Cricket Stroke Recognition Using Computer Vision Methods

Moodley, Tevin; Haar, Dustin van der

doi:10.1007/978-981-15-1465-4_18

Cited by 13 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, models from existing studies for batsmen’s stroke prediction are selected. The studies [ 18 , 19 , 20 ] use images and video datasets to predict different types of strokes. These studies employ AlexNet, LSTM, and RF models for stroke prediction.…”

Section: Resultsmentioning

confidence: 99%

“…Human pose estimation for predicting players’ performance in sports has been investigated recently, leading to several techniques and approaches in this field. A recent study [ 18 ] proposed a batsman shorts estimation model to identify four different strokes in cricket: glance, drive, block, and cut. The study utilized an image dataset of cricket strokes and extracted feature vectors from head, feet, bat, and hand positions to train several models, including a k-nearest neighbor, support vector machine, and convolutional neural network (CNN)/AlexNet.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Cricket Performance Analysis with Human Pose Estimation and Machine Learning

Siddiqui,

Younas,

Rustam

et al. 2023

Sensors

View full text Add to dashboard Cite

Cricket has a massive global following and is ranked as the second most popular sport globally, with an estimated 2.5 billion fans. Batting requires quick decisions based on ball speed, trajectory, fielder positions, etc. Recently, computer vision and machine learning techniques have gained attention as potential tools to predict cricket strokes played by batters. This study presents a cutting-edge approach to predicting batsman strokes using computer vision and machine learning. The study analyzes eight strokes: pull, cut, cover drive, straight drive, backfoot punch, on drive, flick, and sweep. The study uses the MediaPipe library to extract features from videos and several machine learning and deep learning algorithms, including random forest (RF), support vector machine, k-nearest neighbors, decision tree, linear regression, and long short-term memory to predict the strokes. The study achieves an outstanding accuracy of 99.77% using the RF algorithm, outperforming the other algorithms used in the study. The k-fold validation of the RF model is 95.0% with a standard deviation of 0.07, highlighting the potential of computer vision and machine learning techniques for predicting batsman strokes in cricket. The study’s results could help improve coaching techniques and enhance batsmen’s performance in cricket, ultimately improving the game’s overall quality.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Enhancing Cricket Performance Analysis with Human Pose Estimation and Machine Learning

Siddiqui,

Younas,

Rustam

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The shoulder extension was reported much more in successful pull-shots of batters as compared to unsuccessful pull-shot. Velocity of batters bat was increased due to higher shoulder extension and batters were benefited (Moodley & Haar, 2020). It was found that in the successful pull-shot shoulder velocity was faster than that of unsuccessful pull-shots.…”

Section: Discussionmentioning

confidence: 97%

Analysis of Upper Body Three-D Motion of Batters for Execution of Pull Shot in Cricket

Marwat

2022

JSRD

View full text Add to dashboard Cite

In modern international cricket pull-shot is used as deadly weapon against fast bowlers by the batters that is why the technique of pulling the short pitch deliveries has clinched importance and improved. The researcher has tried to investigate kinematics of the batters’ upper extremities in the cricket during executing pulling the short pitch ball. It was investigated that how the batters manage ball's speed, bounce, and uniformity during playing pull shot during competitions. Cricket players participating in HEC Pakistan, universities cricket championship from the Gomal University, Dera Ismail Khan, and KP, Pakistan were targeted sample of the study. The kinematic analysis was performed by using analysis software. The kinematics of upper extremities of the 12 batters for successful and unsuccessful pull shots were compared by using repeated measure (ANOVA). In better pull shot it was observed that the movement of the shoulders and arms were rapid, while, batters position was closer to line of short pitch ball. The results have shown that best and successful pull shot batters upper extremities joints extension and thus adjustment abilities were comparatively better than the others.

show abstract

Section: Har Implementation In Different Sportsmentioning

confidence: 99%

“…In two consecutive works [ 179 , 180 ] authors focused on the recognition of four different strokes in cricket (glance, block, drive, and cut) from images. In [ 179 ], the HOG features were combined with SVM, KNN, and AlexNet architecture. In [ 180 ], they used the OpenPose skeleton key points [ 181 ] as a set of defining features that are fed into an LSTM network.…”

Section: Har Implementation In Different Sportsmentioning

confidence: 99%