tags: CoachAI IJCAI-PRICAI 2020

IJCAI-PRICAI 2020 Tutorial: Video-based Data Collection for Sports Tactical Analysis

Tsì-Uí İk and Wen-Chih Peng
Department of Computer Science
College of Comoputer Science
National Chiao Tung University
1001 University Road, Hsinchu City 30010, Taiwan

SlideShare

{Link Here}

Abstract

Sports match video keeps most information in the games. In this talk, taking badminton as an example, we will introduce how deep learning and machine learning can help in the collection of microscopic data from sports match video. In addition, some interesting results of tactical analysis will be given.

Introdcution

Sports activities entertain people and play an import role in our daily life. For professional athletes, pre-match strategic analysis may bring information to break opponent's tactics and be the key to win the tight games. In this talk, taking badminton as an example, we will introduce how deep learning and machine learning can help in sports tactical analysis.
To enable tactical analysis, data collection is a prerequisite. Since video keep rich visual information, it is considered as the log of video sensors and can help in data collection. First of all, we will survey techniques of computer vision, deep learning, and machine learning that can be used to extract microscopic data from video for tactical analysis. The techniques including homography mapping, tiny object tracking, human skeleton detection, depth map prediction, etc. will be covered.
The second topic is tactical analysis. Statistic methods will be used to reveal overall information. Pattern discovery algorithms will be used to find the ball usage pattern. Spatial analysis will be used to understand the mobility of athletes. Visualization techniques will be applied to help in data mining and effective communication between athletes and their coaches.

What Will Be Covered?

• Computer vision for sports applications
• Tracking high speed and tiny objects from broadcast video
• Deep learning networks for human skeleton detection and depth map prediction
• What is shot-by-shot microscopic data?
• Tools for labeling shot-by-shot microscopic data
• Ball type classification
• Analysis of running speed
• Analysis of ball usage patterns

Potential Audience

• People who are interested in the applications of computer vision, deep learning, and machine learning.
• People who are interested in video-based data collection.
• People who are interested in sports tactical analysis.
• People who want to develop video labeling tools.

Sports Big Data –- The Power of Data

Money Ball

Data Collection Technologies

Shot-by-Shot Microscopic Data

Body Sensor Networks

Hawk-Eye

Computer Vision –- Cameras as Video Sensors

Deep Learning

Technical Aspects

Object Detection

Human Skeleton

Positioning

Tracking

Open Dataset

CoachAI

Data Collection

Strategic Analysis

Training Devices

Demo

About Presenters

This tutorial will be given by Prof. Tsi-Ui Ik and Prof. Wen-Chih Peng both from Department of Computer Science, National Chiao Tung University, Taiwan. More information is given below.

Dr. Tsì-Uí İk, Professor

Dr. Tsì-Uí İk received his Ph.D. degree in Computer Science from the Illinois Institute of Technology in 2005, and B.S. degree in Mathematics and M.S. degrees in Computer Science and Information Engineering from the National Taiwan University in 1991 and 1993, respectively. He is currently a Professor with the Department of Computer Science, the Director of the Institute of Computer Science and Engineering, and the Associate Dean of the College of Computer Science, National Chiao Tung University. He is a member of the IEEE. He had been a Senior Research Fellow of the Department of Computer Science, City University of Hong Kong. He was bestowed the Outstanding Young Engineer Award by the Chinese Institute of Engineers in 2009, and the Young Scholar Best Paper Award by IEEE IT/COMSOC Taipei/Tainan Chapter in 2010. He received the Best Paper Award at ITST 2012. He received the 3-year Outstanding Young Researcher Grant from the National Science Council, Taiwan in 2012. His research focuses on intelligent applications, such as intelligent sports learning and intelligent transportation systems, mobile sensing, machine learning, deep learning, and wireless sensor and ad hoc networks.

Dr. Wen-Chih Peng, Professor

Wen-Chih Peng received the BS and MS degrees from the National Chiao Tung University, Taiwan, in 1995 and 1997, respectively, and the Ph.D. degree in Electrical Engineering from the National Taiwan University, Taiwan, R.O.C in 2001. Currently, he is a professor and the chairman of the department of computer science, National Chiao Tung University, Taiwan. Prior to joining the department of Computer Science, National Chiao Tung University, he was mainly involved in the projects related to mobile computing, data broadcasting and network data management. Dr. Peng published some papers in several prestigious conferences, such as ACM Conference on Knowledge Discovery and Data Mining (ACM KDD), IEEE International Conference on Data Mining (ICDM), ACM Conference on Management of Data (ACM SIGMOD) and ACM Conference on Information and Knowledge Management (ACM CIKM) and prestigious journals (e.g., IEEE TKDE, IEEE TMC, The VLDB Journal, and IEEE TPDS). Dr. Peng has the best paper award in ACM Workshop on location-based social network 2009 and the best student paper award in IEEE International Conference on Mobile Data Management 2011. His research interests include mobile data management, sensor data management and data mining. He is a member of IEEE.

Reference

1. Y.-C. Huang, I-N. Liao, C.-H. Chen, T.-U. İk, and W.-C. Peng, "TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications," in the 1st IEEE International Workshop of Content-Aware Video Analysis (CAVA 2019) in conjunction with the 16th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS 2019), 18-21 September 2019, Taipei, Taiwan.
2. T.-H. Hsu, C.-H. Chen, N. P. Ju, T.-U. İk, W.-C. Peng, C.-C. Wang, Y.-S. Wang, Y.-H. Lin, Y.-C. Tseng, J.-L. Huang, and Y.-T. Ching, "CoachAI: A Project for Microscopic Badminton Match Data Collection and Tactical Analysis," in the 20th Asia-Pacific Network Operations and Management Symposium (APNOMS 2019), 18-20 September 2019, Matsue, Japan.
3. S. I. Soraya, S.-P. Chuang, Y.-C. Tseng, T.-U. İk, and Y.-T. Ching, "A Comprehensive Multisensor Dataset Employing RGBD Camera, Inertial Sensor and Web Camera," in the 20th Asia-Pacific Network Operations and Management Symposium (APNOMS 2019), 18-20 September 2019, Matsue, Japan.
4. J. Lin, C.-W. Chang, C.-H. Wang, H.-C. Chi, C.-W. Yi, Y.-C. Tseng, and C.-C. Wang, "Design and Implement a Mobile Badminton Stroke Classification System," in the 19th Asia-Pacific Network Operations and Management Symposium (APNOMS 2017), pp.235-238, 27-29 September 2017, Seoul, Korea.
5. Y.-C. Huang, C.-W. Yi, W.-C. Peng, H.-C. Lin, and C.-Y. Huang, "A Study on Multiple Wearable Sensors for Activity Recognition," in the 2017 IEEE Conference on Dependable and Secure Computing (DSC 2017), pp. 449-453, 7-10 August 2017, Taipei, Taiwan.
6. S. I. Soraya, T.-H. Chiang, G.-J. Chan, Y.-J. Su, C.-W. Yi, Y.-C. Tseng, and Y.-T. Ching, "IoT/M2M Wearable-based Activity-calorie Monitoring and Analysis for Elders," in the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS 2017), pp. 2390-2393, 11-15 July 2017, Jeju Island, Korea.
7. G.-J. Chan, D.-H. Lin, C.-W. Yi, and C.-C. Tseng, "A Two-layer Hierarchical Framework for Activity Sequence Recognition by Wearable Sensors," in the 18th Asia-Pacific Network Operations and Management Symposium (APNOMS 2016), Kanazawa, Japan, 5-7 October 2016.
8. H.-H. Tsai and C.-W. Yi, "Wearable ECG for tension assessment in movie watching and adventure riding," in the 11th IEEE International Conference on Mobile Ad-hoc and Sensor Networks (IEEE MSN 2015), Shenzhen, China, 16-18 December 2015.
9. H.-H. Tsai, Y.-T. Chuang, C.-W. Yi, and Y.-C. Wang, "A Study on Wearable Electrocardiograph," in the IEEE 10th International Conference on Intelligent Sensors, Sensor Networks and Information Processing (IEEE ISSNIP 2015), Singapore, 7-9 April 2015.
10. Y.-C. Huang, T.-L. Chen, B.-C. Chiu, C.-W. Yi, C.-W. Lin, Y.-J. Yeh, and L.-C. Kuo, "Calculate golf swing trajectories from IMU sensing data," in Proceedings of the 41st International Conference on Parallel Processing Workshops (ICPPW 2012), pp. 505-513, Pittsburgh, PA, USA, 10-13 September 2012.
11. P.-L. Shih, P.-J. Chiu, Y.-C. Cheng, J.-Y. Lin, and C.-W. Yi, "Energy-aware pedestrian trajectory system," in Proceedings of the 41st International Conference on Parallel Processing Workshops (ICPPW 2012), pp. 514-523, Pittsburgh, PA, USA, 10-13 September 2012.
12. C.-M. Su, J.-W. Chou, C.-W. Yi, Y.-C. Tseng, and C.-H. Tsai, "Sensor-aided personal navigation systems for handheld devices," in Proceedings of the 39th International Conference on Parallel Processing Workshops (ICPPW 2010), pp. 533-541, San Diego, CA, USA, 16 September 2010.