• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.567-571
• /
• 2009

Sports game broadcasting system uses multiple video cameras in order to offer exciting and dynamic scenes for the TV audiences. Since, however, the traditional broadcasting system edits the multiple views into a static video stream, it is difficult to provide the intelligent broadcasting service that summarizes or retrieves specific scenes or events based on the user preference. In this paper, we propose the summarization and retrieval system for the soccer videos based on multiple cameras. It extracts the highlights such as shot on goal, crossing, foul, and set piece using dynamic Bayesian network based on soccer players' primitive behaviors annotated on videos, and selects a proper view for each highlight according to its type. The proposed system, therefore, offers users the highlight summarization or preferred view selection, and can provide personalized broadcasting services by considering the user's preference.

• The KIPS Transactions:PartA
• /
• v.16A no.5
• /
• pp.389-394
• /
• 2009

Lately the usage of multimedia equipment with small LCD displays is rapidly increasing. Although many people use devices like this, videos intended for TV or HDTV are sent to these mobile devices. Therefore cases where it is hard for the user to view the desired scenes are growing more frequent. Currently, most services simply reduce the size of the content to fit the screen when they offer it for mobile devices. However, especially with sports broadcasts, there are many areas that cannot be seen very well because it was simply reduced in size. We therefore consider this weakness and are researching how to let the user choose an area of interest and then sending it to the user in a way that fits the device. In this paper, we address the problem of video delivery and personalization. For the delivered video content, we suggest the UP-SAM User Personalized Context-Aware Service Adaptation Middleware) model that uses the video content description and MPEG-21 multimedia framework.

• 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.

• Journal of Digital Convergence
• /
• v.19 no.1
• /
• pp.421-430
• /
• 2021

The study was conducted to examine the educational experiences and perceptions of college students in the field of physical education as they were taken remote classes in university due to the effects of the social collective infection caused by COVID-19. To achieve the purpose of the study, an online survey was conducted on 278 university students who major in physical education, and the survey questions include the status of remote classes, remote class recognition (preference, and satisfaction level). As for the analysis method, frequency analysis, response sample t-verification, ANOVA, and word-cradle were performed using SPSS 22.0 and R programs, and all significance levels were set at .05. The results from the above research process are as follows. First, in the types of remote classes in the sports category due to COVID-19, video types were used the most in both theoretical and practical classes, and the following was shown as assignment types. The third type was the voice record lecture type for theoretical classes, and the practical class was the video lecture scene. Second, in the remote class preference for the students, both theory and practical classes, video format were the most prefered, followed by video lecture scene and voice lecture type. Third, the analysis of the differences in satisfaction between theoretical and practical classes of the students showed that there was no difference in satisfaction according to the type of class.

• Journal of the Korean Society for Computer Game
• /
• v.31 no.4
• /
• pp.61-70
• /
• 2018

In this paper, we propose a synchronized playback method of 3D reference model and video by extracting golf swing information from learner's golf video to precisely compare and analyze each motion in each position and time in the golf swing, and present the implementation result. In order to synchronize the 3D model with the learner's swing video, the learner's golf swing movie is first photographed and relative time information is extracted from the photographed video according to the position of the golf club from the address posture to the finishing posture. Through applying time information from learners' swing video to a 3D reference model that rigs the motion information of a pro-golfer's captured swing motion at 120 frames per second through high-quality motion capture equipment into a 3D model and by synchronizing the 3D reference model with the learner's swing video, the learner can correct or learn his / her posture by precisely comparing his or her posture with the reference model at each position of the golf swing. Synchronized playback can be used to improve the functionality of manually adjusting system for comparing and analyzing the reference model and learner's golf swing. Except for the part where the image processing technology that detects each position of the golf posture is applied, It is expected that the method of automatically extracting the time information of each location from the video and of synchronized playback can be extended to general life sports field.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.283-292
• /
• 2018

UHD (Ultra High Definition) broadcasting technology, and UWV (Ultra Wide Vision) which is the high quality panoramic video of wide view angle based on UHD, were commercialized in Korea for the first time in the world, and those are representative realistic video technologies that maximize the user's sense of presence. By comparing the user's subjective reaction of UHD and UWV, the purpose of this study is to systematically establish the user's subjective video quality evaluation. For this purpose, a large screen projection experiment is designed by setting the screen size (4k x 2k, 8k x 2k) and content types (sports, landscape, concert) as variables to measure the user's subjective video quality evaluation and satisfaction. As a result of the study, the users' evaluation of UWV was higher than UHD in all items of subjective video quality, and satisfaction. Moreover, the results showed the significant differences depending on the video contents. Based on the results of the research, the study proposed the points necessary for the development and commercialization of UWV panoramic technology, and suggestions for the future research.

• Korean Journal of Applied Biomechanics
• /
• v.24 no.1
• /
• pp.11-18
• /
• 2014

The purposes of this study were to analyze the kinematics and electromyographic variables of the upper extremity for the backhand clear motion according to the type of hitting in badminton. Seven elite male university players were selected as the subjects. Four digital video cameras and Noraxon Telemyo 2400 were used to collect the 3D kinematics and electromyographic data. The results were as follows: 1) in the phase of impact, the time of motion for the overhead backhand clear was the longest, 2) in the event of impact, the distance of step toward X direction was the longest and the distance of step toward Y direction was the shortest for the overhead backhand clear, 3) in the event of backswing, the rotation angles of shoulder and pelvis and the flexion angle of shoulder for the overhead backhand clear were the biggest, 4) the maximum flexion angular velocity of shoulder and the maximum extension angular velocity of elbow for the overhead backhand clear were the biggest, and 5) in the phase of impact, mean EMG of the wrist flexor, triceps, and trapezius muscle for the overhead backhand clear was bigger than that for the underhand stroke and in the phase of follow-through, mean EMG of the wrist flexor and extensor, biceps, triceps, and trapezius muscle for the overhead backhand clear was the biggest.

• Korean Journal of Applied Biomechanics
• /
• v.20 no.3
• /
• pp.293-301
• /
• 2010

The purpose of this study was to investigate the kinematic difference between skilled and less skilled group for the forward walk at dance sports rumba. Six female players(skilled group: 3, less skilled group: 3) were participated as the subjects. To obtain the three-dimensional location coordinates in the joints and segments, it shot with 100Hz/s using 8 video cameras. Step length, shoulder rotation angle, orientation angle and angular velocity of pelvis were analyzed for each trail. The skilled group showed a bigger movement than the less skilled group at the shoulder rotation angle and ROM. The skilled group showed a bigger movement than the less skilled group at the up/down obliquity and internal/external rotation movement for pelvis. And the skilled group showed a bigger movement than the less skilled group at Maximum angle (down obliquity) of P2 and Maximum angle (up obliquity) of P3 to pelvis ROM. The skilled group showed a faster angular velocity than the less skilled group at P2 (+ direction, posterior) of anterior & posterior tilt, P2 & P3 (- direction, up) of up & down obliquity, and P2 (+ direction, external) of internal & external rotation.

• Journal of Fashion Business
• /
• v.22 no.6
• /
• pp.53-69
• /
• 2018

In recent years, digital media providing entertainment and information have become an important channel of customer experience. The aim of this study is to evaluate the effects of digital signage's characteristics on flow and brand attitudes and to verify the mediating role of pleasure in digital signage and flow. The stimuli were developed for a sports brand stores using 3D and video editing software. The survey was conducted on 544 subjects from both gender aged 20 to 49 years old, i.e. the population that constitutes the major target group for sports brands. The data collected was analyzed using IBM SPSS 24.0. Specifically, frequency analysis, factor analysis, reliability analysis, t-test, and regression analysis were performed on the data. Based on the results, we can draw the following conclusions; First, the dimension of digital signage was classified into aesthetic and functional attributes. Additionally, we found out that women highly value aesthetic attributes of digital signage while the customers in their 40s pay more attention to functional attributes than their counterparts aged 20-30 years. Second, our results suggest that pleasure has a mediating effect in the relationship between digital signage attributes and flow; specifically, both sub-dimensions of digital signage features (aesthetic attributes and functional attributes) affect flow by means of pleasure. Third, our results demonstrated that the flow of digital signage had a significant impact on brand attitudes.

• Journal of IKEEE
• /
• v.3 no.1 s.4
• /
• pp.93-100
• /
• 1999

When providing MPEG-2 video service through the ATM network, the degradation of QoS caused by cell losses and cell errors occuring from ATM netwok was assessed by the end-users subjectively and then the relation between CLR, CER and subjective QoS of MPEG-2 video was analyzed. Cell losses and cell errors occuring from the ATM network were generated according to the normal and exponential distribution by NEM module. Video sources were divided into sports and drama by moving feature and were tested. The results of our experiments show that the excellent quality of subjective QoS grade 5 was achieved for a cell loss rate of $2{\times}10^{-7}$ and for a cell error rate of $2{\times}10^{-7}$ and the good quality of subjective QoS grade 4 was achieved for a cell loss rate of $2{\times}10^{-6}$ and for a cell error rate of $2{\times}10^{-6}$ When providing MPEC-2 video service through the ATM network, the results of our experiments will be used as valuable information to determine the network performance objectives for satisfying the QoS required by the end-users and to design the network.