Sensor-based stroke detection and stroke type classification in table tennis

Blank, Peter; Hoßbach, Julian; Schuldhaus, Dominik; Eskofier, Bjoern M.

doi:10.1145/2802083.2802087

Cited by 79 publications

(43 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Ref., [20] a single IMU sensor is attached to the front end of a table tennis racket handle to detect and classify various stroke types (drive, push, block and topspin for both forehand and backhand) among amateur and professional players. Kinematic data of acceleration and angular velocity are collected to detect stroke events and classify basic stroke types using pattern recognition algorithms.…”

Section: Performance Monitoring In Sportsmentioning

confidence: 99%

“…Inter-arm coordination slope change detection using CUSUM, orientation estimation and peak detection [18] 3D orientation of left and right skies, Initial sensor calibration; Initial rest vector, gravity vector alignment Angle of attack Descent trajectory, rotation vector alignment; Quaternion-based integration of gyroscope data Power strokes, Breaking, Turns, Jumps Feature extraction and template matching for skating action detection, [14] and Curves for skating Warping LCSS algorithm for classification of staking action Slap and wrist shots for shooting in ice hockey Feature extraction (maximum, minimum, mean rotational velocities) followed by recognition of shoot types using Random Forest classifier [16] Backswing, Downswing, Impact, Follow-through Raw acceleration and gyroscope data [20] drive, push, block, and topspin with forehand Event detection algorithm based on energy calculation, highpass filtering, drive, push, block, and topspin with backhand negative masking and peak detection for stroke detection; SVM with RBF kernel provides the best result for stroke type classification [12] Forehand and Backhand with Topspin and Slice, K-means clustering, Similarity measure and non-maximum suppression Smash, Footsteps (Shot steps and Side steps) for segment detection and LCSS classifier for shot classification;…”

Section: Gether With Some Notesmentioning

confidence: 99%

“…In Table 6, sampling rates used in sports performance monitoring are demonstrated, where it can be seen that the sampling frequency of 100 Hz is mostly used for the wearable sensors. [20,30] In Table 7, the problems associated with various studies together with some corresponding notes are presented. As we see, various issues like data transmission, sensors positions, sensors fusion, complexity, flexibility, etc.…”

Section: Gether With Some Notesmentioning

confidence: 99%

See 2 more Smart Citations

Body sensor networks for monitoring performances in sports: A brief overview and some new thoughts

Sattar¹,

Azad²,

Sikder³

2019

AIR

View full text Add to dashboard Cite

This paper aims to review on body sensor networks (BSNs) for sports from performance monitoring point of view with some new thoughts. The focus of the paper is to show that wearable sensor is more efficient than cameras in measuring sport performance and thereby video data and video based systems can be replaced by wearable sensors. Here, the current state-of-the art in BSNs are mainly introduced relating to sports performance instead of physical activity and health/safety related issues for sports and to the best of our knowledge, this has not been done yet for different types of sports rather than a particular sport. Although the progress in BSN for sports performance is in early stage, the ultimate goal is to develop a complete training/match analysis tool using wearable sensors and various analyses techniques to monitor as well as improve performances in sports.

show abstract

Section: Performance Monitoring In Sportsmentioning

confidence: 99%

Section: Gether With Some Notesmentioning

confidence: 99%

Section: Gether With Some Notesmentioning

confidence: 99%

See 1 more Smart Citation

Body sensor networks for monitoring performances in sports: A brief overview and some new thoughts

Sattar¹,

Azad²,

Sikder³

2019

AIR

View full text Add to dashboard Cite

show abstract

“…However, they do not examine whether a ball impact timing is precise or not. Blank et al also proposed a system that uses inertial sensors attached to a table tennis racket [13]. The system detects table tennis strokes by using an event detection method.…”

Section: Activity Recognitionmentioning

confidence: 99%

A Method for Determining the Moment of Touching a Card Using Wrist-worn Sensor in Competitive Karuta

Yamada

Murao

Terada

et al. 2018

Journal of Information Processing

View full text Add to dashboard Cite

Abstract:Competitive karuta is an official Japanese card game and is described as "martial art on the tatami." Recently, competitive karuta has attracted a great deal of attention among young people. One of characteristic rules of competitive karuta is that there is no referee; therefore players must judge themselves even if the difficult situation arises. Consequently, the players sometimes get into an argument over their judgement, which disrupts the other matches in the room because all the matches proceed in parallel. In this paper, we propose a system that judges the player who took a card first in a competitive karuta match. Our system measures motion data when players take a card by using a wrist-worn accelerometer and gyroscope, and estimates the times when the players touched the card. From the evaluation experiments, 69.2% of rounds were estimated without error and 99.0% of rounds were estimated within 20-ms error. When our system was introduced on the close game, the accuracy of deciding the player taking a card was 75%.

show abstract

“…Moreover, industry professionals have put significant effort into developing friendly sensors and equipment for human use. HAR is studied to solve practical problems, improve the safety and comfort of people's lives in their homes and in their daily common activities, and when combined with many professional fields such as medicine [5] [6], health [7] [8], and sports [9] [10] is an inevitable trend. Of course, these achievements get approval.…”

Section: Introductionmentioning

confidence: 99%

Understanding and Improving Deep Neural Network for Activity Recognition

Li¹,

Si²,

Li³

et al. 2018

Proceedings of the 11th EAI International Conference on Mobile Multimedia Communications

View full text Add to dashboard Cite

Activity recognition has become a popular research branch in the field of pervasive computing in recent years. A large number of experiments can be obtained that activity sensor-based data's characteristic in activity recognition is variety, volume, and velocity. Deep learning technology, together with its various models, is one of the most effective ways of working on activity data. Nevertheless, there is no clear understanding of why it performs so well or how to make it more effective. In order to solve this problem, first, we applied convolution neural network on Human Activity Recognition Using Smart phones Data Set. Second, we realized the visualization of the sensor-based activity's data features extracted from the neural network. Then we had in-depth analysis of the visualization of features, explored the relationship between activity and features, and analyzed how Neural Networks identify activity based on these features. After that, we extracted the significant features related to the activities and sent the features to the DNN-based fusion model, which improved the classification rate to 96.1%. This is the first work to our knowledge that visualizes abstract sensor-based activity data features. Based on the results, the method proposed in the paper promises to realize the accurate classification of sensorbased activity recognition.

show abstract

Sensor-based stroke detection and stroke type classification in table tennis

Cited by 79 publications

References 4 publications

Body sensor networks for monitoring performances in sports: A brief overview and some new thoughts

Body sensor networks for monitoring performances in sports: A brief overview and some new thoughts

A Method for Determining the Moment of Touching a Card Using Wrist-worn Sensor in Competitive Karuta

Understanding and Improving Deep Neural Network for Activity Recognition

Contact Info

Product

Resources

About