• Journal of Mechanical Science and Technology
• /
• v.17 no.11
• /
• pp.1665-1673
• /
• 2003

We propose an image-based three-dimensional shape determination system. The shape, and thus the three-dimensional coordinate information of the 3-D object, is determined solely from captured images of the 3-D object from a prescribed set of viewpoints. The approach is based on the shape-from-silhouette (SFS) technique, and the efficacy of the SFS method is tested using a sample data set. The extracted three-dimensional shape is modeled with polygons generated by a new iterative triangulation algorithm, and the polygon model can be exported to commercial software. The proposed system may be used to visualize the 3-D object efficiently, or to quickly generate initial CAD data for reverse engineering purposes, including three dimensional design applications such as 3-D animation and 3-D games.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.29-41
• /
• 2022

In this paper, we introduce a novel real-time, interactive animation system which uses real-time motion inputs from a low-cost motion-sensing device Kinect. Our system generates interaction motions between the user character and the counterpart character in real-time. While the motion of the user character is generated mimicking the user's input motion, the other character's motion is decided to react to the user avatar's motion. During a pre-processing step, our system analyzes the reference motion data and generates mapping model in advance. At run-time, our system first generates initial poses of two characters and then modifies them so that it could provide plausible interacting behavior. Our experimental results show plausible interacting animations in that the user character performs a modified motion of user input and the counterpart character properly reacts against the user character. The proposed method will be useful for developing real-time interactive animation systems which provide a better immersive experience for users.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.4 s.97
• /
• pp.102-109
• /
• 1999

Reverse engineering is a technique that helps designers to quickly generate computer interpretable data from existing physical objects. It can be used for generating CAD data from a mechanical part of high precision, or generating computer animation characters from physical mock-ups. We developed a low precision reverse engineering system that is composed of surface/solid generation software and a contact type commercial 3D digitizer. A unique point sampling procedure has been devised to easily form solid topology from the sampled data. It was also shown that STL data for rapid prototyping was successfully generated from the solid.

• International Journal of Contents
• /
• v.3 no.3
• /
• pp.32-37
• /
• 2007

Up to now, several tools to evaluate visual perception tests have been introduced for different purposes. However, they were mostly manual tools, paper books in which the therapists would turn the pages while working together with patients. This paper discusses a potential plan to develop motor-free visual perception test software for Korean patients with brain injury, and to construct a centralized database for their evaluated data in a client/server environment. Through its development, we eventually hope to achieve effective management of the data for better understanding of patients' visual perceptual skills and the standardization of the evaluation for Korean patients. With the help of the computerized environment, we also expect some advantages such as acquisition of reliable results from patients with brain injury, automation for storing and accessing patients' data, construction of the patients' database and the management of a vast amount of the data within it and the provision of a foundation to promote further development of various perceptual-cognitive rehabilitation programs.

• Journal of the Korean Society of Costume
• /
• v.51 no.4
• /
• pp.31-42
• /
• 2001

The purpose of this study was to develop a large representative data base for character goods marketing strategy. The study was to determine character name awareness in relation to segmented distribution regions and such demographic variables as sex and age. The author also analyzed preferred design. A total of 360 questionnaires were distributed and 359 reliable ones were used for statistical analysis. A SAS statistical package including frequency tables and Chi square test and factor analysis and Kendall′s relation analyses was used. The results are as follow : character name awareness involves "character name decognition" based on asking subjects to identify character names from 50 given names. "Tele-tubbies" was found to be a dominant commercial character name as a result of the recognition test, and "Sailer-moon" was found to be a dominant animation character goods as a result of the recognition test. Character recognition was significantly different in the segmented distribution legions, three age groups and different sex groups. People considered design first in purchasing any character goods, and they considered color second in purchasing them. The most favored part of garment far character to be stitch to was the center front in the T-shirt/dress shirt, the center back in the Jumper/jacket, back pocket in the trousers/skirt. The results of a Chi-square test showed that preferred part in the trousers/skirt of character was related with age variables.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.16-25
• /
• 2018

The talking head (TH) indicates an utterance face animation generated based on text and voice input. In this paper, we propose the generation method of TH with facial expression and intonation by speech input only. The problem of generating TH from speech can be regarded as a regression problem from the acoustic feature sequence to the facial code sequence which is a low dimensional vector representation that can efficiently encode and decode a face image. This regression was modeled by bidirectional RNN and trained by using SAVEE database of the front utterance face animation database as training data. The proposed method is able to generate TH with facial expression and intonation TH by using acoustic features such as MFCC, dynamic elements of MFCC, energy, and F0. According to the experiments, the configuration of the BLSTM layer of the first and second layers of bidirectional RNN was able to predict the face code best. For the evaluation, a questionnaire survey was conducted for 62 persons who watched TH animations, generated by the proposed method and the previous method. As a result, 77% of the respondents answered that the proposed method generated TH, which matches well with the speech.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.589-595
• /
• 2010

In this paper, we have designed and implemented a personalized health training system which provides health training methods using 3D animation based on the data from a professional trainer, after a trainee inputs individual physical characteristics. Many trainers at fitness centers provide only sketchy training method and usage of fitness machines not appropriate training method for trainee's physical characteristics. Individual characteristics. Individual characteristics prepared tabular input which consists of exercise goals, exercise areas, whether or not the normal movement, and RM. The system provides the training methods, the effects of exercise, and the health training motions through searching the database more accurately.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.773-774
• /
• 2015

Motion capture tracks the movement of the actor and quickly transfers it as a motion data for animation purposes. The data from the motion capture can be easily controled and applied to animating characters to make realistic movement. But conventional motion capture system is very expensive and need spacious room for its own. Recently Kinect based motion capture is widely used for its simplicity and comparably low budget. However, the Kinect based motion capture data is often corrupted by jitter and unstable data. In this paper, we propose the novel post processing method to stabilize the unwanted jitter in the motion capture data.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.4
• /
• pp.231-241
• /
• 2006

Creating controllable, responsive avatars is an important problem in computer games and virtual environments. Recently, large collections of motion capture data have been exploited for increased realism in avatar animation and control. Large motion sets have the advantage of accommodating a broad variety of natural human motion. However, when a motion set is large, the time required to identify an appropriate sequence of motions is the bottleneck for achieving interactive avatar control. In this paper, we present a novel method for training avatar behaviors from unlabelled motion data in order to animate and control avatars at minimal runtime cost. Based on machine learning technique, called Q-teaming, our training method allows the avatar to learn how to act in any given situation through trial-and-error interactions with a dynamic environment. We demonstrate the effectiveness of our approach through examples that include avatars interacting with each other and with the user.