Cricket shot classification using motion vector

Karmaker, Debajyoti; Chowdhury, Azm Ehtesham; Miah, M. Saef Ullah; Imran, Md. Al; Rahman, Mashiour

doi:10.1109/icctim.2015.7224605

Cited by 36 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shih [20] covered various content-aware sports video analysis and summarization techniques on a broader scope of games, techniques, issues, benchmarks, and datasets. Karmaker et al [21] employed an optical flow tracing method for shot classification of the cricket sport. A trained 3D MACH filter recognized the actions.…”

Section: Scene Classification Via Deep-learning Approachmentioning

confidence: 99%

Scene Classification for Sports Video Summarization Using Transfer Learning

Rafiq

Agyeman

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper proposes a novel method for sports video scene classification with the particular intention of video summarization. Creating and publishing a shorter version of the video is more interesting than a full version due to instant entertainment. Generating shorter summaries of the videos is a tedious task that requires significant labor hours and unnecessary machine occupation. Due to the growing demand for video summarization in marketing, advertising agencies, awareness videos, documentaries, and other interest groups, researchers are continuously proposing automation frameworks and novel schemes. Since the scene classification is a fundamental component of video summarization and video analysis, the quality of scene classification is particularly important. This article focuses on various practical implementation gaps over the existing techniques and presents a method to achieve high-quality of scene classification. We consider cricket as a case study and classify five scene categories, i.e., batting, bowling, boundary, crowd and close-up. We employ our model using pre-trained AlexNet Convolutional Neural Network (CNN) for scene classification. The proposed method employs new, fully connected layers in an encoder fashion. We employ data augmentation to achieve a high accuracy of 99.26% over a smaller dataset. We conduct a performance comparison against baseline approaches to prove the superiority of the method as well as state-of-the-art models. We evaluate our performance results on cricket videos and compare various deep-learning models, i.e., Inception V3, Visual Geometry Group (VGGNet16, VGGNet19) , Residual Network (ResNet50), and AlexNet. Our experiments demonstrate that our method with AlexNet CNN produces better results than existing proposals.

show abstract

Section: Scene Classification Via Deep-learning Approachmentioning

confidence: 99%

Scene Classification for Sports Video Summarization Using Transfer Learning

Rafiq

Agyeman

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The shots are classified by computing the Laplacian of Gaussian (LoG) of each frame. Laplacian of Gaussian (LoG) is used as there are large number of motion vectors [3].…”

Section: B Literature Related To Methodologies 1) Shot Detection Using Cnn and Lstm Modelsmentioning

confidence: 99%

“…Extraction of salient features and optical flow directly from cricket shot videos is still a difficult task as there are several different direction optical flows of body parts are created while playing a shot. So classification of different shots is done using spatio-temporal 3D MACH filter which also uses motion estimation approach [3].…”

Section: ) Wireless Electronic Training System For Cricketmentioning

confidence: 99%

A Review on Automated Cricket Trainer

Shah¹

2021

IJRASET

View full text Add to dashboard Cite

In today's world cricket is known to be one of the most popular sports. Also it is considered as a very competitive sport as there are various leagues, tournaments held for cricket between countries all over the world. So performance in such a popular sport is a very important aspect for an individual or even as a team. When an individual is playing for the team his/her performance contributes for the team. If a player's performance is not good then it might result for the team to end up on the losing side. So as a batsman, a player should play every inning with the responsibility of the team. But many times, even the best batsmen make mistakes while playing a particular shot. The study focuses on helping a batsman to correct his/her errors in miscued shots. So that when the same shot is played again chances of errors decrease. It tries to help the player to detect the error in a miscued shot as due to which part the shot was not executed properly. With the help of this, players can work on those errors and minimize them when played again. In this paper, an in-depth study is performed on various systems developed forshot detections, posture detection. Various approaches mentioned are studied with pros and cons identified.

show abstract

“…However, the best model had a low accuracy of 85% for the hook shot. In [ 7 ], a motion-estimation approach was proposed to classify cricket shots. Eight classes of angle ranges were defined to detect cricket shots.…”

Section: Related Workmentioning

confidence: 99%

CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit

Sen

Deb

Dhar

et al. 2021

Sensors

View full text Add to dashboard Cite

Recognizing the sport of cricket on the basis of different batting shots can be a significant part of context-based advertisement to users watching cricket, generating sensor-based commentary systems and coaching assistants. Due to the similarity between different batting shots, manual feature extraction from video frames is tedious. This paper proposes a hybrid deep-neural-network architecture for classifying 10 different cricket batting shots from offline videos. We composed a novel dataset, CricShot10, comprising uneven lengths of batting shots and unpredictable illumination conditions. Impelled by the enormous success of deep-learning models, we utilized a convolutional neural network (CNN) for automatic feature extraction, and a gated recurrent unit (GRU) to deal with long temporal dependency. Initially, conventional CNN and dilated CNN-based architectures were developed. Following that, different transfer-learning models were investigated—namely, VGG16, InceptionV3, Xception, and DenseNet169—which freeze all the layers. Experiment results demonstrated that the VGG16–GRU model outperformed the other models by attaining 86% accuracy. We further explored VGG16 and two models were developed, one by freezing all but the final 4 VGG16 layers, and another by freezing all but the final 8 VGG16 layers. On our CricShot10 dataset, these two models were 93% accurate. These results verify the effectiveness of our proposed architecture compared with other methods in terms of accuracy.

show abstract

Cricket shot classification using motion vector

Cited by 36 publications

References 8 publications

Scene Classification for Sports Video Summarization Using Transfer Learning

Scene Classification for Sports Video Summarization Using Transfer Learning

A Review on Automated Cricket Trainer

CricShotClassify: An Approach to Classifying Batting Shots from Cricket Videos Using a Convolutional Neural Network and Gated Recurrent Unit

Contact Info

Product

Resources

About