• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1029-1032
• /
• 1999

Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tissue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific face image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from 2D marker movement using neural network. This also 3D motion estimation from 2D point or flow information in captered image under restriction of physics based face model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3797-3822
• /
• 2020

The inspection of cracks on the surface of tunnel linings is a common method of evaluate the condition of the tunnel. In particular, determining the thickness and shape of a crack is important because it indicates the external forces applied to the tunnel and the current condition of the concrete structure. Recently, several automatic crack detection methods have been proposed to identify cracks using captured tunnel lining images. These methods apply an image-segmentation mechanism with well-annotated datasets. However, generating the ground truths requires many resources, and the small proportion of cracks in the images cause a class-imbalance problem. A weakly annotated dataset is generated to reduce resource consumption and avoid the class-imbalance problem. However, the use of the dataset results in a large number of false positives and requires post-processing for accurate crack detection. To overcome these issues, we propose a crack detection method using a ternary classifier. The proposed method significantly reduces the false positive rate, and the performance (as measured by the F1 score) is improved by 0.33 compared to previous methods. These results demonstrate the effectiveness of the proposed method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.12
• /
• pp.620-631
• /
• 2001

In interactive environments including computer games and virtual reality applications, we have increased need for interactive control of articulated body motions. Recently, physically based methods including constrained dynamics techniques are introduced to this area, in order to produce more realistic animation sequences. However, they are hard to achieve real-time control of articulated bodies, due to their heavy computations. In this paper, we present a procedural method for interactive animation of articulated bodies. In our method, each object of the constrained body is first moved according to their physical properties and external forces, without considering any constraints. Then, the locations of objects are adjusted to satisfy given constraints. Through adapting this two-stage approach, we have avoided the solving of large linear systems of equations, to finally achieve the interactive animation of articulated bodies. We also present a few example sequences of animations, which are interactively generated on PC platforms. This method can be easily applied to character animations in virtual environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.5
• /
• pp.8-15
• /
• 2011

The goal of this paper is to describe how to construct an integrated simulation system that integrates limited perception-based mapping with spatial reasoning, path planning, and human motion style in order for a virtual soldier to effectively communicate with other virtual solders and/or human participants in a simulation. Virtual human research often ignores or simplifies perception by using a full map (with omniscient perception). In addition, previous research used a placement node where virtual environment designers save in advance the required information. However, this paper also shows that the human-like movement behavior can be achieved by the integrated ECA system with the mapping that supports a spatial understanding and does not require the omniscient perception.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.9
• /
• pp.415-423
• /
• 2001

Recently, there are many attempts to reproduce real world fine art pieces in digital forms. The digital representations are convenient to store and/or transmit. In contrast, mobiles, or moving sculptures, such as those designed by Alexander Calder cannot to reproduced realistically by usual reproduction techniques. Since mobiles are originally designed to generate motions in response to external forces applied to it, people could not fully enjoy them through photographs or static images. We present a virtual mobile system where use can easily control the mobile and can feel the impressions that the artist originally intended to provide. A real-world mobile is reconstructed in a three-dimensional physically-based model. and then virtual wind is generated to give motions to it. The motions of the mobile are generated by constraint dynamics and impulse dynamics techniques, which are modified to fully utilize the characteristics of the mobile, and finally give interactive displays on the PC platforms. The techniques presented can easily be extended to simulate other interactive dynamics systems.

• Journal of the Korea Computer Graphics Society
• /
• v.6 no.1
• /
• pp.19-27
• /
• 2000

This paper proposes a non-self-intersecting multiresolution deformable model to extract and reconstruct three-dimensional boundaries of objects from volumetric data. Deformable models offer an attractive method for extracting and reconstructing the boundary surfaces. However, convensional deformable models have three limitations- sensitivity to model initialization, difficulties in dealing with severe object concavities, and model self-intersections. We address the initialization problem by multiresolution model representation, which progressively refines the deformable model based on multiresolution volumetric data in order to extract the boundaries of the objects in a coarse-to-fine fashion. The concavity problem is addressed by mesh size regularization, which matches its size to the unit voxel of the volumetric data. We solve the model self-intersection problem by including a non-self-intersecting force among the customary internal and external forces in the physics-based formulation. This paper presents results of applying our new deformable model to extracting a sphere surface with concavities from a computer-generated volume data and a brain cortical surface from a MR volume data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.33-38
• /
• 1999

Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tissue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific race image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from 2D marker movement using neural network. This also 3D motion estimation from 2D point or flow information in captered image under restriction of physics based fare model.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.8
• /
• pp.701-709
• /
• 2000

Real world wind can be classified into two categories: natural wind and artificial wind. Artificial wind can be generated by human beings, air conditioners, electric fans, etc. In this paper, a model for artificial wind is presented. We also present methods to efficiently calculate the forces applied to the objects under influence of the artificial wind. Our model is designed for real-time applications such as virtual environments. A general wind generating system can be established through integrating our model with previous wind models those are concentrated on the natural wind generation.

• Journal of Sensor Science and Technology
• /
• v.11 no.4
• /
• pp.200-208
• /
• 2002

This paper represents the development of an array-type flexible tactile sensor using PVDF(polyvinylidene fluoride) film and flexible circuitry. The tactile sensor which has $8{\times}8$ taxels is made by using PVDF film and FPC(flexible printed circuit) technique. Experimental results on static and dynamic properties are obtained by applying arbitrary forces and frequencies generated by the shaker. In the static characteristics, the threshold and the linearity of the sensor are investigated. Also dynamic response of the sensor subjected to the variable frequencies is examined. The signals of a contact force to the tactile sensor are sensed and processed in the DSP system in which the signals are digitalized and filtered. Finally, the signals are integrated for taking the force profile. The processed signals of the outputs of the sensor are visualized on a personal computer, the shape and force distribution of the contacted object are obtained using two and three-dimensional image in real time. The reasonable performance for the detection of contact state is verified through the experiment.

• Journal of the Korea Society for Simulation
• /
• v.29 no.2
• /
• pp.35-47
• /
• 2020

Immediate and serious attention on CGF(computer generated forces) behavior modeling for defense M&S (modeling & simulation) is required in response to the reduction in the number of troops and development of 4^th industrial technologies. It is crucial for both military person and engineer to understand such technologies. The research aims to provide guidelines for establishment of research direction on CGF behavior modeling. We investigate traditional and/or novel methodologies such as rule-based, agent-based, and learning-based method. Discussions on future direction of applicable area and strategies are followed. We expect that the research plays a key role for understanding CGF behavior modeling.