by Man-lee Liu. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves 143-151). / LIST OF TABLES --- p.vi / LIST OF FIGURES --- p.xii / CHAPTER / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Model-based Motion Analysis --- p.2 / Chapter 1.1.1 --- With 3D-to-3D Point Correspondences --- p.4 / Chapter 1.1.2 --- With 2D-to-3D Point Correspondences --- p.5 / Chapter 1.1.3 --- With 2D-to-2D Point Correspondences --- p.6 / Chapter 1.2 --- Motion-based Segmentation --- p.7 / Chapter 1.3 --- 3D Object Recognition --- p.8 / Chapter 1.4 --- Organization of the Thesis --- p.8 / Chapter 2 --- Literature Review and Summary of Contributions --- p.10 / Chapter 2.1 --- Model-based Motion Analysis --- p.10 / Chapter 2.1.1 --- With 3D-to-3D Point Correspondences --- p.10 / Chapter 2.1.2 --- With 2D-to-3D Point Correspondences --- p.13 / Chapter 2.1.2.1 --- An Iterative Approach: Lowe's Algorithm --- p.18 / Chapter 2.1.2.2 --- A Linear Approach: Faugeras's Algorithm --- p.19 / Chapter 2.1.3 --- With 2D-to-2D Point Correspondences --- p.22 / Chapter 2.2 --- Motion-based Segmentation --- p.27 / Chapter 2.3 --- 3D Object Recognition --- p.28 / Chapter 2.4 --- Summary of Contributions --- p.30 / Chapter 3 --- Model-based Motion Analysis with 2D-to-3D Point Correspondences --- p.34 / Chapter 3.1 --- A new Iterative Algorithm for the Perspective-4-point Problem: TL-algorithm --- p.34 / Chapter 3.1.1 --- Algorithm --- p.35 / Chapter 3.1.2 --- Experiment --- p.37 / Chapter 3.1.2.1 --- Experiment using Synthetic Data --- p.38 / Chapter 3.1.2.2 --- Experiment using Real Data --- p.42 / Chapter 3.2 --- An Enhancement of Faugeras's Algorithm --- p.42 / Chapter 3.2.1 --- Experimental Comparison between the Original Faugeras's Algorithm and the Modified One --- p.44 / Chapter 3.2.1.1 --- Experiment One: Fixed Motion --- p.44 / Chapter 3.2.1.2 --- Experiment Two: Using Motion Generated Ran- domly --- p.50 / Chapter 3.2.2 --- Discussion --- p.54 / Chapter 3.3 --- A new Linear Algorithm for the Model-based Motion Analysis: Six-point Algorithm --- p.55 / Chapter 3.3.1 --- General Information of the Six-point Algorithm --- p.55 / Chapter 3.3.2 --- Original Version of the Six-point Algorithm --- p.56 / Chapter 3.3.2.1 --- Linear Solution Part --- p.56 / Chapter 3.3.2.2 --- Constraint Satisfaction --- p.58 / Use of Representation of Rotations by Quaternion --- p.62 / Use of Singular Value Decomposition --- p.62 / Determination of the translational matrix --- p.63 / Chapter 3.3.3 --- Second Version of the Six-point Algorithm --- p.64 / Chapter 3.3.4 --- Experiment --- p.65 / Chapter 3.3.4.1 --- With Synthetic Data --- p.66 / Experiment One: With Fixed Motion --- p.66 / Experiment Two: With Motion Generated Randomly --- p.77 / Chapter 3.3.4.2 --- With Real Data --- p.93 / Chapter 3.3.5 --- Summary of the Six-Point Algorithm --- p.93 / Chapter 3.3.6 --- A Visual Tracking System by using Six-point Algorithm --- p.95 / Chapter 3.4 --- Comparison between TL-algorithm and Six-point Algorithm developed --- p.97 / Chapter 3.5 --- Summary --- p.102 / Chapter 4 --- Motion-based Segmentation --- p.104 / Chapter 4.1 --- A new Approach with 3D-to-3D Point Correspondences --- p.104 / Chapter 4.1.1 --- Algorithm --- p.105 / Chapter 4.1.2 --- Experiment --- p.109 / Chapter 4.2 --- A new Approach with 2D-to-3D Point Correspondences --- p.112 / Chapter 4.2.1 --- Algorithm --- p.112 / Chapter 4.2.2 --- Experiment --- p.116 / Chapter 4.2.2.1 --- Experiment using synthetic data --- p.116 / Chapter 4.2.2.2 --- Experiment using real image sequence --- p.119 / Chapter 4.3 --- Summary --- p.119 / Chapter 5 --- 3D Object Recognition --- p.121 / Chapter 5.1 --- Proposed Algorithm for the 3D Object Recognition --- p.122 / Chapter 5.1.1 --- Hypothesis step --- p.122 / Chapter 5.1.2 --- Verification step --- p.124 / Chapter 5.2 --- 3D Object Recognition System --- p.125 / Chapter 5.2.1 --- System in Matlab: --- p.126 / Chapter 5.2.2 --- System in Visual C++ --- p.129 / Chapter 5.3 --- Experiment --- p.131 / Chapter 5.3.1 --- System in Matlab --- p.132 / Chapter 5.3.2 --- System in Visual C++ --- p.136 / Chapter 5.4 --- Summary --- p.139 / Chapter 6 --- Conclusions --- p.140 / REFERENCES --- p.142 / APPENDIX / Chapter A --- Representation of Rotations by Quaternion --- p.152 / Chapter B --- Constrained Optimization --- p.154

Zhou, Shengli. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 133-140). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts also in Chinese.

Recent research in visual object recognition has shown that context can facilitate object recognition. This study assessed the effect of self-relevant familiarity of context in object recognition. Participants performed a task in which they had to recognize degraded objects shown under varying levels of contextual information. The level of degradation at which they could successfully recognize the target object was used as a measure of performance. There were five contextual conditions: (1) no context, (2) context, (3) context and size, (4) context and location, (5) context, size and location. Within each contextual condition, we compared the performance of "Expert" participants who viewed objects in the context of their own house and "Novice" participants who viewed those particular settings for the first time. Ratings were performed to assess each object's consistency, frequency, position consistency, typicality and shape distinctiveness. Object's size was the only contextual info rmation that did not affect performance. Contextual information significantly reduced the amount of bottom-up visual information needed for object identification for both experts and novices. An interaction (Contextual Information x Level of Familiarity) was observed. Expert participants' performance improved significantly more than novice participants' performance by the presence of contextual information. Location information affected the performance of expert participants, only when objects that occupied stable positions were considered. Both expert and novice participants performed better with objects that rated high in typicality and shape distinctiveness. Object's consistency, frequency and position consistency did not seem to affect expert participants' performance but did affect novice participants' performance. / A regression analysis model that included Level of Familiarity, Contextual Information Level, Shape and Typical performance. Our results are in accordance with the priming model of visual object recognition. We concluded that a self-relevant context has its own consistency rules and that it affects visual object recognition by narrowing down the number of expectations and the search space significantly more than a non-self-relevant context does. Keywords: visual object recognition, self-relevant familiarity, location, size, probability. / by Evangelie Daskagianni. / Thesis (Ph.D.)--Florida Atlantic University, 2011. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2011. Mode of access: World Wide Web.

跨模態圖像的合成和識別已成為計算機視覺領域的熱點。實際應用中存在各種各樣的圖像模態，比如刑偵中使用的素描畫和光照不變人臉識別中使用的近紅外圖像。由於某些模態的圖像很難獲得，模態間的轉換和匹配是一項十分有用的技術，為計算機視覺的應用提供了很大的便利。 / 本論文研究了三個應用：人像素描畫的合成，基於樣本的圖像風格化和人像素描畫識別。 / 我們將人像素描畫的合成的前沿研究擴展到非可控條件下的合成。以前的工作都只能在嚴格可控的條件下從照片合成素描畫。我們提出了一種魯棒的算法，可以從有光照和姿態變化的人臉照片合成素描畫。該算法用多尺度馬爾可夫隨機場來合成局部素描圖像塊。對光照和姿態的魯棒性通過三個部分來實現：基於面部器官的形狀先驗可以抑制缺陷和扭曲的合成效果，圖像塊的特征描述子和魯棒的距離測度用來選擇素描圖像塊，以及像素灰度和梯度的一致性來有效地匹配鄰近的素描圖像塊。在CUHK人像素描數據庫和網上的名人照片上的實驗結果表明我們的算法顯著提高了現有算法的效果。 / 針對基於樣本的圖像風格化，我們提供了一種將模板圖像的藝術風格傳遞到照片上的有效方法。大多數已有方法沒有考慮圖像內容和風格的分離。我們提出了一種通過頻段分解的風格傳遞算法。一幅圖像被分解成低頻、中頻和高頻分量，分別描述內容、主要風格和邊緣信息。接著中頻和高頻分量中的風格從模板傳遞到照片，這一過程用馬爾可夫隨機場來建模。最後我們結合照片中的低頻分量和獲得的風格信息重建出藝術圖像。和其它算法相比，我們的方法不僅合成了風格，而且很好的保持了原有的圖像內容。我們通過圖像風格化和個性化藝術合成的實驗來驗證了算法的有效性。 / 我們為人像素描畫的識別提出了一個從數據中學習人臉描述子的新方向。最近的研究都集中在轉換照片和素描畫到相同的模態，或者設計復雜的分類算法來減少從照片和素描畫提取的特征的模態間差異。我們提出了一種新穎的方法：在提取特征的階段減小模態間差異。我們用一種基於耦合信息論編碼的人臉描述子來獲取有判別性的局部人臉結構和有效的匹配照片和素描畫。通過最大化在量化特征空間的照片和素描畫的互信息，我們設計了耦合信息論投影森林來實現耦合編碼。在世界上最大的人像素描畫數據庫上的結果表明我們的方法和已有最好的方法相比有顯著提高。 / Inter-modality image synthesis and recognition has been a hot topic in computer vision. In real-world applications, there are diverse image modalities, such as sketch images for law enforcement and near infrared images for illumination invariant face recognition. Therefore, it is often useful to transform images from a modality to another or match images from different modalities, due to the difficulty of acquiring image data in some modality. These techniques provide large flexibility for computer vision applications. / In this thesis we study three problems: face sketch synthesis, example-based image stylization, and face sketch recognition. / For face sketch synthesis, we expand the frontier to synthesis from uncontrolled face photos. Previous methods only work under well controlled conditions. We propose a robust algorithm for synthesizing a face sketch from a face photo with lighting and pose variations. It synthesizes local sketch patches using a multiscale Markov Random Field (MRF) model. The robustness to lighting and pose variations is achieved with three components: shape priors specific to facial components to reduce artifacts and distortions, patch descriptors and robust metrics for selecting sketch patch candidates, and intensity compatibility and gradient compatibility to match neighboring sketch patches effectively. Experiments on the CUHK face sketch database and celebrity photos collected from the web show that our algorithm significantly improves the performance of the state-of-the-art. / For example-based image stylization, we provide an effective approach of transferring artistic effects from a template image to photos. Most existing methods do not consider the content and style separately. We propose a style transfer algorithm via frequency band decomposition. An image is decomposed into the low-frequency (LF), mid-frequency (MF), and highfrequency( HF) components, which describe the content, main style, and information along the boundaries. Then the style is transferred from the template to the photo in the MF and HF components, which is formulated as MRF optimization. Finally a reconstruction step combines the LF component of the photo and the obtained style information to generate the artistic result. Compared to the other algorithms, our method not only synthesizes the style, but also preserves the image content well. We demonstrate that our approach performs excellently in image stylization and personalized artwork in experiments. / For face sketch recognition, we propose a new direction based on learning face descriptors from data. Recent research has focused on transforming photos and sketches into the same modality for matching or developing advanced classification algorithms to reduce the modality gap between features extracted from photos and sketches. We propose a novel approach by reducing the modality gap at the feature extraction stage. A face descriptor based on coupled information-theoretic encoding is used to capture discriminative local face structures and to effectively match photos and sketches. Guided by maximizing the mutual information between photos and sketches in the quantized feature spaces, the coupled encoding is achieved by the proposed coupled information-theoretic projection forest. Experiments on the largest face sketch database show that our approach significantly outperforms the state-of-the-art methods. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Zhang, Wei. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 121-137). / Abstract also in Chinese. / Abstract --- p.i / Acknowledgement --- p.v / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Multi-Modality Computer Vision --- p.1 / Chapter 1.2 --- Face Sketches --- p.4 / Chapter 1.2.1 --- Face Sketch Synthesis --- p.6 / Chapter 1.2.2 --- Face Sketch Recognition --- p.7 / Chapter 1.3 --- Example-based Image Stylization --- p.9 / Chapter 1.4 --- Contributions and Summary of Approaches --- p.10 / Chapter 1.5 --- Thesis Road Map --- p.13 / Chapter 2 --- Literature Review --- p.14 / Chapter 2.1 --- Related Works in Face Sketch Synthesis --- p.14 / Chapter 2.2 --- Related Works in Example-based Image Stylization --- p.17 / Chapter 2.3 --- Related Works in Face Sketch Recognition --- p.21 / Chapter 3 --- Lighting and Pose Robust Sketch Synthesis --- p.27 / Chapter 3.1 --- The Algorithm --- p.31 / Chapter 3.1.1 --- Overview of the Method --- p.32 / Chapter 3.1.2 --- Local Evidence --- p.34 / Chapter 3.1.3 --- Shape Prior --- p.40 / Chapter 3.1.4 --- Neighboring Compatibility --- p.42 / Chapter 3.1.5 --- Implementation Details --- p.43 / Chapter 3.1.6 --- Acceleration --- p.45 / Chapter 3.2 --- Experimental Results --- p.47 / Chapter 3.2.1 --- Lighting and Pose Variations --- p.49 / Chapter 3.2.2 --- Celebrity Faces from the Web --- p.54 / Chapter 3.3 --- Conclusion --- p.54 / Chapter 4 --- Style Transfer via Band Decomposition --- p.58 / Chapter 4.1 --- Introduction --- p.58 / Chapter 4.2 --- Algorithm Overview --- p.63 / Chapter 4.3 --- Image Style Transfer --- p.64 / Chapter 4.3.1 --- Band Decomposition --- p.64 / Chapter 4.3.2 --- MF and HF Component Processing --- p.67 / Chapter 4.3.3 --- Reconstruction --- p.74 / Chapter 4.4 --- Experiments --- p.76 / Chapter 4.4.1 --- Comparison to State-of-the-Art --- p.76 / Chapter 4.4.2 --- Extended Application: Personalized Artwork --- p.82 / Chapter 4.5 --- Conclusion --- p.84 / Chapter 5 --- Coupled Encoding for Sketch Recognition --- p.86 / Chapter 5.1 --- Introduction --- p.86 / Chapter 5.1.1 --- Related work --- p.89 / Chapter 5.2 --- Information-Theoretic Projection Tree --- p.90 / Chapter 5.2.1 --- Projection Tree --- p.91 / Chapter 5.2.2 --- Mutual Information Maximization --- p.92 / Chapter 5.2.3 --- Tree Construction with MMI --- p.94 / Chapter 5.2.4 --- Randomized CITP Forest --- p.102 / Chapter 5.3 --- Coupled Encoding Based Descriptor --- p.103 / Chapter 5.4 --- Experiments --- p.106 / Chapter 5.4.1 --- Descriptor Comparison --- p.108 / Chapter 5.4.2 --- Parameter Exploration --- p.109 / Chapter 5.4.3 --- Experiments on Benchmarks --- p.112 / Chapter 5.5 --- Conclusions --- p.115 / Chapter 6 --- Conclusion --- p.116 / Bibliography --- p.121

捕捉攝像機運動和重建攝像機成像場景深度圖的測定是在計算機視覺和機器任務包括可視化控制和自主導航是非常重要。在執行上述任務時，一個攝像機（或攝像機群組）通常安裝在機器的執行端部。攝像機和執行端部之間的手眼校準在視覺控制的正常操作中是不可缺少的。同樣，在對於需要使用多個攝像機的情况下，它們的相對幾何關係也是對各種計算機視覺應用來說也是非常重要。 / 攝像機和場景的相對運動通常產生出optical flow。問題的困難主要在於，在直接觀察視頻中的optical flow通常不是完全由運動誘導出的optical flow，而只是它的一部分。這個部分就是空間圖像等光線輪廓的正交。這部分的流場被稱為normal flow。本論文提出直接利用normal flow，而不是由normal flow引申出的optical flow，去解決以下的問題：尋找攝像機運動，場景深度圖和手眼校準。這種方法有許多顯著的貢獻，它不需引申流場，進而不要求平滑的成像場景。跟optical flow相反，normal flow不需要複雜的優化處理程序去解決流場不連續性的問題，這種技術一般是需要用大量的計算量。這也打破了傳統攝像機運動與場景深度之間的問題，在沒有預先知道不連續位置的情況下也可找出攝像機的運動。這篇論提出了幾個直接方法運用在三種不同類型的視覺系統，分別是單個攝像機，雙攝像機和多個攝像機，去找出攝像機的運動。 / 本論文首先提通過Apparent Flow 正深度 (AFPD) 約束去利用所有觀察到的normal flow去找出單個攝像機的運動參數。AFPD約束是利用一個優化問題來估計運動參數。一個反复由粗到細雙重約束的投票框架能使AFPD約束尋找出運動參數。 / 由於有限的視頻採樣率，normal flow在提取方向比其幅度部分更準確。本論文提出了兩個約束條件：一個是Apparent Flow方向（AFD）的約束，另外一個是Apparent Flow 幅度（AFM）的約束去尋找運動參數。第一個約束本身是作為一個線性不等式系統去約束運動方向的參數，第二個是利用所有圖像位置的旋轉幅度的統一性去進一步限制運動參數。一個兩階段從粗到細的約束框架能使AFD及AFM約束尋找出運動參數。 / 然而，如果沒有optical flow，normal flow是唯一的原始資料，它通常遭受到有限影像分辨率和有限視頻採樣率的問題而產生出錯誤。本文探討了這個問題的補救措施，方法是把一些攝像機併在一起，形成一個近似球形的攝像機，以增加成像系統的視野。有了一個加寬視野，normal flow的數量可更大，這可以用來抵銷normal flow在每個成像點的提取錯誤。更重要的是，攝像頭的平移和旋轉運動方向可以透過Apparent Flow分離 (AFS) 約束 及 延伸Apparent Flow分離 (EAFS) 約束來獨立估算。 / 除了使用單攝像機或球面成像系統之外，立體視覺成像系統提供了其它的視覺線索去尋找攝像機在沒有被任意縮放大小的平移運動和深度圖。傳統的立體視覺方法是確定在兩個輸入圖像特徵的對應。然而，對應的建立是非常困難。本文探討了兩個直接方法來恢復完整的攝像機運動，而沒有需要利用一對影像明確的點至點對應。第一種方法是利用AFD和AFM約束伸延到立體視覺系統，並提供了一個穩定的幾何方法來確定平移運動的幅度。第二個方法需要利用有一個較大的重疊視場，以提供一個不需反覆計算的closed-form算法。一旦確定了運動參數，深度圖可以沒有任何困難地重建。從normal flow產生的深度圖一般是以稀疏的形式存在。我們可以通過擴張深度圖，然後利用它作為在常見的TV-L₁框架的初始估計。其結果不僅有一個更好的重建性能，也產生出更快的運算時間。 / 手眼校準通常是基於像圖特徵對應。本文提出一個替代方法，是從動態攝像系統產生的normal flow來做自我校準。為了使這個方法有更強防備噪音的能力，策略是使用normal flow的流場方向去尋找手眼幾何的方向部份。偏離點及部分的手眼幾何可利用normal flow固有的流場屬性去尋找。最後完整的手眼幾何可使用穩定法來變得更可靠。手眼校準還可以被用來確定多個攝像機的相對幾何關係，而不需要求它們有重疊的視場。 / Determination of general camera motion and reconstructing depth map from a captured video of the imaged scene relative to a camera is important for computer vision and various robotics tasks including visual control and autonomous navigation. A camera (or a cluster of cameras) is usually mounted on the end-effector of a robot arm when performing the above tasks. The determination of the relative geometry between the camera frame and the end-effector frame which is commonly referred as hand-eye calibration is essential to proper operation in visual control. Similarly, determining the relative geometry of multiple cameras is also important to various applications requiring the use of multi-camera rig. / The relative motion between an observer and the imaged scene generally induces apparent flow in the video. The difficulty of the problem lies mainly in that the flow pattern directly observable in the video is generally not the full flow field induced by the motion, but only partial information of it, which is orthogonal to the iso-brightness contour of the spatial image intensity profile. The partial flow field is known as the normal flow field. This thesis addresses several important problems in computer vision: determination of camera motion, recovery of depth map, and performing hand-eye calibration from the apparent flow (normal flow) pattern itself in the video data directly but not from the full flow interpolated from the apparent flow. This approach has a number of significant contributions. It does not require interpolating the flow field and in turn does not demand the imaged scene to be smooth. In contrast to optical flow, no sophisticated optimization procedures that account for handling flow discontinuities are required, and such techniques are generally computational expensive. It also breaks the classical chicken-and-egg problem between scene depth and camera motion. No prior knowledge about the locations of the discontinuities is required for motion determination. In this thesis, several direct methods are proposed to determine camera motion using three different types of imaging systems, namely monocular camera, stereo camera, and multi-camera rig. / This thesis begins with the Apparent Flow Positive Depth (AFPD) constraint to determine the motion parameters using all observable normal flows from a monocular camera. The constraint presents itself as an optimization problem to estimate the motion parameters. An iterative process in a constrained dual coarse-to-fine voting framework on the motion parameter space is used to exploit the constraint. / Due to the finite video sampling rate, the extracted normal flow field is generally more accurate in direction component than its magnitude part. This thesis proposes two constraints: one related to the direction component of the normal flow field - the Apparent Flow Direction (AFD) constraint, and the other to the magnitude component of the field - the Apparent Flow Magnitude (AFM) constraint, to determine motion. The first constraint presents itself as a system of linear inequalities to bind the direction of motion parameters; the second one uses the globality of rotational magnitude to all image positions to constrain the motion parameters further. A two-stage iterative process in a coarse-to-fine framework on the motion parameter space is used to exploit the two constraints. / Yet without the need of the interpolation step, normal flow is only raw information extracted locally that generally suffers from flow extraction error arisen from finiteness of the image resolution and video sampling rate. This thesis explores a remedy to the problem, which is to increase the visual field of the imaging system by fixating a number of cameras together to form an approximate spherical eye. With a substantially widened visual field, the normal flow data points would be in a much greater number, which can be used to combat the local flow extraction error at each image point. More importantly, the directions of translation and rotation components in general motion can be separately estimated with the use of the novel Apparent Flow Separation (AFS) and Extended Apparent Flow Separation (EAFS) constraints. / Instead of using a monocular camera or a spherical imaging system, stereo vision contributes another visual clue to determine magnitude of translation and depth map without the problem of arbitrarily scaling of the magnitude. The conventional approach in stereo vision is to determine feature correspondences across the two input images. However, the correspondence establishment is often difficult. This thesis explores two direct methods to recover the complete camera motion from the stereo system without the explicit point-to-point correspondences matching. The first method extends the AFD and AFM constraints to stereo camera, and provides a robust geometrical method to determine translation magnitude. The second method which requires the stereo image pair to have a large overlapped field of view provides a closed-form solution, requiring no iterative computation. Once the motion parameters are here, depth map can be reconstructed without any difficulty. The depth map resulted from normal flows is generally sparse in nature. We can interpolate the depth map and then utilizing it as an initial estimate in a conventional TV-L₁ framework. The result is not only a better reconstruction performance, but also a faster computation time. / Calibration of hand-eye geometry is usually based on feature correspondences. This thesis presents an alternative method that uses normal flows generated from an active camera system to perform self-calibration. In order to make the method more robust to noise, the strategy is to use the direction component of the flow field which is more noise-immune to recover the direction part of the hand-eye geometry first. Outliers are then detected using some intrinsic properties of the flow field together with the partially recovered hand-eye geometry. The final solution is refined using a robust method. The method can also be used to determine the relative geometry of multiple cameras without demanding overlap in their visual fields. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Hui, Tak Wai. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 159-165). / Abstracts in English and Chinese. / Acknowledgements --- p.i / Abstract --- p.ii / Lists of Figures --- p.xiii / Lists of Tables --- p.xix / Chapter Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Background --- p.1 / Chapter 1.2 --- Motivation --- p.4 / Chapter 1.3 --- Research Objectives --- p.6 / Chapter 1.4 --- Thesis Outline --- p.7 / Chapter Chapter 2 --- Literature Review --- p.10 / Chapter 2.1 --- Introduction --- p.10 / Chapter 2.2 --- Recovery of Optical Flows --- p.10 / Chapter 2.3 --- Egomotion Estimation Based on Optical Flow Field --- p.14 / Chapter 2.3.1 --- Bilinear Constraint --- p.14 / Chapter 2.3.2 --- Subspace Method --- p.15 / Chapter 2.3.3 --- Partial Search Method --- p.16 / Chapter 2.3.4 --- Fixation --- p.17 / Chapter 2.3.5 --- Region Alignment --- p.17 / Chapter 2.3.6 --- Linearity and Divergence Properties of Optical Flows --- p.18 / Chapter 2.3.7 --- Constraint Lines and Collinear Points --- p.18 / Chapter 2.3.8 --- Multi-Camera Rig --- p.19 / Chapter 2.3.9 --- Discussion --- p.21 / Chapter 2.4 --- Determining Egomotion Using Direct Methods --- p.22 / Chapter 2.4.1 --- Introduction --- p.22 / Chapter 2.4.2 --- Classical Methods --- p.23 / Chapter 2.4.3 --- Pattern Matching --- p.24 / Chapter 2.4.4 --- Search Subspace Method --- p.25 / Chapter 2.4.5 --- Histogram-Based Method --- p.26 / Chapter 2.4.6 --- Multi-Camera Rig --- p.26 / Chapter 2.4.7 --- Discussion --- p.27 / Chapter 2.5 --- Determining Egomotion Using Feature Correspondences --- p.28 / Chapter 2.6 --- Hand-Eye Calibration --- p.30 / Chapter 2.7 --- Summary --- p.31 / Chapter Chapter 3 --- Determining Motion from Monocular Camera Using Merely the Positive Depth Constraint --- p.32 / Chapter 3.1 --- Introduction --- p.32 / Chapter 3.2 --- Related Works --- p.33 / Chapter 3.3 --- Background --- p.34 / Chapter 3.3 --- Apparent Flow Positive Depth (AFPD) Constraint --- p.39 / Chapter 3.4 --- Numerical Solution to AFPD Constraint --- p.40 / Chapter 3.5 --- Constrained Coarse-to-Fine Searching --- p.40 / Chapter 3.6 --- Experimental Results --- p.43 / Chapter 3.7 --- Conclusion --- p.47 / Chapter Chapter 4 --- Determining Motion from Monocular Camera Using Direction and Magnitude of Normal Flows Separately --- p.48 / Chapter 4.1 --- Introduction --- p.48 / Chapter 4.2 --- Related Works --- p.50 / Chapter 4.3 --- Apparent Flow Direction (AFD) Constraint --- p.51 / Chapter 4.3.1 --- The Special Case: Pure Translation --- p.51 / Chapter 4.3.1.1 --- Locus of Translation Using Full Flow as a Constraint --- p.51 / Chapter 4.3.1.2 --- Locus of Translation Using Normal Flow as a Constraint --- p.53 / Chapter 4.3.2 --- The Special Case: Pure Rotation --- p.54 / Chapter 4.3.2.1 --- Locus of Rotation Using Full Flow as a Constraint --- p.54 / Chapter 4.3.2.2 --- Locus of Rotation Using Normal Flow as a Constraint --- p.54 / Chapter 4.3.3 --- Solving the System of Linear Inequalities for the Two Special Cases --- p.55 / Chapter 4.3.5 --- Ambiguities of AFD Constraint --- p.59 / Chapter 4.4 --- Apparent Flow Magnitude (AFM) Constraint --- p.60 / Chapter 4.5 --- Putting the Two Constraints Together --- p.63 / Chapter 4.6 --- Experimental Results --- p.65 / Chapter 4.6.1 --- Simulation --- p.65 / Chapter 4.6.2 --- Video Data --- p.67 / Chapter 4.6.2.1 --- Pure Translation --- p.67 / Chapter 4.6.2.2 --- General Motion --- p.68 / Chapter 4.7 --- Conclusion --- p.72 / Chapter Chapter 5 --- Determining Motion from Multi-Cameras with Non-Overlapping Visual Fields --- p.73 / Chapter 5.1 --- Introduction --- p.73 / Chapter 5.2 --- Related Works --- p.75 / Chapter 5.3 --- Background --- p.76 / Chapter 5.3.1 --- Image Sphere --- p.77 / Chapter 5.3.2 --- Planar Case --- p.78 / Chapter 5.3.3 --- Projective Transformation --- p.79 / Chapter 5.4 --- Constraint from Normal Flows --- p.80 / Chapter 5.5 --- Approximation of Spherical Eye by Multiple Cameras --- p.81 / Chapter 5.6 --- Recovery of Motion Parameters --- p.83 / Chapter 5.6.1 --- Classification of a Pair of Normal Flows --- p.84 / Chapter 5.6.2 --- Classification of a Triplet of Normal Flows --- p.86 / Chapter 5.6.3 --- Apparent Flow Separation (AFS) Constraint --- p.87 / Chapter 5.6.3.1 --- Constraint to Direction of Translation --- p.87 / Chapter 5.6.3.2 --- Constraint to Direction of Rotation --- p.88 / Chapter 5.6.3.3 --- Remarks about the AFS Constraint --- p.88 / Chapter 5.6.4 --- Extension of Apparent Flow Separation Constraint (EAFS) --- p.89 / Chapter 5.6.4.1 --- Constraint to Direction of Translation --- p.90 / Chapter 5.6.4.2 --- Constraint to Direction of Rotation --- p.92 / Chapter 5.6.5 --- Solution to the AFS and EAFS Constraints --- p.94 / Chapter 5.6.6 --- Apparent Flow Magnitude (AFM) Constraint --- p.96 / Chapter 5.7 --- Experimental Results --- p.98 / Chapter 5.7.1 --- Simulation --- p.98 / Chapter 5.7.2 --- Real Video --- p.103 / Chapter 5.7.2.1 --- Using Feature Correspondences --- p.108 / Chapter 5.7.2.2 --- Using Optical Flows --- p.108 / Chapter 5.7.2.3 --- Using Direct Methods --- p.109 / Chapter 5.8 --- Conclusion --- p.111 / Chapter Chapter 6 --- Motion and Shape from Binocular Camera System: An Extension of AFD and AFM Constraints --- p.112 / Chapter 6.1 --- Introduction --- p.112 / Chapter 6.2 --- Related Works --- p.112 / Chapter 6.3 --- Recovery of Camera Motion Using Search Subspaces --- p.113 / Chapter 6.4 --- Correspondence-Free Stereo Vision --- p.114 / Chapter 6.4.1 --- Determination of Full Translation Using Two 3D Lines --- p.114 / Chapter 6.4.2 --- Determination of Full Translation Using All Normal Flows --- p.115 / Chapter 6.4.3 --- Determination of Full Translation Using a Geometrical Method --- p.117 / Chapter 6.5 --- Experimental Results --- p.119 / Chapter 6.5.1 --- Synthetic Image Data --- p.119 / Chapter 6.5.2 --- Real Scene --- p.120 / Chapter 6.6 --- Conclusion --- p.122 / Chapter Chapter 7 --- Motion and Shape from Binocular Camera System: A Closed-Form Solution for Motion Determination --- p.123 / Chapter 7.1 --- Introduction --- p.123 / Chapter 7.2 --- Related Works --- p.124 / Chapter 7.3 --- Background --- p.125 / Chapter 7.4 --- Recovery of Camera Motion Using a Linear Method --- p.126 / Chapter 7.4.1 --- Region-Correspondence Stereo Vision --- p.126 / Chapter 7.3.2 --- Combined with Epipolar Constraints --- p.127 / Chapter 7.4 --- Refinement of Scene Depth --- p.131 / Chapter 7.4.1 --- Using Spatial and Temporal Constraints --- p.131 / Chapter 7.4.2 --- Using Stereo Image Pairs --- p.134 / Chapter 7.5 --- Experiments --- p.136 / Chapter 7.5.1 --- Synthetic Data --- p.136 / Chapter 7.5.2 --- Real Image Sequences --- p.137 / Chapter 7.6 --- Conclusion --- p.143 / Chapter Chapter 8 --- Hand-Eye Calibration Using Normal Flows --- p.144 / Chapter 8.1 --- Introduction --- p.144 / Chapter 8.2 --- Related Works --- p.144 / Chapter 8.3 --- Problem Formulation --- p.145 / Chapter 8.3 --- Model-Based Brightness Constraint --- p.146 / Chapter 8.4 --- Hand-Eye Calibration --- p.147 / Chapter 8.4.1 --- Determining the Rotation Matrix R --- p.148 / Chapter 8.4.2 --- Determining the Direction of Position Vector T --- p.149 / Chapter 8.4.3 --- Determining the Complete Position Vector T --- p.150 / Chapter 8.4.4 --- Extrinsic Calibration of a Multi-Camera Rig --- p.151 / Chapter 8.5 --- Experimental Results --- p.151 / Chapter 8.5.1 --- Synthetic Data --- p.151 / Chapter 8.5.2 --- Real Image Data --- p.152 / Chapter 8.6 --- Conclusion --- p.153 / Chapter Chapter 9 --- Conclusion and Future Work --- p.154 / Related Publications --- p.158 / Bibliography --- p.159 / Appendix --- p.166 / Chapter A --- Apparent Flow Direction Constraint --- p.166 / Chapter B --- Ambiguity of AFD Constraint --- p.168 / Chapter C --- Relationship between the Angle Subtended by any two Flow Vectors in Image Plane and the Associated Flow Vectors in Image Sphere --- p.169

用投影機替代傳統的顯示器可在較小尺寸的設備上得到較大尺寸的顯示，從而彌補了傳統顯示器移動性差的不足。投影機照相機系統通過不可感知的結構光，在顯示視頻內容的同時具備了三維傳感能力，從而可為自然人機交互提供良好的平臺。投影機照相機系統在人機交互中的應用主要包括以下四個核心內容: (1)同時顯示和傳感，即如何在最低限度的影響原始投影的前提下，使得普通視頻投影機既是顯示設備又是三維傳感器;(2) 三維信息的理解:即如何通過利用額外的信息來彌補稀疏點云的不足，從而改善系統性能; (3) 分割:即如何在不斷變化投影內容的影響下得到準確的分割(4) 姿態識別:即如何從單張圖像中得到三維姿態。本文將針對上述四個方面進行深入的研究和探討，並提出改造方案。 / 首先，為了解決嵌入編碼不可見性與編碼恢復魯棒性之間的矛盾，本文提出一種在編解碼兩端同時具備抗噪能力的方法。我們使用特殊設計的幾何圖元和較大的海明距離來編碼，從而增強了抗噪聲干擾能力。同時在解碼端，我們使用事先通過訓練得到的幾何圖元檢測器來檢測和識別嵌入圖像的編碼，從而解決了因噪聲干擾使用傳統結構光中的分割方法很難提取嵌入編碼的困難。 / 其次在三維信息的理解方面，我們提出了一個通過不可感知結構光來實現六自由度頭部姿態估計的方法。首先，通過精心設計的投影策略和照相機-投影機的同步，在不可感知結構光的照射下，我們得到了模式圖和與之相對應的紋理圖。然後，在紋理圖中使用主動表觀模型定位二維面部特徵，在模式圖中通用結構光方法計算出點雲坐標，結合上述兩種信息來計算面部特征點的三維坐標。最后，通過不同幀中對應特征點三維坐標間的相關矩陣的奇異值分解來估計頭部的朝向和位移。 / 在分割方面，我們提出一種在投影機-照相機系統下由粗到精的手部分割方法。首先手部區域先通過對比度顯著性檢測的方法粗略分割出來，然後通過保護邊界的平滑方法保證分割區域的一致性，最后精確的分割結果自置信度分析得到。 / 最後，我們又探討如何僅使用投影機和照相機將在普通桌面上的投影區域轉化成觸摸屏的方案。我們將一種經過統計分析得到的隨機二元編碼嶽入到普通投影內容中，從而在用戶沒有感知的情況下，使得投影機-照相機系統具備三維感知的能力。最終手指是否觸及桌面是通過投影機-照相機-桌面系統的標定信息，精准的手部區域分割和手指尖定位，投影機投影平面勻照相機圖像平面的單應映射以及最入投影的編碼來確定。 / The use of a projector in place of traditional display device would dissociate display size from device size, making portability much less an issue. Associated with camera, the projector-camera system allows simultaneous video display and 3D acquisition through imperceptible structured light sensing, providing a vivid and immersed platform for natural human-computer interaction. Key issues involved in the approach include: (1) Simultaneous Display and Acquisition: how to make normal video projector not only a display device but also a 3D sensor even with the prerequisite of incurring minimum disturbance to the original projection; (2) 3D Information Interpretation: how to interpret the spare depth information with the assistance of some additional cues to enhance the system performance; (3) Segmentation: how to acquire accurate segmentation in the presence of the incessant variation of the projected video content; (4) Posture Recognition: how to infer 3D posture from single image. This thesis aims at providing improved solutions to each of these issues. / To address the conflict between imperceptibility of the embedded codes and the robustness of code retrieval, noise-tolerant schemes to both the coding and decoding stages are introduced. At the coding end, specifically designed primitive shapes and large Hamming distance are employed to enhance tolerance toward noise. At the decoding end, pre-trained primitive shape detectors are used to detect and identify the embedded codes a task difficult to achieve by segmentation that is used in general structured light methods, for the weakly embedded information is generally interfered by substantial noise. / On 3D information interpretation, a system that estimates 6-DOF head pose by imperceptible structured light sensing is proposed. First, through elaborate pattern projection strategy and camera-projector synchronization, pattern-illuminated images and the corresponding scene-texture image are captured with imperceptible patterned illumination. Then, 3D positions of the key facial feature points are derived by a combination of the 2D facial feature points in the scene-texture image localized by AAM and the point cloud generated by structured light sensing. Eventually, the head orientation and translation are estimated by SVD of a correlation matrix that is generated from the 3D corresponding feature point pairs over different frames. / On the segmentation issue, we describe a coarse-to-fine hand segmentation method for projector-camera system. After rough segmentation by contrast saliency detection and mean shift-based discontinuity-preserved smoothing, the refined result is confirmed through confidence evaluation. / Finally, we address how an HCI (Human-Computer Interface) with small device size, large display, and touch input facility can be made possible by a mere projector and camera. The realization is through the use of a properly embedded structured light sensing scheme that enables a regular light-colored table surface to serve the dual roles of both a projection screen and a touch-sensitive display surface. A random binary pattern is employed to code structured light in pixel accuracy, which is embedded into the regular projection display in a way that the user perceives only regular display but not the structured pattern hidden in the display. With the projection display on the table surface being imaged by a camera, the observed image data, plus the known projection content, can work together to probe the 3D world immediately above the table surface, like deciding if there is a finger present and if the finger touches the table surface, and if so at what position on the table surface the finger tip makes the contact. All the decisions hinge upon a careful calibration of the projector-camera-table surface system, intelligent segmentation of the hand in the image data, and exploitation of the homography mapping existing between the projector’s display panel and the camera’s image plane. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Dai, Jingwen. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 155-182). / Abstract also in Chinese. / Abstract --- p.i / 摘要 --- p.iv / Acknowledgement --- p.vi / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation --- p.1 / Chapter 1.2 --- Challenges --- p.2 / Chapter 1.2.1 --- Simultaneous Display and Acquisition --- p.2 / Chapter 1.2.2 --- 3D Information Interpretation --- p.3 / Chapter 1.2.3 --- Segmentation --- p.4 / Chapter 1.2.4 --- Posture Recognition --- p.4 / Chapter 1.3 --- Objective --- p.5 / Chapter 1.4 --- Organization of the Thesis --- p.5 / Chapter 2 --- Background --- p.9 / Chapter 2.1 --- Projector-Camera System --- p.9 / Chapter 2.1.1 --- Projection Technologies --- p.10 / Chapter 2.1.2 --- Researches in ProCams --- p.16 / Chapter 2.2 --- Natural Human-Computer Interaction --- p.24 / Chapter 2.2.1 --- Head Pose --- p.25 / Chapter 2.2.2 --- Hand Gesture --- p.33 / Chapter 3 --- Head Pose Estimation by ISL --- p.41 / Chapter 3.1 --- Introduction --- p.42 / Chapter 3.2 --- Previous Works --- p.44 / Chapter 3.2.1 --- Head Pose Estimation --- p.44 / Chapter 3.2.2 --- Imperceptible Structured Light --- p.46 / Chapter 3.3 --- Method --- p.47 / Chapter 3.3.1 --- Pattern Projection Strategy for Imperceptible Structured Light Sensing --- p.47 / Chapter 3.3.2 --- Facial Feature Localization --- p.48 / Chapter 3.3.3 --- 6 DOF Head Pose Estimation --- p.54 / Chapter 3.4 --- Experiments --- p.57 / Chapter 3.4.1 --- Overview of Experiment Setup --- p.57 / Chapter 3.4.2 --- Test Dataset Collection --- p.58 / Chapter 3.4.3 --- Results --- p.59 / Chapter 3.5 --- Summary --- p.63 / Chapter 4 --- Embedding Codes into Normal Projection --- p.65 / Chapter 4.1 --- Introduction --- p.66 / Chapter 4.2 --- Previous Works --- p.68 / Chapter 4.3 --- Method --- p.70 / Chapter 4.3.1 --- Principle of Embedding Imperceptible Codes --- p.70 / Chapter 4.3.2 --- Design of Embedded Pattern --- p.73 / Chapter 4.3.3 --- Primitive Shape Identification and Decoding --- p.76 / Chapter 4.3.4 --- Codeword Retrieval --- p.77 / Chapter 4.4 --- Experiments --- p.79 / Chapter 4.4.1 --- Overview of Experiment Setup --- p.79 / Chapter 4.4.2 --- Embedded Code Imperceptibility Evaluation --- p.81 / Chapter 4.4.3 --- Primitive Shape Detection Accuracy Evaluation --- p.82 / Chapter 4.5 --- Sensitivity Evaluation --- p.84 / Chapter 4.5.1 --- Working Distance --- p.85 / Chapter 4.5.2 --- Projection Surface Orientation --- p.87 / Chapter 4.5.3 --- Projection Surface Shape --- p.88 / Chapter 4.5.4 --- Projection Surface Texture --- p.91 / Chapter 4.5.5 --- Projector-Camera System --- p.91 / Chapter 4.6 --- Applications --- p.95 / Chapter 4.6.1 --- 3D Reconstruction with Normal Video Projection --- p.95 / Chapter 4.6.2 --- Sensing Surrounding Environment on Mobile Robot Platform --- p.97 / Chapter 4.6.3 --- Natural Human-Computer Interaction --- p.99 / Chapter 4.7 --- Summary --- p.99 / Chapter 5 --- Hand Segmentation in PROCAMS --- p.102 / Chapter 5.1 --- Previous Works --- p.103 / Chapter 5.2 --- Method --- p.106 / Chapter 5.2.1 --- Rough Segmentation by Contrast Saliency --- p.106 / Chapter 5.2.2 --- Mean-Shift Region Smoothing --- p.108 / Chapter 5.2.3 --- Precise Segmentation by Fusing --- p.110 / Chapter 5.3 --- Experiments --- p.111 / Chapter 5.4 --- Summary --- p.115 / Chapter 6 --- Surface Touch-Sensitive Display --- p.116 / Chapter 6.1 --- Introduction --- p.117 / Chapter 6.2 --- Previous Works --- p.119 / Chapter 6.3 --- Priors in Pro-Cam System --- p.122 / Chapter 6.3.1 --- Homography Estimation --- p.123 / Chapter 6.3.2 --- Radiometric Prediction --- p.124 / Chapter 6.4 --- Embedding Codes into Video Projection --- p.125 / Chapter 6.4.1 --- Imperceptible Structured Light --- p.125 / Chapter 6.4.2 --- Embedded Pattern Design Strategy and Statistical Analysis --- p.126 / Chapter 6.5 --- Touch Detection using Homography and Embedded Code --- p.129 / Chapter 6.5.1 --- Hand Segmentation --- p.130 / Chapter 6.5.2 --- Fingertip Detection --- p.130 / Chapter 6.5.3 --- Touch Detection Through Homography --- p.131 / Chapter 6.5.4 --- From Resistive Touching to Capacitive Touching --- p.133 / Chapter 6.6 --- Experiments --- p.135 / Chapter 6.6.1 --- System Initialization --- p.137 / Chapter 6.6.2 --- Display Quality Evaluation --- p.139 / Chapter 6.6.3 --- Touch Accuracy Evaluation --- p.141 / Chapter 6.6.4 --- Trajectory Tracking Evaluation --- p.145 / Chapter 6.6.5 --- Multiple-Touch Evaluation --- p.145 / Chapter 6.6.6 --- Efficiency Evaluation --- p.147 / Chapter 6.7 --- Summary --- p.149 / Chapter 7 --- Conclusion and Future Work --- p.150 / Chapter 7.1 --- Conclusion and Contributions --- p.150 / Chapter 7.2 --- Related Publications --- p.152 / Chapter 7.3 --- Future Work --- p.153 / Bibliography --- p.155

by Po-Ming Wong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references (leaves 94-100). / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Introduction --- p.1 / Chapter 1.2 --- Image Data --- p.2 / Chapter 1.2.1 --- Feature Detection --- p.2 / Chapter 1.3 --- Neural Networks --- p.4 / Chapter 1.4 --- Invariant Object Recognition --- p.5 / Chapter 1.5 --- Thesis Outline --- p.7 / Chapter 2 --- Feature Extraction --- p.8 / Chapter 2.1 --- Review of the Principle Component Analysis (PCA) Method --- p.9 / Chapter 2.1.1 --- Theory --- p.10 / Chapter 2.2 --- Covariance Operator --- p.13 / Chapter 2.3 --- Corner Extraction Method --- p.16 / Chapter 2.3.1 --- Corner Detection on the Surface of an Object --- p.16 / Chapter 2.3.2 --- Corner Detection at Boundary Region --- p.17 / Chapter 2.3.3 --- Steps in Corner Detection Process --- p.21 / Chapter 2.4 --- Experiment Results and Discussion --- p.23 / Chapter 2.4.1 --- Features Localization --- p.27 / Chapter 2.4.2 --- Preparing Feature Points for Matching Process --- p.32 / Chapter 2.5 --- Summary --- p.32 / Chapter 3 --- Invariant Graph Matching Using High-Order Hopfield Network --- p.36 / Chapter 3.1 --- Review of the Hopfield Network --- p.37 / Chapter 3.1.1 --- 3D Image Matching Algorithm --- p.40 / Chapter 3.1.2 --- Iteration Algorithm --- p.44 / Chapter 3.2 --- Third-order Hopfield Network --- p.45 / Chapter 3.3 --- Experimental Results --- p.49 / Chapter 3.4 --- Summary --- p.58 / Chapter 4 --- Hopfield Network for 2D and 3D Mirror-Symmetric Image Match- ing --- p.59 / Chapter 4.1 --- Introduction --- p.59 / Chapter 4.2 --- Geometric Symmetry --- p.60 / Chapter 4.3 --- Motivation --- p.62 / Chapter 4.4 --- Third-order Hopfield Network for Solving 2D Symmetry Problems --- p.66 / Chapter 4.5 --- Forth-order Hopfield Network for Solving 3D Symmetry Problem --- p.71 / Chapter 4.6 --- Experiment Results --- p.78 / Chapter 4.7 --- Summary --- p.88 / Chapter 5 --- Conclusion --- p.90 / Chapter 5.1 --- Results and Contributions --- p.90 / Chapter 5.2 --- Future Work --- p.92 / Bibliography --- p.94

No description available.

Leung, Man Chuen. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (leaves 81-88). / Abstract also in Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Motivation and Objective --- p.1 / Chapter 1.2 --- Contribution --- p.3 / Chapter 1.3 --- Organization of the Thesis --- p.4 / Chapter 2 --- Background --- p.5 / Chapter 2.1 --- Introduction --- p.5 / Chapter 2.2 --- Static Projector and Screen Systems --- p.6 / Chapter 2.3 --- Dynamic Projector or Screen Systems --- p.9 / Chapter 2.3.1 --- Movable Projector Systems --- p.10 / Chapter 2.3.2 --- Dynamic Screen Systems --- p.11 / Chapter 2.4 --- Summary --- p.17 / Chapter 3 --- System Overview --- p.18 / Chapter 3.1 --- System Design --- p.18 / Chapter 3.2 --- Our Approach --- p.18 / Chapter 3.2.1 --- Offline Projector Camera Calibration --- p.20 / Chapter 3.2.2 --- Quadrangle Detection and Tracking --- p.20 / Chapter 3.2.3 --- Projection --- p.22 / Chapter 3.3 --- Extension --- p.22 / Chapter 4 --- Projector-Camera Pair Calibration --- p.23 / Chapter 4.1 --- Introduction --- p.23 / Chapter 4.2 --- Projective Geometry of a Projector --- p.25 / Chapter 4.3 --- Calibration Method --- p.27 / Chapter 5 --- Quadrangle Detection and Tracking --- p.31 / Chapter 5.1 --- Introduction --- p.31 / Chapter 5.2 --- Line Feature Extraction --- p.33 / Chapter 5.3 --- Automatic Quadrangle Detection --- p.33 / Chapter 5.4 --- Real-time Quadrangle Tracking --- p.36 / Chapter 5.4.1 --- State Dynamic Model --- p.39 / Chapter 5.4.2 --- Observation Model --- p.39 / Chapter 5.5 --- Tracking Lose Strategy --- p.41 / Chapter 5.5.1 --- Determination of Tracking Failure --- p.42 / Chapter 5.6 --- Recover from Tracking Failure --- p.43 / Chapter 6 --- Projection onto the Cardboard --- p.44 / Chapter 7 --- Implementation and Experiment Results --- p.47 / Chapter 7.1 --- Introduction --- p.47 / Chapter 7.2 --- Projector-Camera Pair Calibration --- p.49 / Chapter 7.3 --- Quadrangle Detection and Tracking --- p.51 / Chapter 7.3.1 --- Experiment 1 - Tracking precision and robustness against occlusion --- p.51 / Chapter 7.3.2 --- Experiment 2 - Robustness against dense clutter --- p.52 / Chapter 7.3.3 --- Experiment 3 - Tracking of a paper with printed content --- p.53 / Chapter 7.3.4 --- Experiment 4 - Moving camera --- p.53 / Chapter 7.3.5 --- Processing Time --- p.55 / Chapter 7.4 --- Projection Performance --- p.57 / Chapter 7.4.1 --- Projection Precision --- p.57 / Chapter 7.4.2 --- Projection Latency --- p.58 / Chapter 8 --- Limitations and Discussions --- p.61 / Chapter 8.1 --- Limitation on Projection Resolution --- p.61 / Chapter 8.2 --- Limitation on Depth of Field --- p.62 / Chapter 8.3 --- Tracking Stability and Processing Time --- p.62 / Chapter 8.4 --- Handling Projected Light --- p.63 / Chapter 8.5 --- Possible Extensions --- p.63 / Chapter 9 --- View Dependent Projection and Application --- p.65 / Chapter 9.1 --- View Dependent Projection --- p.65 / Chapter 9.2 --- Head Pose Tracking --- p.67 / Chapter 9.3 --- Application - Hand-held 3D Model Viewer --- p.68 / Chapter 9.3.1 --- Introduction --- p.68 / Chapter 9.3.2 --- Implementation Detail --- p.69 / Chapter 9.3.3 --- Experiment Results --- p.73 / Chapter 9.3.4 --- Discussions --- p.73 / Chapter 9.4 --- Summary --- p.75 / Chapter 10 --- Conclusions --- p.77 / A Pose Estimation of Cardboard --- p.79 / Bibliography --- p.81

Du, Hao. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (p. 61). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- 3D Reconstruction from 2D Line Drawings and its Applications --- p.1 / Chapter 1.2 --- Algorithmic Development of 3D Reconstruction from 2D Line Drawings --- p.3 / Chapter 1.2.1 --- Line Labeling and Realization Problem --- p.4 / Chapter 1.2.2 --- 3D Reconstruction from Multiple Line Drawings --- p.5 / Chapter 1.2.3 --- 3D Reconstruction from a Single Line Drawing --- p.6 / Chapter 1.3 --- Research Problems and Our Contributions --- p.12 / Chapter 2 --- Adaptive Parameter Setting --- p.15 / Chapter 2.1 --- Regularities in Optimization-Based 3D Reconstruction --- p.15 / Chapter 2.1.1 --- Face Planarity --- p.18 / Chapter 2.1.2 --- Line Parallelism --- p.19 / Chapter 2.1.3 --- Line Verticality --- p.19 / Chapter 2.1.4 --- Isometry --- p.19 / Chapter 2.1.5 --- Corner Orthogonality --- p.20 / Chapter 2.1.6 --- Skewed Facial Orthogonality --- p.21 / Chapter 2.1.7 --- Skewed Facial Symmetry --- p.22 / Chapter 2.1.8 --- Line Orthogonality --- p.24 / Chapter 2.1.9 --- Minimum Standard Deviation of Angles --- p.24 / Chapter 2.1.10 --- Face Perpendicularity --- p.24 / Chapter 2.1.11 --- Line Collinearity --- p.25 / Chapter 2.1.12 --- Whole Symmetry --- p.25 / Chapter 2.2 --- Adaptive Parameter Setting in the Objective Function --- p.26 / Chapter 2.2.1 --- Hill-Climbing Optimization Technique --- p.28 / Chapter 2.2.2 --- Adaptive Weight Setting and its Explanations --- p.29 / Chapter 3 --- Parameter Learning --- p.33 / Chapter 3.1 --- Construction of A Large 3D Object Database --- p.33 / Chapter 3.2 --- Training Dataset Generation --- p.34 / Chapter 3.3 --- Parameter Learning Framework --- p.37 / Chapter 3.3.1 --- Evolutionary Algorithms --- p.38 / Chapter 3.3.2 --- Reconstruction Error Calculation --- p.39 / Chapter 3.3.3 --- Parameter Learning Algorithm --- p.41 / Chapter 4 --- Experimental Results --- p.45 / Chapter 4.1 --- Adaptive Parameter Setting --- p.45 / Chapter 4.1.1 --- Use Manually-Set Weights --- p.45 / Chapter 4.1.2 --- Learn the Best Weights with Different Strategies --- p.48 / Chapter 4.2 --- Evolutionary-Algorithm-Based Parameter Learning --- p.49 / Chapter 5 --- Conclusions and Future Work --- p.53 / Bibliography --- p.55