Xiong, Wei. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (leaves 56-61). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 2 --- Background Study --- p.6 / Chapter 2.1 --- Stereo matching --- p.6 / Chapter 2.2 --- Digital image matting --- p.8 / Chapter 2.3 --- Expectation Maximization --- p.9 / Chapter 3 --- Model Definition --- p.12 / Chapter 4 --- Initialization --- p.20 / Chapter 4.1 --- Initializing disparity --- p.20 / Chapter 4.2 --- Initializing alpha matte --- p.24 / Chapter 5 --- Optimization --- p.26 / Chapter 5.1 --- Expectation Step --- p.27 / Chapter 5.1.1 --- "Computing E((Pp(df = d1̐ưجθ(n),U))" --- p.28 / Chapter 5.1.2 --- "Computing E((Pp(db = d2̐ưجθ(n),U))" --- p.29 / Chapter 5.2 --- Maximization Step --- p.31 / Chapter 5.2.1 --- "Optimize α, given {F, B} fixed" --- p.34 / Chapter 5.2.2 --- "Optimize {F, B}, given α fixed" --- p.37 / Chapter 5.3 --- Computing Final Disparities --- p.40 / Chapter 6 --- Experiment Results --- p.42 / Chapter 7 --- Conclusion --- p.54 / Bibliography --- p.56

Stereo vision from short-baseline image pairs is one of the most active research fields in computer vision. The estimation of dense disparity maps from stereo image pairs is still a challenging task and there is further space for improving accuracy, minimizing the computational cost and handling more efficiently outliers, low-textured areas, repeated textures, disparity discontinuities and light variations. This PhD thesis presents two novel methodologies relating to stereo vision from short-baseline image pairs: I. The first methodology combines three different cost metrics, defined using colour, the CENSUS transform and SIFT (Scale Invariant Feature Transform) coefficients. The selected cost metrics are aggregated based on an adaptive weights approach, in order to calculate their corresponding cost volumes. The resulting cost volumes are merged into a combined one, following a novel two-phase strategy, which is further refined by exploiting semi-global optimization. A mean-shift segmentation-driven approach is exploited to deal with outliers in the disparity maps. Additionally, low-textured areas are handled using disparity histogram analysis, which allows for reliable disparity plane fitting on these areas. II. The second methodology relies on content-based guided image filtering and weighted semi-global optimization. Initially, the approach uses a pixel-based cost term that combines gradient, Gabor-Feature and colour information. The pixel-based matching costs are filtered by applying guided image filtering, which relies on support windows of two different sizes. In this way, two filtered costs are estimated for each pixel. Among the two filtered costs, the one that will be finally assigned to each pixel, depends on the local image content around this pixel. The filtered cost volume is further refined by exploiting weighted semi-global optimization, which improves the disparity accuracy. The handling of the occluded areas is enhanced by incorporating a straightforward and time efficient scheme. The evaluation results show that both methodologies are very accurate, since they handle efficiently low-textured/occluded areas and disparity discontinuities. Additionally, the second approach has very low computational complexity. Except for the aforementioned two methodologies that use as input short-baseline image pairs, this PhD thesis presents a novel methodology for generating 3D point clouds of good accuracy from wide-baseline stereo pairs.

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.

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.

Abstract not available

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

We present a framework for the design and implementation of visually-guided, interactive, mobile robots. Essential to the framework's robust performance is our behavior-based robot control architecture enhanced with a state of the art decision-theoretic planner that takes into account the temporal characteristics of robot actions and allows us to achieve principled coordination of complex subtasks implemented as robot behaviors/skills. We study two different models of the decision theoretic layer: Multiply Sectioned Markov Decision Processes (MSMDPs) under the assumption that the world state is fully observable by the agent, and Partially Observable Markov Decision Processes (POMDPs) that remove the latter assumption and allow us to model the uncertainty in sensor measurements. The MSMDP model utilizes a divide-and-conquer approach for solving problems with millions of states using concurrent actions. For solving large POMDPs, we present heuristics that improve the computational efficiency of the point-based value iteration algorithm while tackling the problem of multi-step actions using Dynamic Bayesian Networks. In addition, we describe a state-of-the-art simultaneous localization and mapping algorithm for robots equipped with stereo vision. We first present the Monte-Carlo algorithm sigmaMCL for robot localization in 3D using natural landmarks identified by their appearance in images. Secondly, we extend sigmaMCL and develop the sigmaSLAM algorithm for solving the simultaneous localization and mapping problem for visually-guided, mobile robots. We demonstrate our real-time algorithm mapping large, indoor environments in the presence of large changes in illumination, image blurring and dynamic objects. Finally, we demonstrate empirically the applicability of our framework for developing interactive, mobile robots capable of completing complex tasks with the aid of a human companion. We present an award winning robot waiter for serving hors d'oeuvres at receptions and a robot for delivering verbal messages among inhabitants of an office-like environment.

Thesis (Ph.D.)--Brown University, 2008. / Vita. Advisor: David H. Laidlaw. Includes bibliographical references (leaves 150-157).

Thesis (Ph. D.)--Carnegie Mellon University, 2003. / "September 2003." Includes bibliographical references.

It is now possible for physical objects to have a dynamic digital presence via active identification codes that can be scanned via ubiquitous devices such as smart phones or tablets. En-co.de is a web service for the generation, storing, retrieval, and augmentation of metadata associated with physical objects. The service is built upon the concept that metadata associated with an object can be retrieved through a Quick Response (QR) coded URL. En-co.de serves to link a physical entity to a digital archive of information and provides services such as geolocation and SMS text alerts when an object's identifier, or tag, is scanned. I provide an analysis of QR code qualitative characteristics, the architecture for the en-co.de web service, a scalability study of the en-co.de architecture, and the results of the completed service in production in this report. In addition, the analysis is complemented with an evaluation of comparable identification schemes and web services. / text