Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Cust, Emily; Sweeting, Alice; Ball, Kevin; Robertson, Sam

doi:10.1080/02640414.2018.1521769

Cited by 219 publications

(184 citation statements)

References 126 publications

(355 reference statements)

Supporting

Mentioning

177

Contrasting

Unclassified

Order By: Relevance

“…At the first level of classification, determining if the dancer was jumping or lifting their leg, using all six sensors and not including transitions, the model developed in this study performed superiorly to previously developed HAR algorithms in sport [10,12,17,33], with an average degree of accuracy of 98.2%. Convolutional neural networks have previously been applied to a single wearable sensor's accelerometer output to identify 10 different specific strikes in beach volleyball at a single level of classification with a lower classification accuracy of 83.2% [33].…”

Section: Discussionmentioning

confidence: 90%

“…Recently, more sophisticated machine learning techniques have been developed, such as deep learning for HAR [16,17]. Deep learning models are able to automatically learn features from raw data and are often able to achieve better performance than traditional machine learning because their added complexity allows the models to take greater advantage of larger and more complex training datasets [16].…”

Section: Introductionmentioning

confidence: 99%

“…While there is a growing body of literature supporting the use of machine learning for activity recognition in sports [12,17], based on review of the literature, to our knowledge, there are no reports of a machine learning approach to assist in quantifying ballet specific movement tasks. Thus, the purpose of this study was to develop a HAR system using wearable sensor data to accurately identify key ballet movements (jumping and lifting the leg), allowing for objective quantification of training volume in ballet.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development of a Human Activity Recognition System for Ballet Tasks

et al. 2020

View full text Add to dashboard Cite

Background: Accurate and detailed measurement of a dancer's training volume is a key requirement to understanding the relationship between a dancer's pain and training volume. Currently, no system capable of quantifying a dancer's training volume, with respect to specific movement activities, exists. The application of machine learning models to wearable sensor data for human activity recognition in sport has previously been applied to cricket, tennis and rugby. Thus, the purpose of this study was to develop a human activity recognition system using wearable sensor data to accurately identify key ballet movements (jumping and lifting the leg). Our primary objective was to determine if machine learning can accurately identify key ballet movements during dance training. The secondary objective was to determine the influence of the location and number of sensors on accuracy.Results: Convolutional neural networks were applied to develop two models for every combination of six sensors (6, 5, 4, 3, etc.) with and without the inclusion of transition movements. At the first level of classification, including data from all sensors, without transitions, the model performed with 97.8% accuracy. The degree of accuracy reduced at the second (83.0%) and third (75.1%) levels of classification. The degree of accuracy reduced with inclusion of transitions, reduction in the number of sensors and various sensor combinations. Conclusion: The models developed were robust enough to identify jumping and leg lifting tasks in real-world exposures in dancers. The system provides a novel method for measuring dancer training volume through quantification of specific movement tasks. Such a system can be used to further understand the relationship between dancers' pain and training volume and for athlete monitoring systems. Further, this provides a proof of concept which can be easily translated to other lower limb dominant sporting activities Key PointsDeep learning models were shown to have acceptable accuracy when applied to recognised ballet-specific jumping and leg lifting tasks in a population of 23 dancers. A system of multiple sensors (six per dancer) was shown to have the greatest accuracy; however, the optimal single sensor model also performed with acceptable accuracy. The inclusion of all six sensors yielded the highest degree of accuracy: however, fewer sensors still provided an acceptable degree of accuracy. For real-world application, minimal sensors are required to reduce athlete burden. The method demonstrated for model development is highly translatable for future developments in other lower limb dominant sporting activities.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Human Activity Recognition System for Ballet Tasks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Inspired by the phenomenon of the human-visual-cortex system, CNNs extract high-level features from an image. Image analysis has more subfields like pattern recognition, digital geometry, medical imaging, and computer vision [57][58][59][60]. These subfields cover various modern-day applications in astronomy, defence, filtering, microscopy, remote sensing, robotics, and machine vision [61,62].…”

Section: Image Analysismentioning

confidence: 99%

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Ilyas

Shahzad

Kim

2019

Sensors

View full text Add to dashboard Cite

Traditional handcrafted crowd-counting techniques in an image are currently transformed via machine-learning and artificial-intelligence techniques into intelligent crowd-counting techniques. This paradigm shift offers many advanced features in terms of adaptive monitoring and the control of dynamic crowd gatherings. Adaptive monitoring, identification/recognition, and the management of diverse crowd gatherings can improve many crowd-management-related tasks in terms of efficiency, capacity, reliability, and safety. Despite many challenges, such as occlusion, clutter, and irregular object distribution and nonuniform object scale, convolutional neural networks are a promising technology for intelligent image crowd counting and analysis. In this article, we review, categorize, analyze (limitations and distinctive features), and provide a detailed performance evaluation of the latest convolutional-neural-network-based crowd-counting techniques. We also highlight the potential applications of convolutional-neural-network-based crowd-counting techniques. Finally, we conclude this article by presenting our key observations, providing strong foundation for future research directions while designing convolutional-neural-network-based crowd-counting techniques. Further, the article discusses new advancements toward understanding crowd counting in smart cities using the Internet of Things (IoT).

show abstract

“…Smart sensors are fast becoming key tools in performance analysis for decreasing the time of direct observation with optimal validity [13,16]. The symbiosis between both instruments (performance analysis and smart devices), has focused its development in high-performance sport, mainly [11] because of the desire for performance improvement and control of the training load in many sports, e.g., soccer [17,18], football [19], basketball [20], rugby [21,22], and tennis [3,13,23].…”

Section: Introductionmentioning

confidence: 99%

Using Smart Sensors to Monitor Physical Activity and Technical–Tactical Actions in Junior Tennis Players

Giménez-Egido

Ortega

Verdú-Conesa

et al. 2020

IJERPH

View full text Add to dashboard Cite

The use of smart devices to obtain real-time data has notably increased in the context of training. These technological tools provide data which monitor the external load and technical–tactical actions related to psychological and physical health in junior tennis players. The purpose of this paper is to monitor technical–tactical actions and physical activity during a current tennis competition in the Green stage using a Zepp Tennis Smart Sensor 2. The participants were 20 junior tennis players (under 10 years of age), with an average age of 9.46 years. The total number of strokes (n= 21,477) during 75 matches was analyzed. The study variables were the following aspects: (a) number of strokes, (b) ball impact in the sweet spot; (c) racket speed; (d) ball spin; (e) calories burned; and (f) match time. The current system of competition, based on knockout, does not meet the World Health Organization’s recommendations for daily physical activity time. Players mainly used flat forehands with a lack of variability in technical–tactical actions which did not meet the current learning opportunity criteria of comprehensive methodologies. The competition system in under-11 tennis should be adapted to the players’ characteristics by improving the variability and quantity of practice.

show abstract

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Cited by 219 publications

References 126 publications

Development of a Human Activity Recognition System for Ballet Tasks

Development of a Human Activity Recognition System for Ballet Tasks

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Using Smart Sensors to Monitor Physical Activity and Technical–Tactical Actions in Junior Tennis Players

Contact Info

Product

Resources

About