• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.5
• /
• pp.1199-1206
• /
• 2015

This paper introduces an algorithm for computing similarity between two poses in the motion capture data with different scale of skeleton, different number of joints and different joint names. The proposed algorithm first performs the topological analysis on the skeleton hierarchy for classifying the joints into more meaningful groups. The global joints positions of each joint group then are aggregated into a point cloud. The number of joints and their positions are automatically adjusted in this process. Once we have two point clouds, the algorithm finds an optimal 2D transform matrix that transforms one point cloud to the other as closely as possible. Then, the similarity can be obtained by summing up all distance values between two points clouds after applying the 2D transform matrix. After some experiment, we found that the proposed algorithm is able to compute the similarity between two poses regardless of their scale, joint name and the number of joints.

• Korean Journal of Computational Design and Engineering
• /
• v.13 no.6
• /
• pp.403-411
• /
• 2008

The alignment of facial images is crucial for 2D face recognition. This is the same to facial meshes for 3D face recognition. Most of the 3D face recognition methods refer to 3D alignment but do not describe their approaches in details. In this paper, we focus on describing an automatic 3D alignment in viewpoint of quantitative analysis. This paper presents a framework of 3D face alignment and normalization based on feature points obtained by Active Shape Models (ASMs). The positions of eyes and mouth can give possibility of aligning the 3D face exactly in three-dimension space. The rotational transform on each axis is defined with respect to the reference position. In aligning process, the rotational transform converts an input 3D faces with large pose variations to the reference frontal view. The part of face is flopped from the aligned face using the sphere region centered at the nose tip of 3D face. The cropped face is shifted and brought into the frame with specified size for normalizing. Subsequently, the interpolation is carried to the face for sampling at equal interval and filling holes. The color interpolation is also carried at the same interval. The outputs are normalized 2D and 3D face which can be used for face recognition. Finally, we carry two sets of experiments to measure aligning errors and evaluate the performance of suggested process.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.39-47
• /
• 2023

In this paper, we propose a method to measure the similarity between golf swings in videos. As it is known that deep learning-based artificial intelligence technology is effective in the field of computer vision, attempts to utilize artificial intelligence in video-based sports data analysis are increasing. In this study, the joint coordinates of a person in a golf swing video were obtained using a deep learning-based pose estimation model, and based on this, the similarity of each swing segment was measured. For the evaluation of the proposed method, driver swing videos from the GolfDB dataset were used. As a result of measuring swing similarity by pairing swing videos of a total of 36 players, 26 players evaluated that their other swing sequence was the most similar, and the average ranking of similarity was confirmed to be about 5th. This ensured that the similarity could be measured in detail even when the motion was performed similarly.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.299-302
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of$.$10 persons show that the proposed method yields high recognition rates.

• Transactions of the Society of Information Storage Systems
• /
• v.8 no.1
• /
• pp.6-10
• /
• 2012

The tribological behavior of microsystems needs to be clearly understood in order to improve the reliability of precision components. For example, friction and wear phenomena pose serious problems in MEMS applications. As a first step to investigate the tribological behavior of such systems, an appropriate testing system must be acquired. In this work, a micro-wear tester based MEMS platform was designed. The main concern was to achieve a desirable range of horizontal displacement for the specimen holder and also to apply a normal force in the tens of ${\mu}N$ range. The structural analysis of the micro-wear tester showed that the proposed design satisfied these requirements while maintaining the structural integrity.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.822-826
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of 10 persons show that the proposed method yields high recognition rates.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.1
• /
• pp.41-48
• /
• 2014

This paper analyzes the Monte Carlo localization (MCL) method, which estimates the pose of an indoor mobile robot. A mobile robot must know where it is to navigate in an indoor environment. The MCL technique is one of the most influential and popular techniques for estimation of robot position and orientation using a particle filter. For the analysis, we perform experiments in an indoor environment with a differential drive robot and ultrasonic range sensor system. The analysis uses MATLAB for implementation of the MCL and investigates the effects of the control parameters on the MCL performance. The control parameters are the uncertainty of the motion model of the mobile robot and the noise level of the measurement model of the range sensor.

• Journal of Korea Multimedia Society
• /
• v.17 no.5
• /
• pp.547-555
• /
• 2014

This paper presents a method for hand segmentation using depth information, and adaptive threshold by means of histogram analysis and color clustering in HSV color model. We consider hand area as a nearer object to the camera than background on depth information. And the threshold of hand color is adaptively determined by clustering using the matching of color values on the input image with one of the regions of hue histogram. Experimental results demonstrate 95% accuracy rate. Thus, we confirmed that the proposed method is effective for hand segmentation in variations of hand color, scale, rotation, pose, different lightning conditions and any colored background.

• Lingua Humanitatis
• /
• v.2 no.2
• /
• pp.301-319
• /
• 2002

In a recent paper, I have proposed an analysis concerning propositions and 'that'-clauses as a solution to Kripke's puzzle and other similar puzzles, which I now call 'the Indefinite Description Analysis of Belief Ascription Sentences.' I have listed some of the major advantages of this analysis besides its merit as a solution to the puzzles: it is amenable to the direct-reference theory of proper names; it does not nevertheless need to introduce Russellian (singular) propositions or any other new entities. David Lewis has constructed an interesting argument to refute this analysis. His argument seems to show that my analysis has an unwelcome consequence: if someone believes any proposition, then he or she should, ipso facto, believe any necessary (mathematical or logical) proposition (such as the proposition that 1 succeeds 0). In this paper, I argue that Lewis's argument does not pose a real threat to my analysis. All his argument shows is that we should not accept the assumption called 'the equivalence thesis': if two sentences are equivalent, then they express the same proposition. I argue that this thesis is already in trouble for independent reasons. Especially, I argue that if we accept the equivalence thesis then, even without my analysis, we can derive a sentence like 'Fred believes that 1 succeeds 0 and snow is white' from a sentence like 'Fred believes that snow is white.' The consequence mentioned above is not worse than this consequence.

• The Journal of Korea Robotics Society
• /
• v.4 no.4
• /
• pp.265-272
• /
• 2009

IVarious driving mechanisms to adapt to uneven environment have been developed for many urban search and rescue (USAR) missions. A tracked mechanism has been widely used to maintain the stability of robot's pose and to produce large traction force on uneven terrain in this research area. However, it has a drawback of low energy efficiency due to friction force when rotating. Moreover, single tracked mechanism can be in trouble when the body gets caught with high projections, so the track doesn't contact on the ground. A transformable tracked mechanism is proposed to solve these problems. The mechanism is designed with several articulations surrounded by tracks, used to generate an attack angle when the robot comes near obstacles. The stair climbing ability of proposed robot was analyzed since stairs are one of the most difficult obstacles in USAR mission. Stair climbing process is divided into four separate static analysis phases. Design parameters are optimized according to geometric limitations from the static analysis. The proposed mechanism was produced from optimized design parameters, and demonstrated in artificially constructed uneven environment and the actual stairway.