Browsing by Author "Lin, I-Chen"

Now showing 1 - 17 of 17

Adaptive Motion Data Representation with Repeated Motion Analysis
(2011-04-01)
Lin, I-Chen
;
Peng, Jen-Yu
;
Lin, Chao-Chih
;
Tsai, Ming-Han
;
資訊工程學系
In this paper, we present a representation method for motion capture data by exploiting the nearly repeated characteristics and spatiotemporal coherence in human motion. We extract similar motion clips of variable lengths or speeds across the database. Since the coding costs between these matched clips are small, we propose the repeated motion analysis to extract the referred and repeated clip pairs with maximum compression gains. For further utilization of motion coherence, we approximate the subspace-projected clip motions or residuals by interpolated functions with range-aware adaptive quantization. Our experiments demonstrate that the proposed feature-aware method is of high computational efficiency. Furthermore, it also provides substantial compression gains with comparable reconstruction and perceptual errors.
Augmented Reality Instruction for Object Assembly based on Markerless Tracking
(2016)
Wu, Li-Chen
;
Lin, I-Chen
;
Tsai, Ming-Han
;
交大名義發表
;
National Chiao Tung University
Conventional object assembly instructions are usually written or illustrated in a paper manual. Users have to associate these static instructions with real objects in 3D space. In this paper, a novel augmented reality system is presented for a user to interact with objects and instructions. While most related methods pasted obvious markers onto objects for tracking and constrained their orientations or shapes, we adopt a markerless strategy for more intuitive interaction. Based on live information from an off-the-shelf RGB-D camera, the proposed tracking procedure identifies components in a scene, tracks their 3D positions and orientations, and evaluates whether there are combinations of components. According to the detected events and poses, our indication procedure then dynamically displays indication lines, circular arrows and other hints to guide a user to manipulate the components into correct poses. The experiment shows that the proposed system can robustly track the components and respond intuitive instructions at an interactive rate. Most of users in evaluation are interested and willing to use this novel technique for object assembly.
Enhancing the Realism of Sketch and Painted Portraits With Adaptable Patches
(2018-02-01)
Lee, Yin-Hsuan
;
Chang, Yu-Kai
;
Chang, Yu-Lun
;
Lin, I-Chen
;
Wang, Yu-Shuen
Realizing unrealistic faces is a complicated task that requires a rich imagination and comprehension of facial structures. When face matching, warping or stitching techniques are applied, existing methods are generally incapable of capturing detailed personal characteristics, are disturbed by block boundary artefacts, or require painting-photo pairs for training. This paper presents a data-driven framework to enhance the realism of sketch and portrait paintings based only on photo samples. It retrieves the optimal patches of adaptable shapes and numbers according to the content of the input portrait and collected photos. These patches are then seamlessly stitched by chromatic gain and offset compensation and multi-level blending. Experiments and user evaluations show that the proposed method is able to generate realistic and novel results for a moderately sized photo collection.
Feature-point driven 3D expression editing
(2007)
Chuang, Chii-Yuan
;
Lin, I-Chen
;
Lo, Yung-Sheng
;
Lin, Chao-Chih
;
資訊工程學系
Producing a life-like 3D facial expression is usually a labor-intensive process. in movie and game industries, motion capture and 3D scanning techniques, acquiring motion data from real persons, are used to speed up the production. However, acquiring dynamic and subtle details, such as wrinkles, on a face are still difficult or expensive. In this paper, we propose a feature-point-driven approach to synthesize novel expressions with details. Our work can be divided into two main parts: acquisition of 3D facial details and expression synthesis. 3D facial details are estimated from sample images by a shape-from-shading technique. While employing relation between specific feature points and facial surfaces in prototype images, our system provides an intuitive editing tool to synthesize 3D geometry and corresponding 2D textures or 3D detailed normals of novel expressions. Besides expression editing, the proposed method can also be extended to enhance existing motion capture data with facial details.
Human face aging with guided prediction and detail synthesis
(2014-09-01)
Tsai, Ming-Han
;
Liao, Yen-Kai
;
Lin, I-Chen
;
資訊工程學系
;
Department of Computer Science
In this paper, we present an example-based method to estimate the aging process of a human face. To tackle the difficulty of collecting considerable chronological photos of individuals, we utilize a two-layer strategy. Based on a sparse aging database, an EM-PCA-based algorithm with the personal guidance vector is first applied to conjecture the temporal variations of a target face. Since the subspace-based prediction may not preserve detailed creases, we propose synthesizing facial details with a separate texture dataset. Besides automatic simulation, the proposed framework can also include further guidance, e.g., parents\' impact vector or users\' indication of wrinkles. Our estimated results can improve feature point positions and user evaluation demonstrates that the two-layer approach provides more reasonable aging prediction.
Image-based detail reconstruction of non-Lambertian surfaces
(2010-01-01)
Lin, I-Chen
;
Chang, Wen-Hsing
;
Lo, Yung-Sheng
;
Peng, Jen-Yu
;
Lin, Chan-Yu
This paper presents a novel optimization framework for estimating the static or dynamic surfaces with details. The proposed method uses dense depths from a structured-light system or sparse ones from motion capture as the initial positions, and exploits non-Lambertian reflectance models to approximate surface reflectance. Multi-stage shape-from-shading (SFS) is then applied to optimize both shape geometry and reflectance properties. Because this method uses non-Lambertian properties, it can compensate for triangulation reconstruction errors caused by view-dependent reflections. This approach can also estimate detailed undulations on text-tireless regions, and employs spatial-temporal constraints for reliably tracking time-varying surfaces. Experiment results demonstrate that accurate and detailed 3D surfaces can be reconstructed from images acquired by off-the-shelf devices. Copyright (C) 2010 John Wiley & Sons, Ltd.
Immersive VR Environment for Architectural Design Education
(2017-01-01)
Tsou, Chia-Hung
;
Hsu, Ting-Wei
;
Lin, Chun-Heng
;
Tsai, Ming-Han
;
Hsu, Pei-Hsien
In tradition architectural design education, instructor and students share and discuss their ideas through drawings and models. Physical models are hard to be modified during discussion, and it is difficult to view the interior spaces. Drawings, including plans, elevations and sections, are generally used as a medium for the purpose of presentation and discussion. We propose an integrated system to support architectural design education, in which multiple users can not only explore and discuss 3D designs in a VR environment, but also manipulate 3D elements. This system also integrates procedural 3D modeling, providing users with the capability of modifying 3D designs in real-time through adjustments of parameters.
Improving Spatial Orientation in Immersive Environments
(2016-01-01)
Kotlarek, Joseph
;
Lin, I-Chen
;
Ma, Kwan-Liu
;
交大名義發表
;
National Chiao Tung University
In this paper, we present a comparative evaluation of three different approaches to improving users' spatial awareness in virtual reality environments, and consequently their user experience and productivity. Using a scientific visualization task, we test the performance of 21 participants to navigate around a virtual immersive environment. Our results suggest that using landmarks, a 3D minimap, and waypoint navigation all contribute to improved spatial orientation, while the macroscopic view of the environment provided by the 3D minimap has the greatest positive impact on spatial orientation. Users also prefer the 3D minimap for usability and immersion by a wide margin over the other techniques.
Interactive and flexible motion transition
(2007-09-01)
Peng, Jen-Yu
;
Lin, I-Chen
;
Chao, Jui-Hsiang
;
Chen, Yan-Ju
;
Juang, Gwo-Hao
In this paper, we present an example-based motion synthesis technique. Users can interactively control the virtual character to perform desired actions in any order. The desired action can be not only recorded or pre-computed motion, but also parametric synthesized one to attain the precise control of avatars. Moreover, a user can change their commands any time to switch to another action according to the instant response of opponents infighting. The quality transition motions between consecutive actions are rapidly synthesized through traversing a simple graph structure which represents the transition relationships between different poses. The graph is constructed according to clustering on frames in a corpus of motion capture data. With the pre-computation of path finding, our approach can also be applied to real-time applications. Besides, this pre-computed graph structure can be used to transit those motions not included in the database. Furthermore, our approach is automatic without any human intervention. The final results demonstrate the potential of our algorithm. Copyright (c) 2007 John Wiley & Sons, Ltd.
Interactive Visual Analysis for Vehicle Detector Data
(2015-06-01)
Chen, Yi-Cheng
;
Wang, Yu-Shuen
;
Lin, Wen-Chieh
;
Huang, Wei-Xiang
;
Lin, I-Chen
Visualization of vehicle detection (VD) data is essential because the data play an important role in traffic control and policy development. Most previous works focus on visualizing trajectories obtained from global positioning system (GPS), which are detailed but less representative. In contrast, VD data report the traffic statistic at each sensing site during a time span, including speed, flow, and occupancy of each lane, which contain comprehensive traffic information for analysis. In this work, we visualize three-year VD data of freeways in Taiwan. The visualization depicts the traffic situation at a site over time using a color-coded chart that extends from left to right over time. The charts are vertically stacked and horizontally aligned according to VD\'s located mileage and data time, respectively, to provide global insight. Our system allows semantic zoom, which changes the chart appearance in a continuous manner, to enable macro- and micro- scopic visualizations. Analysts can explore events that span an area with different sizes and that persist a time span with various lengths. To ensure the feasibility of our visualization, before the system design, we conducted a study with experts who work in the national freeway bureau and the institute of transportation of Taiwan. We also showed our results to the experts after the prototype system was built. The feedback shows that our VD data visualization is helpful to traffic control and policy development.
Markerless 3D Hand Posture Estimation from Monocular Video by Two-level Searching
(2013-01-01)
Pun, Iek-Kuong
;
Lin, I-Chen
;
Tang, Tsung-Hsien
;
資訊工程學系
;
Department of Computer Science
In this paper, a markerless 3D hand tracking system for monocular RGB video is presented. We propose a novel two-level approach to efficiently grasp the personal characteristics and high varieties of hand postures. Our system first searches the approximate nearest neighbors in a small personalized real-hand image set, and retrieves more details from a large synthetic 3D hand posture database. Temporal consistency property is also utilized for disambiguating and noise reduction. Our prototype system can approximate hand poses including rigid and non-rigid out-of-image-plane rotation, slow and fast gesture changing during rotation. It can also recover from a short-term missing hand situation in an interactive rate.
Multi-layered Expression Synthesis
(2011-01-01)
Lin, Jia-Ru
;
Lin, I-Chen
;
多媒體工程研究所
;
Institute of Multimedia Engineering
In this paper, a feature-point-driven expression editing and synthesis framework is proposed. While the extensively used blend shape methods suffer detail losing during image blending, the proposed multi-layer method can retain the flexibility and variety of geometry editing and preserve detail features as well. For low-frequency sub-bands, optimization-based blend shape is presented for large-to-mid scale synthesis. In addition, statistics-based feature matching and enhancement are proposed for high-frequency details. Our results show that the proposed methods are adequate to high-resolution expression synthesis and detail-preserved image editing.
Partial Motion Blending and Assembly for Interactive Motion Synthesis
(2008)
Juang, Gwo-Hao
;
Chen, Yan-Ju
;
Peng, Jen-Yu
;
Lin, I-Chen
;
Chao, Jui-Hsiang
Interactively controlling or editing motion capture data is an intriguing topic in games or animation prototyping. However, data-driven approaches require a large data set to synthesize motion of high variety. In the first part of this paper, we propose novel partial motion synthesis to extend the control parameter space or variety of limited motion data. We extend the attack range of kicking or punching by blending body parts respectively and then reassembling. Users can simply assign a target position in the extended parameter space and will get a motion that hit the desired target. In the second application, we propose applying partial motion assembly for motion editing. Given a sequence of key postures, our system will retrieve resembling partial figures from data sets. While reassembling the different parts of character motion and adjusting the motion variance according to the query motion, our novel synthetic motions can preserve original style and naturalness.
REAL-TIME UPPER BODY POSE ESTIMATION FROM DEPTH IMAGES
(2015)
Tsai, Ming-Han
;
Chen, Kuan-Hua
;
Lin, I-Chen
;
交大名義發表
;
National Chiao Tung University
Estimating upper body poses from a sequence of depth images is a challenging problem. Lately, the state-of-art work adopted a randomized forest method to label human parts in real time. However, it requires enormous training data to obtain favorable results. In this paper, we propose using a novel two-stage method to estimate the probability maps of upper body parts of users. These maps are then used to evaluate the region fitness of body parts for pose recovery. Experiments show that the proposed method can obtain satisfactory outcome in real time and it requires a moderate size of training data.
SI-Cut: Structural Inconsistency Analysis for Image Foreground Extraction
(2015-07-01)
Lin, I-Chen
;
Lan, Yu-Chien
;
Cheng, Po-Wen
;
資訊工程學系
;
多媒體工程研究所
This paper presents a novel approach for extracting foreground objects from an image. Existing methods involve separating the foreground and background mainly according to their color distributions and neighbor similarities. This paper proposes using a more discriminative strategy, structural inconsistency analysis, in which the localities of color and texture are considered. Given an indicated rectangle, the proposed system iteratively maximizes the consensus regions between the original image and predicted structures from the known background. The object contour can then be extracted according to inconsistency in the predicted background and foreground structures. The proposed method includes an efficient image completion technique for structural prediction. The results of experiments showed that the extraction accuracy of the proposed method is higher than that of related methods for structural scenes, and is also comparable to that of related methods for less structural situations.
Skeleton-driven surface deformation through lattices for real-time character animation
(2013-04-01)
Chen, Cheng-Hao
;
Tsai, Ming-Han
;
Lin, I-Chen
;
Lu, Pin-Hua
;
資訊工程學系
In this paper, an efficient deformation framework is presented for skeleton-driven polygonal characters. Standard solutions, such as linear blend skinning, focus on primary deformations and require intensive user adjustment. We propose constructing a lattice of cubic cells embracing the input surface mesh. Based on the lattice, our system automatically propagates smooth skinning weights from bones to drive the surface primary deformation, and it rectifies the over-compressed regions by volume preservation. The secondary deformation is, in the meanwhile, generated by the lattice shape matching with dynamic particles. The proposed framework can generate both low- and high-frequency surface motions such as muscle deformation and vibrations with few user interventions. Our results demonstrate that the proposed lattice-based method is liable to GPU computation, and it is adequate to real-time character animation.
VR Lighting Design
(2017-01-01)
Lee, Chi-Yang
;
Chang, Hsuan-Ming
;
Lin, Chun-Heng
;
Tsai, Ming-Han
;
Lin, Wen-Chieh
Lighting design is a crucial process in video games, animation, interior design, and some other fields. Current lighting design systems support only direct lighting paradigm which requires fine-tuning each light's parameters to achieve a global lighting effect. In this study, we developed an integrated lighting design system which comprises direct, indirect, and inverse lighting design paradigms in VR enviromnent. The system provides designers with an immersive, intuitive, and effective way of lighting design.