13 results on '"Hoeryong Jung"'
Search Results
2. IMU/UWB Sensor Fusion Using Moving Average Filter for Indoor Positioning of Mobile Robot
- Author
-
Hoeryong Jung, limjunghwan, and Shim Junhyuk
- Subjects
Control and Systems Engineering ,Computer science ,Inertial measurement unit ,Moving average ,business.industry ,Applied Mathematics ,Computer vision ,Mobile robot ,Kalman filter ,Artificial intelligence ,Sensor fusion ,business ,Software - Published
- 2020
- Full Text
- View/download PDF
3. TUHAD: Taekwondo Unit Technique Human Action Dataset with Key Frame-Based CNN Action Recognition
- Author
-
Jinkue Lee and Hoeryong Jung
- Subjects
Data Analysis ,Computer science ,Movement ,convolutional neural network ,02 engineering and technology ,lcsh:Chemical technology ,Biochemistry ,Convolutional neural network ,Article ,Analytical Chemistry ,Unit (housing) ,human action dataset ,0202 electrical engineering, electronic engineering, information engineering ,Humans ,lcsh:TP1-1185 ,Electrical and Electronic Engineering ,Instrumentation ,action recognition ,business.industry ,gesture recognition ,020207 software engineering ,Pattern recognition ,Atomic and Molecular Physics, and Optics ,taekwondo ,Action (philosophy) ,Gesture recognition ,poomsae ,Correlation analysis ,Key frame ,Action recognition ,020201 artificial intelligence & image processing ,Neural Networks, Computer ,Artificial intelligence ,business ,Martial Arts - Abstract
In taekwondo, poomsae (i.e., form) competitions have no quantitative scoring standards, unlike gyeorugi (i.e., full-contact sparring) in the Olympics. Consequently, there are diverse fairness issues regarding poomsae evaluation, and the demand for quantitative evaluation tools is increasing. Action recognition is a promising approach, but the extreme and rapid actions of taekwondo complicate its application. This study established the Taekwondo Unit technique Human Action Dataset (TUHAD), which consists of multimodal image sequences of poomsae actions. TUHAD contains 1936 action samples of eight unit techniques performed by 10 experts and captured by two camera views. A key frame-based convolutional neural network architecture was developed for taekwondo action recognition, and its accuracy was validated for various input configurations. A correlation analysis of the input configuration and accuracy demonstrated that the proposed model achieved a recognition accuracy of up to 95.833% (lowest accuracy of 74.49%). This study contributes to the research and development of taekwondo action recognition.
- Published
- 2020
4. 3D reconstruction of underwater scene for marine bioprospecting using remotely operated underwater vehicle (ROV)
- Author
-
Changjoo Shin, Suengjoon Choi, Kiyong Cho, Youngil Shin, Young-Eun Song, and Hoeryong Jung
- Subjects
0106 biological sciences ,Pixel ,Computer science ,business.industry ,Mechanical Engineering ,Elevation ,Reconstruction algorithm ,02 engineering and technology ,Image plane ,Remotely operated underwater vehicle ,010603 evolutionary biology ,01 natural sciences ,Sonar ,Mechanics of Materials ,Spatial reference system ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Computer vision ,Artificial intelligence ,Underwater ,business - Abstract
Marine bioprospecting is the procedure of identifying the characteristics of marine organisms to develop them into commercial products. This paper proposes a 3D reconstruction algorithm to facilitate 3D visualization of underwater scene for the marine bioprospecting using remotely operated underwater vehicle (ROV). It allows to provide an operator with intuitive user interface and accordingly contribute to enhance the operability of the ROV in the bioprospecting operation. The reconstruction algorithm transforms 2D pixel coordinates of the sonar image into the corresponding 3D spatial coordinates of the scene surface by restoring the surface elevation missing in the sonar image. First, the algorithm segments the objects and shadows in the image by classifying the pixels based on the intensity value of the seafloor. Second, it computes the surface elevation on the object pixels based on their intensity values. Third, the elevation correction factor, which is derived by the ratio between height of the object and the length of the shadow, is multiplied to the surface elevation value. Finally, the 3D coordinates of the scene surfaces are reconstructed using the coordinate transformation from the image plane to the seafloor with the restored surface elevation values. The experimental results show the algorithm successfully reconstructs the surface of the reference object within an error range less than 10 % of the object dimension, and practical applicability to the marine bioprospecting operation.
- Published
- 2018
- Full Text
- View/download PDF
5. Wire-actuated Position Sensor for Object Following Control of Mobile Robot
- Author
-
Hyeongjun Chang, Seokhun Yoon, Junhyuk Sim, Young Eun Song, Hoeryong Jung, and Jaedong Kim
- Subjects
Control and Systems Engineering ,business.industry ,Computer science ,Applied Mathematics ,Computer vision ,Mobile robot ,Artificial intelligence ,business ,Object (computer science) ,Control (linguistics) ,Software ,Position sensor - Published
- 2018
- Full Text
- View/download PDF
6. IMU based Walking Position Tracking using Kinematic Model of Lower Body and Walking Cycle Analysis
- Author
-
Young Eun Song, Hoeryong Jung, and Kee Wook Song
- Subjects
0209 industrial biotechnology ,Computer science ,business.industry ,Mechanical Engineering ,Position tracking ,020207 software engineering ,02 engineering and technology ,Kinematics ,Industrial and Manufacturing Engineering ,020901 industrial engineering & automation ,Lower body ,Inertial measurement unit ,Walking cycle ,0202 electrical engineering, electronic engineering, information engineering ,Computer vision ,Artificial intelligence ,Safety, Risk, Reliability and Quality ,business - Published
- 2018
- Full Text
- View/download PDF
7. Method for Quantitatively Comparing Synergy of Stroke Patients using Non-Negative Matrix Reconstruction with Time Sequence Synchronization (ICCAS 2019)
- Author
-
Junghwan Lim and Hoeryong Jung
- Subjects
0209 industrial biotechnology ,Stroke patient ,Computer science ,business.industry ,020208 electrical & electronic engineering ,Pattern recognition ,02 engineering and technology ,Time sequence ,Neurophysiology ,medicine.disease ,Synchronization ,Matrix (mathematics) ,020901 industrial engineering & automation ,Distortion problem ,0202 electrical engineering, electronic engineering, information engineering ,medicine ,Artificial intelligence ,business ,Muscle synergy ,Stroke - Abstract
Muscle synergy is the association of several muscle groups contracting simultaneously as a single functional unit. Recently, the synergy has been emphasized in neurophysiological studies to utilize it as an evaluation index for stroke patients. In this paper, we proposed novel method for quantitatively comparing muscle synergy of normal people and the stroke patient for evaluating severity of the stroke. The proposed method uses NNR (Non-Negative Matrix Reconstruction) algorithm for reconstructing muscle weight matrix W. The proposed method synchronizes the time sequence of EMG data of the stroke patient with the normal people based on working phases. The method improves the distortion problem of NNR algorithm through the synchronization of time sequence.
- Published
- 2019
- Full Text
- View/download PDF
8. Analytical and Psychophysical Comparison of Bilateral Teleoperators for Enhanced Perceptual Performance
- Author
-
Jang Ho Cho, Doo Yong Lee, Hyoung Il Son, Hoeryong Jung, and Tapomayukh Bhattacharjee
- Subjects
Engineering ,business.industry ,media_common.quotation_subject ,Mobile robot ,Perceptual performance ,Control and Systems Engineering ,Perception ,Frequency domain ,Psychophysics ,Computer vision ,Transparency (data compression) ,Sensitivity (control systems) ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,psychological phenomena and processes ,media_common ,Haptic technology - Abstract
This paper focuses on the human perception capabilities for haptic interaction with remote environments. The perception capabilities are compared for two well-known control methods with two kinds of haptic cues. Analytical and psychophysical methods are used to analyze the performance. The first control method aims at maximizing the transparency of the remote interactions (i.e., transparency-based method ), whereas the second one aims at maximizing the detection and discrimination abilities of the human operator (i.e., perception-based method ). For each of these two control methods, two kinds of haptic cues are studied, which use position and force cues from remote environments. Hybrid matrix formulation is employed, and it is analyzed in the frequency domain for these studies. Psychophysical experiments are then conducted for human-centered evaluation and comparison of the control methods. Analytical and experimental results clearly show that the perception-based method, when compared with the transparency-based method, enhances the human operator's perceptual capabilities of remote environments irrespective of force cues. For each of the two control methods, the force cues always contribute more to the increase in perceptual sensitivity when compared with the case of position cues.
- Published
- 2014
- Full Text
- View/download PDF
9. SURGERY PLANNING SIMULATION FOR CLOSED REDUCTION AND INTERNAL FIXATION
- Author
-
Doo Yong Lee and Hoeryong Jung
- Subjects
Engineering ,Engineering drawing ,business.industry ,medicine.medical_treatment ,Surgery planning ,General Medicine ,Cross section (geometry) ,Intersection ,medicine ,Internal fixation ,Computer vision ,Point (geometry) ,Femur ,Artificial intelligence ,business ,Projection (set theory) ,Reduction (orthopedic surgery) - Abstract
Careful planning of operations is critical to success of the closed reduction and internal fixation (CRIF) surgery to fix proximal femur fractures. This paper presents a novel surgery planning simulation for the CRIF. The developed simulation employs 3D femur model reconstructed from actual patient's CT data, and enables the user to make a plan on the model using 2D mouse. A projection scheme is developed to map a selected point on the monitor screen onto the 3D femur model. A centerline of the femur neck and cross section images are provided to help the user make optimal planning. The centerline of the femur neck is extracted by connecting two center points of cross sections selected by the surgeon. The cross section image is generated using intersection points between the femur model and a plane selected by the user. The simulation also displays post-operative appearance of the femur using 3D implants models.
- Published
- 2008
- Full Text
- View/download PDF
10. A psychophysical evaluation of haptic controllers: viscosity perception of soft environments
- Author
-
Doo Yong Lee, Hoeryong Jung, Heinrich H. Bülthoff, Jang Ho Cho, and Hyoung Il Son
- Subjects
Engineering ,genetic structures ,business.industry ,Just-noticeable difference ,General Mathematics ,Interface (computing) ,media_common.quotation_subject ,Absolute threshold ,behavioral disciplines and activities ,Computer Science Applications ,Control and Systems Engineering ,Viscosity (programming) ,Perception ,Teleoperation ,Computer vision ,Artificial intelligence ,Transparency (data compression) ,business ,Software ,Simulation ,Haptic technology ,media_common - Abstract
SUMMARYIn this paper, human viscosity perception in haptic teleoperation systems is thoroughly analyzed. An accurate perception of viscoelastic environmental properties such as viscosity is a critical ability in several contexts, such as telesurgery, telerehabilitation, telemedicine, and soft-tissue interaction. We study and compare the ability to perceive viscosity from the standpoint of detection and discrimination using several relevant control methods for the teleoperator. The perception-based method, which was proposed by the authors to enhance the operator's kinesthetic perception, is compared with the conventional transparency-based control method for the teleoperation system. The fidelity-based method, which is a primary method among perception-centered control schemes in teleoperation, is also studied. We also examine the necessity and impact of the remote-site force information for each of the methods. The comparison is based on a series of psychophysical experiments measuring absolute threshold and just noticeable difference for all conditions. The results clearly show that the perception-based method enhances both detection and discrimination abilities compare with other control methods. The results further show that the fidelity-based method confers a better discrimination ability than the transparency-based method, although this is not true with respect to detection ability. In addition, we show that force information improves viscosity detection for all control methods, as predicted from previous theoretical analysis, but improves the discrimination threshold only for the perception-based method.
- Published
- 2014
11. Design of a Haptic Interface for a Gastrointestinal Endoscopy Simulation
- Author
-
Doo Yong Lee, Sun Young Yi, In Sik Yu, Hyoung Il Son, Woojin Ahn, Hoeryong Jung, and Hyun Soo Woo
- Subjects
medicine.medical_specialty ,Endoscope ,Computer science ,Workspace ,behavioral disciplines and activities ,medicine ,Torque ,Computer vision ,Simulation ,Haptic technology ,ComputingMethodologies_COMPUTERGRAPHICS ,medicine.diagnostic_test ,business.industry ,Medical simulation ,Rotation around a fixed axis ,Computer Science Applications ,Endoscopy ,Human-Computer Interaction ,Mechanism (engineering) ,body regions ,Hardware and Architecture ,Control and Systems Engineering ,Artificial intelligence ,business ,Software ,psychological phenomena and processes - Abstract
This paper presents a new design and analysis of a haptic interface for a gastrointestinal endoscopy simulation. The gastrointestinal endoscopy is a procedure in which the digestive tract and organs of a patient are diagnosed and treated using a long and flexible endoscope. The developed haptic interface incorporates two degrees of freedom (DOF), each of which is necessary to describe the movements of an endoscope during the actual endoscopy procedures. The haptic interface has a translational motion mechanism to implement the insertion movement of the endoscope, and a rotational motion mechanism to implement the rotational movement of the endoscope. The endoscope included in the haptic interface is supported by a folding guide to prevent the endoscope from buckling. Force feedback in each direction is provided by wire-driven mechanisms. The developed haptic interface has a workspace, sensitivity, and maximum attainable force and torque enough to simulate the endoscopy procedures such as colonoscopy, upper GI (gastrointestinal) endoscopy, and endoscopic retrograde cholangiopancreatography (ERCP). The developed haptic interface is applied to implementation of a colonoscopy simulation. Performance including force bandwidth is evaluated through experiments and simulation.
- Published
- 2012
12. High Fidelity Haptic Rendering for Deformable Objects Undergoing Topology Changes
- Author
-
Stéphane Cotin, Doo Yong Lee, Hoeryong Jung, Christian Duriez, Jérémie Allard, Robotics and Simulation Laboratory (RSLab), Korea Advanced Institute of Science and Technology (KAIST), Simulation in Healthcare using Computer Research Advances (SHACRA), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Inria Nancy - Grand Est, and Institut National de Recherche en Informatique et en Automatique (Inria)
- Subjects
020205 medical informatics ,Computer science ,Computation ,medicine.medical_treatment ,02 engineering and technology ,Haptic rendering ,Topology ,biomechanics ,Contact force ,surgery ,High fidelity ,haptics ,0202 electrical engineering, electronic engineering, information engineering ,medicine ,Computer vision ,Relevance (information retrieval) ,cutting ,Simulation ,Topology (chemistry) ,Haptic technology ,business.industry ,020207 software engineering ,Microsurgery ,simulation ,[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] ,sense organs ,Artificial intelligence ,business ,soft tissue - Abstract
International audience; The relevance of haptic feedback for minimally invasive surgery has been demonstrated at numerous counts. However, the proposed methods often prove inadequate to handle correct contact computation during the complex interactions or topological changes that can be found in surgical interventions. In this paper, we introduce an approach that allows for accurate computation of contact forces even in the presence of topological changes due to the simulation of soft tissue cutting. We illustrate this approach with a simulation of cataract surgery, a typical example of microsurgery.
- Published
- 2010
- Full Text
- View/download PDF
13. Real-time simulation of dynamic fluoroscopy of ERCP
- Author
-
Doo Yong Lee and Hoeryong Jung
- Subjects
medicine.diagnostic_test ,Computer science ,Fluoroscope ,business.industry ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Volume rendering ,Rendering (computer graphics) ,Endoscopy ,Real-time simulation ,Computer Science::Computer Vision and Pattern Recognition ,Computer graphics (images) ,Fluid dynamics ,medicine ,Fluoroscopy ,Computer vision ,Artificial intelligence ,business - Abstract
This paper discusses the methods for real-time rendering of time-varying dynamic fluoroscope images including fluid flow for the ERCP (Endoscopic Retrograde Cholangiopancreatography) simulation. A volume rendering technique is used to generate virtual fluoroscopy images. This paper develops an image-overlaying method which overlaps the timevarying images onto the constant background image. The full size fluoroscopy image is computed from the initial volume data set during the pre-processing stage, which is then saved as the background image. Only the time-varying images are computed from the time-varying volume data set during the actual simulation. This involves relatively small computation compared with the background image. The time-varying images are then overlaid onto the background image to obtain the complete images. This method reduces computational overhead by removing redundant computations. A simplified particle dynamics model is employed for fast simulation of the fluid flow. The fluid model, a collection of particles, interacts only with the ducts based on principles of a complete elastic collision. Hence, the velocity of the particles, when they collide with the duct, can be computed by using simple algebraic equations. The methods are implemented for fast simulation of the ERCP.
- Published
- 2010
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.