• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.3
• /
• pp.165-178
• /
• 2007

The recent progress in multimedia signal processing and transmission technologies has contributed to the extensive use of multimedia devices to watch sports games with small LCD panel. However, the most of video sequences are captured for normal viewing on standard TV or HDTV, for cost reasons, merely resized and delivered without additional editing. This may give the small-display-viewers uncomfortable experiences in understanding what is happening in a scene. For instance, in a soccer video sequence taken by a long-shot camera techniques, the tiny objects (e.g., soccer ball and players) may not be clearly viewed on the small LCD panel. Moreover, it is also difficult to recognize the contents of the scorebox which contains the elapsed time and scores. This renuires intelligent display technique to provide small-display-viewers with better experience. To this end, one of the key technologies is to determine region of interest (ROI) and display the magnified ROI on the screen, where ROI is a part of the scene that viewers pay more attention to than other regions. Examples include a region surrounding a ball in long-shot and a scorebox located in the comer of each frame. In this paper, we propose a scheme for raising viewing experiences of multimedia mobile device users. Instead of taking generic approaches utilizing visually salient features for extraction of ROI in a scene, we take domain-specific approach to exploit unique attributes of the soccer video. The proposed scheme consists of two modules: ROI determination and scorebox extraction. The experimental results show that the proposed scheme offers useful tools for intelligent video display on multimedia mobile devices.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.8 no.2
• /
• pp.31-43
• /
• 2002

The subjects of this study were 15 woman soccer players and 15 untrained woman students at H-Cheju University. Each subject was measured on the muscle strength and peak torque of knee extensors and knee flexors with isokinetic load ($60^{\circ}$/sec, $180^{\circ}$/sec). The results were as follows: 1. There was no significant difference between right and left leg strength measured isokinetically in each group. 2. The peak torque of knee extensors and flexors was significantly higher in scoccer players than untrainded students (p<0.001). 3. For the angle of knee joint showing the highest peak torque, there was significant difference between soccer players and untrained students in knee extensors(p<0.05) and right flexors (p<0.01). 4. For knee H/Q ratio, there was significant difference between two groups(p<0.05). 5. For the total work and average power at $180^{\circ}$/sec, there was significant difference between two groups in knee extensors(p<0.001) and flexors(p<0.01). 6. In soccer players at $60^{\circ}$/sec, there were significant correlations between peak torque and height and between peak torque and weight.(p<0.001). 7. For the muscular contraction velocity at $60^{\circ}$/sec, there was significant difference between two groups in flexors (p<0.01). 8. For the muscular indurance at $180^{\circ}$/sec in extensors and flexors, there was no significant difference between two groups(p<0.05). In conclusion, there were significantly higher in peak torque, contraction velocity, knee joint's angle with the highest peak torque, H/Q ratio, total work and average power in woman scoccer player than general students. But there was no significant difference in muscular endurance. Soccer performance is based on the various components including muscular endurance that is one of the most important components. So it is necessary that the training method to improve the various components (especially including muscular endurance) should be done.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.51-59
• /
• 1999

In this paper we propose the technique for tracking players and a ball and for obtaining players' ground traces using image mosaic in general soccer sequences. Here, general soccer sequences mean the case that there is no extreme zoom-in or zoom-out of TV camera. Obtaining player's ground traces requires that the following three main problems be solved. There main problems: (1) ground field extraction (2) player and ball tracking and team indentification (3) player positioning. The region of ground field is extracted on the basis of color information. Players are tracked by template matching and Kalman filtering. Occlusion reasoning between overlapped players in done by color histogram back-projection. To find the location of a player, a ground model is constructed and transformation between the input images and the field model is computed using four or more feature points. But, when feature points extracted are insufficient, image-based mosaic technique is applied. By this image-to-model transformation, the traces of players on the ground model can be determined. We tested our method on real TV soccer sequence and the experimental results are given.

• Korean Journal of Applied Biomechanics
• /
• v.22 no.3
• /
• pp.349-356
• /
• 2012

This study aimed to assess the effects of progressive lumbar stability exercises and lumbar stability exercises on changes in the transversus abdominis muscle thickness and lower extremity muscle fatigue index in soccer players. Ten subjects were assigned to undergo training in each of the 2 groups, namely, the progressive lumbar stability exercise group and lumbar stability exercise group. Each intervention session lasted for 30 min, and 4 sessions were conducted in a week for 6 weeks for soccer players of S. University in Jeonnam, Korea. Changes in the transversus abdominis muscle thickness and lower extremity muscle fatigue index were measured using ultrasound and surface electromyogram. The results of the ultrasound measurement for the transversus abdominis muscle thickness indicated that progressive lumbar stability exercises were more effective than lumbar stability exercises. The results of the lower extremity muscle fatigue index measurements using surface electromyogram indicated that the fatigue index decreased in the progressive lumbar stability exercise group. Progressive lumbar stability exercise is believed to have put more workload during the shaking of the limbs, leading to increased stability and increased efficiency of the lower extremity muscle, thereby decreasing the fatigue index. Therefore, progressive lumbar stability exercises can be an effective measure for preventing injuries and improving the game performance of sports players by increasing the transversus abdominis muscle thickness and decreasing the lower extremity muscle fatigue index.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.33-36
• /
• 2000

To create a more realistic soccer game derived from TV images, we are developing an image synthesis system that generates 3D image sequence from TV images. We propose the method for the team and the pose recognition of players in TV images. The representation includes camera calibration method, team recognition method and pose recognition method. To find the location of a player on the field, a field model is constructed and a player's field position is transformed by 4-feature points. To recognize the team information of players, we compute RGB mean values and standard deviations of a player in TV images. Finally, to recognize pose of a player, this system computes the velocity and the ratio of player(height/width). Experimental results are included to evaluate the performance of the team and the pose recognition.

• Journal of the Korean housing association
• /
• v.16 no.3
• /
• pp.109-117
• /
• 2005

The purpose of this study is to suggest a basic data of playground design that can arouse various curiosities and interests of children. The 13play areas 'A' kindergartem's playground that parent, music, play equipment, soccer field, water, sand, tunnel, maze, animal, plant, ground hill, bike road, and inner court were evaluated by 16 teachers and 165 children between the age of 4 and 5. POE data of teachers were collected by questionnaire. And children chose and rated very fun and interesting 5 play areas of 13 ones based on the photos. The results were as following. 1) 13 play areas were generally used evenly with diverse purpose. 2) the environment of the play areas was deemed very appropriate. 3) maze area and play equipment area were recognized as the most favored play areas by children. 4) teachers recommended soccer field, plants, maze, tunnel, music area as the most favorable play areas.

• Journal of the Korean Society of Industry Convergence
• /
• v.5 no.3
• /
• pp.269-275
• /
• 2002

The purpose of this study is to examine the effect of the acute aerobic and anaerobic exercise on immune response. Fourteen university soccer players are sampled and divided into two groups -- one group of seven for aerobic exercise, the other for anaerobic exercise. The one group of aerobic exercise went through the Graded Exercise Test of Bruce protocol, using Treadmill, and were driven to be all-out ; the other of anaerobic exercise took the Wingate Test. Blood the respective periods of rest, post exercise, and recovery for ten minutes. The results are as follows. (1) The acute aerobic and anaerobic exercise don't affect monocyte and granulocyte. (2) The change in lymphocyte and NK cell resulting from the acute aerobic and anaerobic exercise shows a significant differences in the three different periods, but not significant differences between the two groups.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.92.4-92
• /
• 2002

In this paper, as an ideal test bed for studies on multi-agent system, the multiple micro robot soccer playing system is introduced at first. The construction of such experimental system has involved lots of kinds of challenges such as sensors fusing, robot designing, vision processing, motion controlling, and especially the cooperation planning of those robots. So in this paper we want to stress emphasis on how to evolve the system automatically based on the model of behavior-based learning in multi-agent domain. At first we present such model in common sense and then apply it to the realistic experimental system . At last we will give some results showing that the proposed approach is feasi...

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.292-297
• /
• 1999

Evolving in artificial agent is an extremely difficult problem, but on the other hand, a challenging task. At present the studies mainly centered on single agent learning problem. In our case, we use simulated soccer to investigate multi-agent cooperative learning. Consider the fundamental differences in learning mechanism, existing reinforcement learning algorithms can be roughly classified into two types-that based on evaluation functions and that of searching policy space directly. Genetic Programming developed from Genetic Algorithms is one of the most well known approaches belonging to the latter. In this paper, we give detailed algorithm description as well as data construction that are necessary for learning single agent strategies at first. In following step moreover, we will extend developed methods into multiple robot domains. game. We investigate and contrast two different methods-simple team learning and sub-group loaming and conclude the paper with some experimental results.