Wang, Tianming. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 59-62). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts also in Chinese.

published_or_final_version / abstract / Computer Science / Master / Master of Philosophy

Zhao, Ming. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (p. 111-117) and index. / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation --- p.1 / Chapter 1.2 --- Objective of the study --- p.2 / Chapter 1.3 --- Challenges and our approach --- p.4 / Chapter 1.4 --- Original contributions --- p.6 / Chapter 1.5 --- Organization of this dissertation --- p.6 / Chapter 2 --- Related Work --- p.9 / Chapter 2.1 --- Critical configuration for motion estimation and projective reconstruction --- p.9 / Chapter 2.1.1 --- Point feature --- p.9 / Chapter 2.1.2 --- Line feature --- p.12 / Chapter 2.2 --- Camera motion estimation --- p.14 / Chapter 2.2.1 --- Line tracking --- p.15 / Chapter 2.2.2 --- Determining camera motion --- p.19 / Chapter 3 --- Preliminaries on Three-View Geometry and Trifocal Tensor --- p.23 / Chapter 3.1 --- Projective spaces P3 and transformations --- p.23 / Chapter 3.2 --- The trifocal tensor --- p.24 / Chapter 3.3 --- Computation of the trifocal tensor-Normalized linear algorithm --- p.31 / Chapter 4 --- Linear Line Structures --- p.33 / Chapter 4.1 --- Models of line space --- p.33 / Chapter 4.2 --- Line structures --- p.35 / Chapter 4.2.1 --- Linear line space --- p.37 / Chapter 4.2.2 --- Ruled surface --- p.37 / Chapter 4.2.3 --- Line congruence --- p.38 / Chapter 4.2.4 --- Line complex --- p.38 / Chapter 5 --- Critical Configurations of Three Views Revealed by Line Correspondences --- p.41 / Chapter 5.1 --- Two-view degeneracy --- p.41 / Chapter 5.2 --- Three-view degeneracy --- p.42 / Chapter 5.2.1 --- Introduction --- p.42 / Chapter 5.2.2 --- Linear line space --- p.44 / Chapter 5.2.3 --- Linear ruled surface --- p.54 / Chapter 5.2.4 --- Linear line congruence --- p.55 / Chapter 5.2.5 --- Linear line complex --- p.57 / Chapter 5.3 --- Retrieving tensor in critical configurations --- p.60 / Chapter 5.4 --- Rank classification of non-linear line structures --- p.61 / Chapter 6 --- Camera Motion Estimation Framework --- p.63 / Chapter 6.1 --- Line extraction --- p.64 / Chapter 6.2 --- Line tracking --- p.65 / Chapter 6.2.1 --- Preliminary geometric tracking --- p.65 / Chapter 6.2.2 --- Experimental results --- p.69 / Chapter 6.3 --- Camera motion estimation framework using EKF --- p.71 / Chapter 7 --- Experimental Results --- p.75 / Chapter 7.1 --- Simulated data experiments --- p.75 / Chapter 7.2 --- Real data experiments --- p.76 / Chapter 7.2.1 --- Linear line space --- p.80 / Chapter 7.2.2 --- Linear ruled surface --- p.84 / Chapter 7.2.3 --- Linear line congruence --- p.84 / Chapter 7.2.4 --- Linear line complex --- p.91 / Chapter 7.3 --- Empirical observation: ruled plane for line transfer --- p.93 / Chapter 7.4 --- Simulation for non-linear line structures --- p.94 / Chapter 8 --- Conclusions and Future Work --- p.97 / Chapter 8.1 --- Summary --- p.97 / Chapter 8.2 --- Future work --- p.99 / Chapter A --- Notations --- p.101 / Chapter B --- Tensor --- p.103 / Chapter C --- Matrix Decomposition and Estimation Techniques --- p.104 / Chapter D --- MATLAB Files --- p.107 / Chapter D.1 --- Estimation matrix --- p.107 / Chapter D.2 --- Line transfer --- p.109 / Chapter D.3 --- Simulation --- p.109

This thesis introduces novel methods for estimating the poses of a reference plane from its reflections for specular surface recovery. Traditional methods for specular surface recovery usually introduce a second camera and an auxiliary calibration pattern to calibrate the poses of the reference plane with respect to the camera. The calibration procedures are comparatively tedious. Auto-estimating the poses of the reference plane is therefore an appealing problem. In the first part of this thesis, two novel and practical methods are proposed to recover the poses of a moving reference plane from its reflections produced on the specular surface given its initial position. As for the first approach, the reference plane is constrained to undergo an unknown pure translation. By observing the reflections of the moving reference plane produced on the specular surface, a closed form solution is derived for recovering the unknown translation. Degenerate cases in which the proposed method fails are studied. As for the second approach, the constraint on the motion of the reference plane is removed, and the reference plane can move freely. Again, a closed form solution is derived for the unknown motion defined by a rotation matrix and a translation vector, and the degenerate cases are also presented. The thesis finally considers the problem for auto-calibrating the reference plane against the camera for specular surface recovery without prior knowledge of the reference plane’s initial position. By only observing its reflections produced on the specular surface, the poses of the reference planes can be recovered in two steps. First, by applying a collinearity constraint to the specular correspondences, a simple closed form solution is derived for recovering the poses of the reference plane relative to its initial pose. Second, by applying a ray incidence constraint to the incident rays formed by the specular correspondences and the visual rays cast from the image, a closed form solution is derived for recovering the poses of the reference plane relative to the camera. The shape of the specular surface then follows. / published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy

基於審美的圖像質量自動評估近年來引起了計算機視覺領域的普遍關注。在這篇論文裡, 我們提出使用局部與整體特徵, 基於圖像內容進行圖片質量評估。首先, 圖像的主題區域被提取出來。這部分區域最吸引觀看者的注意力。基於主題區域, 我們提取局部特徵, 並結合整體特徵進行圖像質量評估。攝影專家拍攝圖片時, 對於不同內容的圖片, 會採取不同的技術手段和審美衡量標準。基於此項觀察, 我們提出根據圖片的內容, 在提取主題區域以及特徵的時候採用不同的手段。我們講數據根據圖像內容分為七類, 並分別設計主題區域提取方法和設計特徵。我們通過翔實的實驗數據，證明提出的框架之有效。 / 同時, 我們提出根據圖像內容特徵構建自適應分類器, 以在不事先知道圖像內容分類的情況下進行自動質量評估, 並取得滿意效果。 / Automatically assessing photo quality from the perspective of visual aesthetics is of great interest in high-level vision research and has drawn much attention in recent years. In this paper, we propose content-based photo quality assessment using both regional and global features. Under this framework, subject areas, which draw the most attentions of human eyes, are first extracted. Then regional features extracted both from subject areas and background regions are combined with global features to assess photo quality. Since professional photographers adopt different photographic techniques and have different aesthetic criteria in mind when taking different types of photos (e.g. landscape versus portrait), we propose to segment subject areas and extract visual features in different ways according to the variety of photo content. We divide the photos into seven categories based on the irvisual content and develop a set of new subject are a extraction methods and new visual features specially designed for different categories. / This argument is supported by extensive experimental comparisons of existing photo quality assessment approaches as well as our new features over different categories of photos. In addition, we propose an approach of online training an adaptive classifier to combine the proposed features according to the visual content of a test photo without knowing its category. Another contribution of this work is to construct a large and diversified benchmark database for the research of photo quality assessment. It includes 17, 613 photos with manually labeled ground truth. This new benchmark database will be released to the research community. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Luo, Wei. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 47-52). / Abstracts also in Chinese. / Chapter Abstract --- p.i / Chapter Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Photo Quality Assessment by Professionals --- p.2 / Chapter 1.2 --- Automatic Quality Assessment --- p.6 / Chapter 1.3 --- Our Approach --- p.8 / Chapter 2 --- RelatedWork --- p.12 / Chapter 3 --- Content-based Quality Assessment --- p.15 / Chapter 3.1 --- Global Features --- p.15 / Chapter 3.1.1 --- Hue Composition Feature --- p.15 / Chapter 3.1.2 --- Scene Composition Feature --- p.19 / Chapter 3.2 --- Subject Area Extraction Methods --- p.21 / Chapter 3.2.1 --- Clarity-Based Subject Area Extraction --- p.22 / Chapter 3.2.2 --- Layout-Based Subject Area Extraction --- p.25 / Chapter 3.2.3 --- Human-Based Subject Area Extraction --- p.25 / Chapter 3.3 --- Regional Features --- p.25 / Chapter 3.3.1 --- Dark Channel Feature --- p.27 / Chapter 3.3.2 --- Clarity Contrast Feature --- p.28 / Chapter 3.3.3 --- Lighting Contrast Feature --- p.30 / Chapter 3.3.4 --- Composition Geometry Feature --- p.30 / Chapter 3.3.5 --- Complexity Features --- p.31 / Chapter 3.3.6 --- Human Based Features --- p.31 / Chapter 3.4 --- Quality Assessment without the Information of Photo Categories --- p.33 / Chapter 4 --- Experimental Results --- p.37 / Chapter 4.1 --- Database description --- p.37 / Chapter 4.2 --- Experimental Settings --- p.40 / Chapter 4.3 --- Result Analysis --- p.41 / Chapter 4.4 --- Conclusions and Discussions --- p.44 / Bibliography --- p.47

Pun Chi Man. / "July 2002." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (p. 119-127). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

published_or_final_version / abstract / Computer Science / Master / Master of Philosophy

Thesis (Ph. D.)--University of Hawaii at Manoa, 1995. / Includes bibliographical references (leaves 220-227). / Microfiche. / xiii, 227 leaves, bound ill. (some col.) 29 cm

創意媒體研究中，圖像/視頻再藝術作為有表現力的用戶定制外觀的創作手段受到了很大關注。交互設計中，特別是在圖像空間只有單張圖像或視頻輸入的情況下，運用計算機輔助設計虛擬地再渲染關注物體的風格化外觀來實現紋理替換是很強大的。現行的紋理替換往往通過操作圖像空間中像素的間距來處理紋理扭曲，原始圖像中潛在的紋理扭曲總是被破壞，因為現行的方法要麼存在由於手動網格拉伸導致的不恰當扭曲，要麼就由於紋理合成而導致不可避免的紋理開裂。圖像/視頻拼貼畫是被發明用以支持在顯示畫布上並行展示多個物體和活動。隨著數字視頻俘獲裝置的快速發展，相關的議題就是快速檢閱和摘要大量的視覺媒體數據集來找出關注的資料。這會是一項繁瑣的任務來審查長且乏味的監控視頻並快速把握重要信息。以關鍵信息和縮短視頻形式為交流媒介，視頻摘要是增強視覺數據集瀏覽效率和簡易理解的手段。 / 本文首先將圖像/視頻再藝術聚焦在高效紋理替換和風格化上。我們展示了一種交互紋理替換方法，能夠在不知潛在幾何結構和光照環境的情況下保持相似的紋理扭曲。我們運用SIFT 棱角特徵來自然地發現潛在紋理扭曲，並應用梯度深度圖復原和皺褶重要性優化來完成扭曲過程。我們運用GPU-CUDA 的並行性，通過實時雙邊網格和特徵導向的扭曲優化來促成交互紋理替換。我們運用基於塊的實時高精度TV-L¹光流，通過基於關鍵幀的紋理傳遞來完成視頻紋理替換。我們進一步研究了基於GPU 的風格化方法，並運用梯度優化保持原始圖像的精細結構。我們提出了一種能夠自然建模原始圖像精細結構的圖像結構圖，並運用基於梯度的切線生成和切線導向的形態學來構建這個結構圖。我們在GPU-CUDA 上通過並行雙邊網格和結構保持促成最終風格化。實驗中，我們的方法實時連續地展現了高質量的圖像/視頻的抽象再藝術。 / 當前，視頻拼貼畫大多創作靜態的基於關鍵幀的拼貼圖片，該結果只包含動態視頻有限的信息，會很大程度影響視覺數據集的理解。爲了便於瀏覽，我們展示了一種在顯示畫布上有效並行摘要動態活動的動態視頻拼貼畫。我們提出應用活動長方體來重組織及提取事件，執行視頻防抖來生成穩定的活動長方體，實行時空域優化來優化活動長方體在三維拼貼空間的位置。我們通過在GPU 上的事件相似性和移動關係優化來完成高效的動態拼貼畫，允許多視頻輸入。擁有再序核函數CUDA 處理，我們的視頻拼貼畫爲便捷瀏覽長視頻激活了動態摘要，節省大量存儲傳輸空間。實驗和調查表明我們的動態拼貼畫快捷有效，能被廣泛應用于視頻摘要。將來，我們會擴展交互紋理替換來支持更複雜的具大運動和遮蔽場景的一般視頻，避免紋理跳動。我們會採用最新視頻技術靈感使視頻紋理替換更加穩定。我們未來關於視頻拼貼畫的工作包括審查監控業中動態拼貼畫應用，並研究含有大量相機運動和不同種視頻過度的移動相機和一般視頻。 / Image/video restyling as an expressive way for producing usercustomized appearances has received much attention in creative media researches. In interactive design, it would be powerful to re-render the stylized presentation of interested objects virtually using computer-aided design tools for retexturing, especially in the image space with a single image or video as input. The nowaday retexturing methods mostly process texture distortion by inter-pixel distance manipulation in image space, the underlying texture distortion is always destroyed due to limitations like improper distortion caused by human mesh stretching, or unavoidable texture splitting caused by texture synthesis. Image/ video collage techniques are invented to allow parallel presenting of multiple objects and events on the display canvas. With the rapid development of digital video capture devices, the related issues are to quickly review and brief such large amount of visual media datasets to find out interested video materials. It will be a tedious task to investigate long boring surveillance videos and grasp the essential information quickly. By applying key information and shortened video forms as vehicles for communication, video abstraction and summary are the means to enhance the browsing efficiency and easy understanding of visual media datasets. / In this thesis, we first focused our image/video restyling work on efficient retexturing and stylization. We present an interactive retexturing that preserves similar texture distortion without knowing the underlying geometry and lighting environment. We utilized SIFT corner features to naturally discover the underlying texture distortion. The gradient depth recovery and wrinkle stress optimization are applied to accomplish the distortion process. We facilitate the interactive retexturing via real-time bilateral grids and feature-guided distortion optimization using GPU-CUDA parallelism. Video retexturing is achieved through a keyframe-based texture transferring strategy using accurate TV-L¹ optical flow with patch motion tracking techniques in real-time. Further, we work on GPU-based abstract stylization that preserves the fine structure in the original images using gradient optimization. We propose an image structure map to naturally distill the fine structure of the original images. Gradientbased tangent generation and tangent-guided morphology are applied to build the structure map. We facilitate the final stylization via parallel bilateral grids and structure-aware stylizing in real-time on GPU-CUDA. In the experiments, our proposed methods consistently demonstrate high quality performance of image/video abstract restyling in real-time. / Currently, in video abstraction, video collages are mostly produced with static keyfame-based collage pictures, which contain limited information of dynamic videos and in uence understanding of visual media datasets greatly. We present dynamic video collage that effectively summarizes condensed dynamic activities in parallel on the canvas for easy browsing. We propose to utilize activity cuboids to reorganize and extract dynamic objects for further collaging, and video stabilization is performed to generate stabilized activity cuboids. Spatial-temporal optimization is carried out to optimize the positions of activity cuboids in the 3D collage space. We facilitate the efficient dynamic collage via event similarity and moving relationship optimization on GPU allowing multi-video inputs. Our video collage approach with kernel reordering CUDA processing enables dynamic summaries for easy browsing of long videos, while saving huge memory space for storing and transmitting them. The experiments and user study have shown the efficiency and usefulness of our dynamic video collage, which can be widely applied for video briefing and summary applications. In the future, we will further extend the interactive retexturing to more complicated general video applications with large motion and occluded scene avoiding textures icking. We will also work on new approaches to make video retexturing more stable by inspiration from latest video processing techniques. Our future work for video collage includes investigating applications of dynamic collage into the surveillance industry, and working on moving camera and general videos, which may contain large amount of camera motions and different types of video shot transitions. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Li, Ping. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 109-121). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts also in Chinese. / Abstract --- p.i / Acknowledgements --- p.v / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Main Contributions --- p.5 / Chapter 1.3 --- Thesis Overview --- p.7 / Chapter 2 --- Efficient Image/video Retexturing --- p.8 / Chapter 2.1 --- Introduction --- p.8 / Chapter 2.2 --- Related Work --- p.11 / Chapter 2.3 --- Image/video Retexturing on GPU --- p.16 / Chapter 2.3.1 --- Wrinkle Stress Optimization --- p.19 / Chapter 2.3.2 --- Efficient Video Retexturing --- p.24 / Chapter 2.3.3 --- Interactive Parallel Retexturing --- p.29 / Chapter 2.4 --- Results and Discussion --- p.35 / Chapter 2.5 --- Chapter Summary --- p.41 / Chapter 3 --- Structure-Aware Image Stylization --- p.43 / Chapter 3.1 --- Introduction --- p.43 / Chapter 3.2 --- Related Work --- p.46 / Chapter 3.3 --- Structure-Aware Stylization --- p.50 / Chapter 3.3.1 --- Approach Overview --- p.50 / Chapter 3.3.2 --- Gradient-Based Tangent Generation --- p.52 / Chapter 3.3.3 --- Tangent-Guided Image Morphology --- p.54 / Chapter 3.3.4 --- Structure-Aware Optimization --- p.56 / Chapter 3.3.5 --- GPU-Accelerated Stylization --- p.58 / Chapter 3.4 --- Results and Discussion --- p.61 / Chapter 3.5 --- Chapter Summary --- p.66 / Chapter 4 --- Dynamic Video Collage --- p.67 / Chapter 4.1 --- Introduction --- p.67 / Chapter 4.2 --- Related Work --- p.70 / Chapter 4.3 --- Dynamic Video Collage on GPU --- p.74 / Chapter 4.3.1 --- Activity Cuboid Generation --- p.75 / Chapter 4.3.2 --- Spatial-Temporal Optimization --- p.80 / Chapter 4.3.3 --- GPU-Accelerated Parallel Collage --- p.86 / Chapter 4.4 --- Results and Discussion --- p.90 / Chapter 4.5 --- Chapter Summary --- p.100 / Chapter 5 --- Conclusion --- p.101 / Chapter 5.1 --- Research Summary --- p.101 / Chapter 5.2 --- Future Work --- p.104 / Chapter A --- Publication List --- p.107 / Bibliography --- p.109

Functional magnetic resonance imaging (fMRI) is an extremely popular investigative and clinical imaging tool that allows safe and noninvasive study of the functional living brain. Fundamentally, fMRI measures a physiological signal as it changes over time. The manner in which this spatio-temporal signal is acquired can create technical challenges during image reconstruction that must be corrected for if any meaningful information is to be extracted from the data. Two particular challenges that are fundamentally intertwined with each other are temporal misalignment and spatial misalignment. Temporal misalignment is due to the nature of fMRI acquisition protocols themselves: a 3D volume is created by sampling and stacking multiple 2D slices. However, these slices are not acquired simultaneously or sequentially, and therefore will always be temporally misaligned with each other. Spatial misalignment arises when subject motion is present during the scan, resulting in individual volumes being spatially misaligned with each other. Spatial and temporal misalignment are not independent from each other, and their interaction can cause additional artifacts and reconstruction challenges if not addressed properly. The purpose of this thesis is to critically examine the problem of both spatial and temporal misalignment from a signal processing perspective, while considering the physical nature and origin of the signal itself, and develop optimal correction routines for spatial and temporal misalignment and their associated artifacts. One of the most immediate problems associated with temporal misalignment is that the order in which the slices are acquired must be known in order for correction to be possible. Surprisingly, this information is rarely provided with old or shared data, meaning that this critical preprocessing step must be skipped, significantly lowering the value of the data. We use the spatio-temporal properties of the fMRI signal to develop a robust and accurate algorithm to infer the slice acquisition order retrospectively from any fMRI scan. The ability to extract the interleave parameter from any data set allows us to perform slice timing correction even if this information had been lost, or was not provided with the scan. In the next section of this work, we develop a new optimal method of slice timing correction (Filter-Shift) based on the fundamental properties of sampling theory in digital signal processing. By examining the properties of the signal of interest (The blood oxygen level depended signal: BOLD signal), we are able to design and implement an effective FIR filter to simultaneously remove noise and reconstruct the signal of interest at any shifted offset, without the need for sub-optimal interpolation. In the final section, we investigate the effects of different motion types on the MR signal based on the Bloch equation, in order to develop a theoretical foundation from which we can create an optimal correction method. We devise a novel method to remove these artifacts: Discrete reconstruction of irregular fMRI trajectory (DRIFT). Our method calculates the exact displacement of the k-space samples due to motion at each dwell time and retrospectively corrects each slice of the fMRI volume using an inverse nonuniform Fourier transform. We conclude that a hybrid approach with both prospective and retrospective components are essentially required for optimal removal of motion artifacts from the fMRI data. The combined work of this thesis provides two theoretically sound and extremely effective correction routines, that both remove artifacts and restore the underlying sampled signal. Motion correction and slice timing correction are typically the first two preprocessing steps to be applied to any fMRI data, and thus provide the foundation for any further analysis. While many other preprocessing steps can be omitted or included depending on the analysis, motion correction and slice timing correction are unequivocally beneficial and necessary for accurate and reliable results. This work provides a theoretical and quantitative framework that describes the optimal removal of artifacts associated with motion and slice timing.