• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.619-628
• /
• 2011

Normally vision-based 3D human pose recognition technology is used to method for convey human gesture in HCI(Human-Computer Interaction). 2D pose model based recognition method recognizes simple 2D human pose in particular environment. On the other hand, 3D pose model which describes 3D human body skeletal structure can recognize more complex 3D pose than 2D pose model in because it can use joint angle and shape information of body part. In this paper, we describe a development of interactive game contents using pose recognition interface that using 3D human body joint information. Our system was proposed for the purpose that users can control the game contents with body motion without any additional equipment. Poses are recognized comparing current input pose and predefined pose template which is consist of 14 human body joint 3D information. We implement the game contents with the our pose recognition system and make sure about the efficiency of our proposed system. In the future, we will improve the system that can be recognized poses in various environments robustly.

• Journal of Convergence for Information Technology
• /
• v.7 no.3
• /
• pp.73-81
• /
• 2017

The generalized Hough transform (GHough) is a useful technique for detecting and locating 2-D model. However, GHough requires a 4-D parameter array and a large amount of time to detect objects of unknown scale and orientation because it enumerates all possible parameter values into a 4-D parameter space. Several n-to-1 mapping algorithms were proposed to reduce the parameter space from 4-D to 2-D. However, these algorithms are very likely to fail due to the random votes cast into the 2-D parameter space. This paper proposes to use internal gradient information in addition to the model boundary points to reduce the number of random votes cast into 2-D parameter space. Experimental result shows that our proposed method can reduce both the number of random votes cast into the parameter space and the execution time effectively.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.4
• /
• pp.356-367
• /
• 2014

A robotic sapatial augmented reality (RSAR) system, which combines robotic components with projector-based AR technique, is unique in its ability to expand the user interaction area by dynamically changing the position and orientation of a projector-camera unit (PCU). For a moving PCU mounted on a conventional robotic device, we can compute its extrinsic parameters using a robot kinematics method assuming a link and joint geometry is available. In a RSAR system based on user-created robot (UCR), however, it is difficult to calibrate or measure the geometric configuration, which limits to apply a conventional kinematics method. In this paper, we propose a data-driven kinematics control method for a UCR-based RSAR system. The proposed method utilized a pre-sampled data set of camera calibration acquired at sufficient instances of kinematics configurations in fixed joint domains. Then, the sampled set is compactly represented as a set of B-spline surfaces. The proposed method have merits in two folds. First, it does not require any kinematics model such as a link length or joint orientation. Secondly, the computation is simple since it just evaluates a several polynomials rather than relying on Jacobian computation. We describe the proposed method and demonstrates the results for an experimental RSAR system with a PCU on a simple pan-tilt arm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2018

Recently, the convolutional neural network shows high performance in many computer vision tasks. However, convolutional neural networks require enormous amount of operation, so it is difficult to adopt them in the embedded environments. To solve this problem, many studies are performed on the ASIC or FPGA implementation, where an efficient representation method is required. The fixed-point representation is adequate for the ASIC or FPGA implementation but causes a performance degradation. This paper proposes a separate optimization of representations for the convolutional layers and the batch normalization layers. With the proposed method, the required bit width for the convolutional layers is reduced from 16 bits to 10 bits for the ResNet-50 neural network. Since the computation amount of the convolutional layers occupies the most of the entire computation, the bit width reduction in the convolutional layers enables the efficient implementation of the convolutional neural networks.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.108-118
• /
• 2013

Recently the 3D modeling techniques were developed rapidly due to rapid development of computer vision, computer graphics with the excellent performance of hardware. With the advent of a variety of 3D contents, 3D modeling technology becomes more in demand and it's quality is increased. 3D face models can be applied widely to such contents with high usability. In this paper, a 3D face modeling is attempted from a given single 2D frontal face image. To achieve the goal, we thereafter the feature points using AAM are extracted from the input frontal face image. With the extracted feature points we deform the 3D general model by 2-pass mesh warping, and also the depth extraction based on intensity values is attempted to. Throughout those processes, a universal 3D face modeling method with less expense and less restrictions to application environment was implemented and it's validity was shown through experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.9
• /
• pp.109-117
• /
• 2019

This study was attempted to provide fundamental data in a disaster response education program by comparing the differences between students of the paramedic and nursing in ego-resilience, disaster-experience and core competencies of disaster response. The data is collected from March 2 to April 2, 2019, on a total of 358 students (196 paramedic students and 162 nursing students) based in Jeolla Province. The structured questionnaire were used as research tools and the collected data were analyzed by using the SPSS program as frequency, percentage, t-test, ANOVA and Pearson's correlation coefficient. The average score of total ego-resilience among the subjects was 86.97 out of 125 points. The number of paramedic students who experienced or witnessed the disaster situation in person was 11.2%, and the number of nursing students was 11.7%. The core competence of disaster response was 3.21% in paramedic students and 3.16% in nursing students. The ego-resilience of the paramedic and nursing students according to their general characteristics is statistically significant differences (t=2.797, p<.005) and the paramedic students has an average score of 3.52 points, which is higher than the nursing students (3.42 points). General characteristics and experience in disasters are statistically significant differences (t=2.797, p<.005), paramedic students had more disaster experiences (3.11 points) than nursing students (2.67 points). It indicated the static correlation relationship between ego-resilience, disaster experience and core competences of disaster response (p<.000). Through this study, the paramedic students were found to be more ego-resilience, more disaster experience and more critical capacity for disaster treatment than nursing students.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.201-210
• /
• 2021

This paper introduces the futsal video analysis system consisting of an analysis program using object tracking technology and a web server that visualizes and provides analyzed data. In this paper, small and medium-sized organizations and amateur players are unable to provide game analysis services, so they propose a system that can solve this problem through this paper. Existing analytical systems use special devices or high-cost cameras, making them difficult for users to use. Thus, in this paper, a system is designed and developed to analyze the competitors' competitions and visualize the data using flat images only. Track an object and calculate the accumulated values to obtain the distance per pixel of the object and extract speed-related data and distance-based data based on it. Converts extracted data to graphs and images through a visualization library, making it convenient to use through web pages. Through this analysis system, we improve the problems of the existing analysis system and make data-based scientific and efficient analysis available.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.81-87
• /
• 2021

Artificial intelligence technology is developing as it enters the fourth industrial revolution. Active researches are going on; visual-based models using CNNs. U-net is one of the visual-based models. It has shown strong performance for semantic segmentation. Although various U-net studies have been conducted, studies on tracking objects with unclear outlines such as gases and smokes are still insufficient. We conducted a U-net study to tackle this limitation. In this paper, we describe how 3D cameras are used to collect data. The data are organized into learning and test sets. This paper also describes how U-net is applied and how the results is validated.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.563-570
• /
• 2024

This paper proposes a method to recognize and track drivable lane areas to assist the driver. The main topic is designing a deep-based network that predicts drivable road areas using computer vision and deep learning technology based on images acquired in real time through a camera installed in the center of the windshield inside the vehicle. This study aims to develop a new model trained with data directly obtained from cameras using the YOLO algorithm. It is expected to play a role in assisting the driver's driving by visualizing the exact location of the vehicle on the actual road consistent with the actual image and displaying and tracking the drivable lane area. As a result of the experiment, it was possible to track the drivable road area in most cases, but in bad weather such as heavy rain at night, there were cases where lanes were not accurately recognized, so improvement in model performance is needed to solve this problem.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.563-572
• /
• 2024

Image processing and computer vision technologies are becoming increasingly important in a variety of application fields that require techniques and tools for sophisticated image analysis. In particular, image segmentation is a technology that plays an important role in image analysis. In this study, in order to identify recent research trends on image segmentation techniques, we used the Web of Science(WoS) database to analyze the R&D topography based on the network structure of the author's keyword co-occurrence matrix. As a result, from 2015 to 2023, as a result of the analysis of the R&D map of research articles on image segmentation, R&D in this field is largely focused on four areas of research and development: (1) researches on collecting and preprocessing image data to build higher-performance image segmentation models, (2) the researches on image segmentation using statistics-based models or machine learning algorithms, (3) the researches on image segmentation for medical image analysis, and (4) deep learning-based image segmentation-related R&D. The scientometrics-based analysis performed in this study can not only map the trajectory of R&D related to image segmentation, but can also serve as a marker for future exploration in this dynamic field.