification by Kernel Trace Ratio algorithms with General Constraints --- p.36 / Chapter 3.7 --- Conclusion --- p.36 / Chapter 4 --- A Convergent Solution to Tensor Subspace Learning --- p.40 / Chapter 4.1 --- Introduction --- p.40 / Chapter 4.2 --- Subspace Learning with Tensor Data --- p.43 / Chapter 4.2.1 --- Graph Embedding with Tensor Representation --- p.43 / Chapter 4.2.2 --- Computational Issues --- p.46 / Chapter 4.3 --- Solution Procedure and Convergency Proof --- p.46 / Chapter 4.3.1 --- Analysis of Monotonous Increase Property --- p.47 / Chapter 4.3.2 --- Proof of Convergency --- p.48 / Chapter 4.4 --- Experiments --- p.50 / Chapter 4.4.1 --- Data Sets --- p.50 / Chapter 4.4.2 --- Monotonicity of Objective Function Value --- p.51 / Chapter 4.4.3 --- Convergency of the Projection Matrices . . --- p.52 / Chapter 4.4.4 --- Face Recognition --- p.52 / Chapter 4.5 --- Conclusions --- p.54 / Chapter 5 --- Maximum Unfolded Embedding --- p.57 / Chapter 5.1 --- Introduction --- p.57 / Chapter 5.2 --- Maximum Unfolded Embedding --- p.59 / Chapter 5.3 --- Optimize Trace Ratio --- p.60 / Chapter 5.4 --- Another Justification: Maximum Variance Em- bedding --- p.60 / Chapter 5.5 --- Linear Extension: Maximum Unfolded Projection --- p.61 / Chapter 5.6 --- Experiments --- p.62 / Chapter 5.6.1 --- Data set --- p.62 / Chapter 5.6.2 --- Evaluation Metric --- p.63 / Chapter 5.6.3 --- Performance Comparison --- p.64 / Chapter 5.6.4 --- Generalization Capability --- p.65 / Chapter 5.7 --- Conclusion --- p.67 / Chapter 6 --- Regression on MultiClass Data --- p.68 / Chapter 6.1 --- Introduction --- p.68 / Chapter 6.2 --- Background --- p.70 / Chapter 6.2.1 --- Intuitive Motivations --- p.70 / Chapter 6.2.2 --- Related Work --- p.72 / Chapter 6.3 --- Problem Formulation --- p.73 / Chapter 6.3.1 --- Notations --- p.73 / Chapter 6.3.2 --- Regularization along Data Manifold --- p.74 / Chapter 6.3.3 --- Cross Manifold Label Propagation --- p.75 / Chapter 6.3.4 --- Inter-Manifold Regularization --- p.78 / Chapter 6.4 --- Regression on Reproducing Kernel Hilbert Space (RKHS) --- p.79 / Chapter 6.5 --- Experiments --- p.82 / Chapter 6.5.1 --- Synthetic Data: Nonlinear Two Moons . . --- p.82 / Chapter 6.5.2 --- Synthetic Data: Three-class Cyclones --- p.83 / Chapter 6.5.3 --- Human Age Estimation --- p.84 / Chapter 6.6 --- Conclusions --- p.86 / Chapter 7 --- Correspondence Propagation --- p.88 / Chapter 7.1 --- Introduction --- p.88 / Chapter 7.2 --- Problem Formulation and Solution --- p.92 / Chapter 7.2.1 --- Graph Construction --- p.92 / Chapter 7.2.2 --- Regularization on categorical Product Graph --- p.93 / Chapter 7.2.3 --- Consistency in Feature Domain and Soft Constraints --- p.96 / Chapter 7.2.4 --- Inhomogeneous Pair Labeling . --- p.97 / Chapter 7.2.5 --- Reliable Correspondence Propagation --- p.98 / Chapter 7.2.6 --- Rearrangement and Discretizing --- p.100 / Chapter 7.3 --- Algorithmic Analysis --- p.100 / Chapter 7.3.1 --- Selection of Reliable Correspondences . . . --- p.100 / Chapter 7.3.2 --- Computational Complexity --- p.102 / Chapter 7.4 --- Applications and Experiments --- p.102 / Chapter 7.4.1 --- Matching Demonstration on Object Recognition Databases --- p.103 / Chapter 7.4.2 --- Automatic Feature Matching on Oxford Image Transformation Database . --- p.104 / Chapter 7.4.3 --- Influence of Reliable Correspondence Number --- p.106 / Chapter 7.5 --- Conclusion and Future Works --- p.106 / Chapter 8 --- Conclusion and Future Work --- p.110 / Bibliography --- p.113

Abstract not available

This thesis presents a new and powerful approach to the development of a general purpose machine vision system. The approach is inspired from anatomical considerations of the primate's vision system. The geometrical arrangement of cones on a primate's retina can be described in terms of a hexagonal grid. The importance of the hexagonal grid is that it possesses special computational features that are pertinent to the vision process. The fundamental thrust of this thesis emanates from the observation that this hexagonal grid can be described in terms of the mathematical object known as a Euclidean ring. The Euclidean ring is employed to generate an algebra of linear transformations which are appropriate for the processing of multidimensional vision data. A parallel autonomous segmentation algorithm for multidimensional vision data is described. The algebra and segmentation algorithm are implemented on a network of transputers. The implementation is discussed in the context of the outline of a general purpose machine vision system's design.

This thesis is concerned with fundamental algorithms for estimating parameters of geometric models that are particularly relevant to computer vision. A general framework is considered which accommodates several important problems involving estimation in a maximum likelihood setting. By considering a special form of a commonly used cost function, a new, iterative, estimation method is evolved. This method is subsequently expanded to enable incorporation of a so-called ancillary constraint. An important feature of these methods is that they can serve as a basis for conducting theoretical comparison of various estimation approaches. Two specific applications are considered: conic fitting, and estimation of the fundamental matrix (a matrix arising in stereo vision). In the case of conic fitting, unconstrained methods are first treated. The problem of producing ellipse-specific estimates is subsequently tackled. For the problem of estimating the fundamental matrix, the new constrained method is applied to generate an estimate which satisfies the necessary rank-two constraint. Other constrained and unconstrained methods are compared within this context. For both of these example problems, the unconstrained and constrained methods are shown to perform with high accuracy and efficiency. The value of incorporating covariance information characterising the uncertainty of measured image point locations within the estimation process is also explored. Covariance matrices associated with data points are modelled, then an empirical study is made of the conditions under which covariance information enables generation of improved parameter estimates. Under the assumption that covariance information is, in itself, subject to estimation error, tests are undertaken to determine the effect of imprecise information upon the quality of parameter estimates. Finally, these results are carried over to experiments to assess the value of covariance information in estimating the fundamental matrix from real images. The use of such information is shown to be of potential benefit when the measurement process of image features is considered. / Thesis (Ph.D.)--School of Computer Science, 2004.

Robots are envisioned to take on jobs that are dirty, dangerous and dull, the three D's of robotics. With this mission, robotic technology today is ubiquitous on the factory floor. However, the same level of success has not occurred when it comes to robots that operate in everyday living spaces, such as homes and offices. A big part of this is attributed to domestic environments being complex and unstructured as opposed to factory settings which can be set up and precisely known in advance. In this thesis we challenge the point of view which regards man-made environments as unstructured and that robots should operate without prior assumptions about the world. Instead, we argue that robots should make use of the inherent structure of everyday living spaces across various scales and applications, in the form of contextual and prior information, and that doing so can improve the performance of robotic tasks. To investigate this premise, we start by attempting to solve a hard and realistic problem, active visual search. The particular scenario considered is that of a mobile robot tasked with finding an object on an entire unexplored building floor. We show that a search strategy which exploits the structure of indoor environments offers significant improvements on state of the art and is comparable to humans in terms of search performance. Based on the work on active visual search, we present two specific ways of making use of the structure of space. First, we propose to use the local 3D geometry as a strong indicator of objects in indoor scenes. By learning a 3D context model for various object categories, we demonstrate a method that can reliably predict the location of objects. Second, we turn our attention to predicting what lies in the unexplored part of the environment at the scale of rooms and building floors. By analyzing a large dataset, we propose that indoor environments can be thought of as being composed out of frequently occurring functional subparts. Utilizing these, we present a method that can make informed predictions about the unknown part of a given indoor environment. The ideas presented in this thesis explore various sides of the same idea: modeling and exploiting the structure inherent in indoor environments for the sake of improving robot's performance on various applications. We believe that in addition to contributing some answers, the work presented in this thesis will generate additional, fruitful questions. / <p>QC 20121105</p> / CogX