Cricket Video Research Articles

A novel multi-modal neural network approach for dynamic and generic sports video summarization

Video Summarization is a video compression/compaction technique to create a shorter yet informative version of original video. Video summarization has offered solutions to plenty of media, user and engineering applications. Though sports video summarization has been an active research topic for some time; there still exists a void for multi-modal, dynamic, generic and domain knowledge based approach for Cricket Sport video summarization. This paper presents a multi-modal video summarization approach to summarize Cricket sport videos. This work captures the domain knowledge acquired from multi-modal (audio-visual) cues. A dual neural network architecture pipeline is proposed to dynamically segment and dynamically summarize Cricket videos for generic target audience. The former Neural Network is grounded on Cricket bowling activity (visual feature) for dynamic video segmentation of Cricket videos. The segments are then forwarded to the latter Neural Network for identification of key segments. The key segment detection module relies on Audio analysis of Cricket video stream to identify exciting, content representative and informative segments as per Cricket domain. Experimental analysis on two novel proposed benchmark datasets, i.e. DPCS (Delivery Play Cricket Sport) image dataset and EXINP (Excited Interval Normal Play) Cricket Dataset (audio based) shows promising results. The results indicate that the proposed multi-modal approach generates exciting, content representative, informative, generic and dynamic summary incorporating domain knowledge of the sport.

Scene Classification for Sports Video Using Transfer Learning

Abstract: The quality of scene classification is particularly crucial because it is a key step in both video summarization and video analysis. This article proposes a strategy to accomplish high-quality scene classification and focuses on several practical implementation gaps over the previous methodologies. We identify five scene types, including batting, bowling, boundary, crowd, and close-up, using cricket as a case study. For scene categorization, we use the ResNet152 model which is pre-trained on imagenet. The proposed method employs new, fully connected layers in an encoder fashion. We also prepared a dataset of cricket video and manually labelled them into five classes which was later used to train the model. The model achieved mean accuracy of 99.15 upon training on the dataset.

A Player-Specific Framework for Cricket Highlights Generation Using Deep Convolutional Neural Networks

Automatic ways to generate video summarization is a key technique to manage huge video content nowadays. The aim of video summaries is to provide important information in less time to viewers. There exist some techniques for video summarization in the cricket domain, however, to the best of our knowledge our proposed model is the first one to deal with specific player summaries in cricket videos successfully. In this study, we provide a novel framework and a valuable technique for cricket video summarization and classification. For video summary specific to the player, the proposed technique exploits the fact i.e., presence of Score Caption (SC) in frames. In the first stage, optical character recognition (OCR) is applied to extract text summary from SC to find all frames of the specific player such as the Start Frame (SF) to the Last Frame (LF). In the second stage, various frames of cricket videos are used in the supervised AlexNet classifier for training along with class labels such as positive and negative for binary classification. A pre-trained network is trained for binary classification of those frames which are attained from the first phase exhibiting the performance of a specific player along with some additional scenes. In the third phase, the person identification technique is employed to recognize frames containing the specific player. Then, frames are cropped and SIFT features are extracted from identified person to further cluster these frames using the fuzzy c-means clustering method. The reason behind the third phase is to further optimize the video summaries as the frames attained in the second stage included the partner player’s frame as well. The proposed framework successfully utilizes the cricket videoo dataset. Additionally, the technique is very efficient and useful in broadcasting cricket video highlights of a specific player. The experimental results signify that our proposed method surpasses the previously stated results, improving the overall accuracy of up to 95%.

Cricket Video Highlight Generation Methods: A Review

The key events extraction from a video for the bestrepresentation of its contents is known as video summarization.In this study, the game of cricket is specifically consideredfor extracting important events such as boundaries, sixes andwickets. The cricket video highlight generation frameworksrequire extensive key event identification. These key events canbe identified by extracting the audio, visual and textual featuresfrom any cricket video.The prediction accuracy of the cricketvideo summarization mainly depends on the game rules, player’sform, their skill, and different natural conditions. This paperprovides a complete survey of latest research in cricket videosummarization methods. It includes the quantitative evaluationof the outcomes of the existing frameworks. This extensive reviewhighly recommended developing deep learning-assisted videosummarization approaches for cricket video due to their morerepresentative feature extraction and classification capabilitythan the conventional edge, texture features, and classifiers. Thescope of this analysis also includes future visions and researchopportunities in cricket highlight generation.

Sport Video Gaming Verses Direct Instruction: Examining Sport Knowledge and Future Sport Intention

While video gaming has pervaded society, dearth research exists investigating the ramifications of incorporating sport video gaming into sport-based physical activity courses. The purpose of this study was two-fold: 1) Determine whether direct instruction or video gaming (or a combination of both) is more effective in learning about a new sport; and 2) Examine to what extent does physically playing or playing a sport video game (or a combination of both) impact one’s intention to want to watch or physically play the sport in the future. This study employed a mixed methods pre/mid/post intervention design with two quasi-experimental groups. Participants included two classes of American university students with little prior knowledge of cricket enrolled in a “Global Games” course. Data was collected across two semesters with students enrolled in this course. During the first semester of data collection, participants first took a demographics questionnaire and cricket pre-test. This “Video Gaming First” (VGF; n = 17) group then played two 50-minute sessions of the video game Don Bradman Cricket, and then took a cricket mid-test. Next, participants partook in two 50-minute direct instruction physical activity lessons on cricket and then took the cricket post-test. Finally, the group participated in a 50-minute focus group session. The subsequent semester, to account for the order effect, all methods were replicated with the second class, except the two video gaming sessions were preceded by the two direction instruction sessions for this “Direct Instruction First” (DIF; n = 17) group. Results indicated that cricket knowledge significantly increased for the VGF from mid-test to post-test (p < .05, η² = 0.71), while the pre-test to mid-test did not significantly differ. For the DIF group, there was a significant increase in cricket knowledge from pre-test to mid-test (p < .05, η² = 0.77), while the mid-test to post-test did not significantly differ. No significant results were found regarding future intention to play or watch cricket. Overall, findings indicated that both groups significantly increased cricket knowledge from direct instruction but not from the cricket video gaming. However, while not statistically significant, the video game sessions did further increase cricket knowledge. Higher education physical activity course instructors may consider using a combination of video games and traditional instruction to teach sports to beginners, but the amount of video gaming equipment available and student training on how to use it should be considered.

Local Optimal-Oriented Pattern and Exponential Weighed-Jaya Optimization-Based Deep Convolutional Networks for Video Summarization

Video summarization is used to generate a short summary video for providing the users a very useful visual and synthetic abstract of the video content. There are various methods are developed for video summarization in existing, still an effective method is required due to some drawbacks, like cost and time. The ultimate goal of the research is to concentrate on an effective video summarization methodology that represents the development of short summary from the entire video stream in an effective manner. At first, the input cricket video consisting of number of frames is given to the keyframe generation phase, which is performed based on Discrete Cosine Transform (DCT) and Euclidean distance for obtaining the keyframes. Then, the residual keyframe generation is carried out based on Deep Convolutional Neural Network (DCNN), which is trained optimally using the proposed Exponential weighed moving average-Jaya (EWMA-Jaya) optimization.

Video Summarization using Deep Convolutional Neural Networks and Mutual Probability-based K-Nearest Neighbour

ABSTRACT The video summarisation is an advanced mechanism for enabling users to handle and browse large videos in an effective manner. Various video summarisation methods are developed in recent days, in which handling of synchronisation and timing issues remain as the important challenge. The proposed video summarisation technique produces a short summary from the huge video stream. Initially, from an input database, the cricket videos containing number of frames are fed to keyframe extraction unit. Here, the keyframe extraction is done by the Euclidean distance and discrete cosine transform, and the best keyframes are selected based on the Euclidean distance. The residual frame is obtained by passing the input frames through deep convolutional neural network. Then, the similarity is calculated by Bhattacharyya distance. For video summarisation process, the optimal frameset is evaluated by matching residual keyframe with obtained keyframes. Here, input queries consisting of face object are subjected to object matching process, which is performed using the proposed mutual probability-based k-nearest neighbour (MP-KNN) to obtain relevant frames based on texture features. The performance of the proposed MP-KNN is superior based on precision, recall, and F-measure with values 0.963, 0.960, and 0.909, respectively.

Retraction: Umpire Gesture Detection and Recognition using HOG and Non-Linear Support Vector Machine (NL-SVM) Classification of Deep Features in Cricket Videos (J. Phys.: Conf. Ser. 2070 012148)

This article has been retracted by IOP Publishing following an allegation that this article may contain tortured phrases [1], masking overlap of other work. [2-4]. IOP Publishing has investigated in line with the COPE guidelines and agree this article should be retracted. IOP Publishing wishes to credit the Problematic Paper Screener for bringing the issue to our attention. The authors have not confirmed whether they agree or disagree to this retraction. [1] Cabanac G, Labbe C, Magazinov A, 2021, Tortured phrases: A dubious writing style emerging in science. Evidence of critical issues affecting established journals, arXiv:2107.06751v1 [2] R Hari and M Wilscy, 2014, Event detection in cricket videos using intensity projection profile of Umpire gestures 2014 Annual IEEE India Conference (INDICON) [3] M.H Kolekar and s Sengupta, 2010, Semantic concept mining in cricket videos for automated highlight generation Multimed Tools Appl 47 545–579 [4] S Nandyal and S.L Kattimani, 2021, An Efficient Umpire Key Frame Segmentation in Cricket Video using HOG and SVM 2021 6th International Conference for Convergence in Technology (I2CT) Retraction published: 10 February 2023

Umpire Gesture Detection and Recognition using HOG and Non-Linear Support Vector Machine (NL-SVM) Classification of Deep Features in Cricket Videos

Gesture Recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost importance in designing an intelligent and efficient human–computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation, monitoring patients or elder people, surveillance systems, sports gesture analysis, human behaviour analysis etc., to virtual reality. In recent years, there has been increased interest in video summarization and automatic sports highlights generation in the game of Cricket. In Cricket, the Umpire has the authority to make important decisions about events on the field. The Umpire signals important events using unique hand on signals and gestures. The primary intention of our work is to design and develop a new robust method for Umpire Action and Non-Action Gesture Identification and Recognition based on the Umpire Segmentation and the proposed Histogram Oriented Gradient (HOG) feature Extraction oriented Non-Linear Support Vector Machine (NL-SVM) classification of Deep Features. Primarily the 80% of Umpire action and non-action images in a cricket match, about 1, 93, 000 frames, the Histogram of Oriented Gradient Deep Features are calculated and trained the system having six gestures of Umpire pose. The proposed HOG Feature Extraction oriented Non-Linear Support Vector Machine classification method achieves the maximal accuracy of 97.95%, the maximal sensitivity of 98.87%, the maximal specificity of 98.89% and maximal Precision of 97.02% which indicates its superiority.

Improving Event detection in Cricket Videos Using Audio Feature Analysis

This paper discusses an event detection approach based on audio, which proves to be effective when applied to the audio component of cricket television broadcaster’s video. In this approach, both crowed noise levels which is in the background and commentator voice which is in focus are considered correlated to key events in the time frame. Classifiers related to Hidden Markov Model (or HMM) are utilized as it is an efficient tool for modeling processes varying with time and broadly used in the area of speech recognition. This experiment done using cricket television broadcaster videos, was successful thus this method can be used for automatic indexing of audio (or video containing audio) for quick searching or segmentation.

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

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.

SGRNN-AM and HRF-DBN: a hybrid machine learning model for cricket video summarization

Summarization is important in sports video analysis; it gives a more compact and interesting representation of content. The automatic cricket video summarization is more challenging as it contains several rules and longer match duration. In this research, a hybrid machine learning approach is proposed to summarize cricket video. It analyzes the excitement, object, and event-based features for the detection of key events from the cricket video. First, the audio is analyzed for the extraction of the exciting clips by using an adaptive threshold, speech-to-text framework, and Stacked Gated Recurrent Neural Network with Attention Module (SGRNN-AM). Then, the scenes of each exciting clip are classified with a new Hybrid Rotation Forest Deep Belief Network (HRF-DBN). Next, the characters and action features are extracted from the scorecard region of each key frame and umpire frames of exciting clips. Finally, SGRNN-AM model is used to detect key events including fours, sixes, and wickets. The accuracy of the proposed SGRNN-AM video summarization model is increased with an attention module in the hidden outputs of Gated Recurrent Unit (GRU) for selecting the significant features. The performance of the suggested technique has been improved on various collections of cricket videos. It achieved a precision of $$96.82\ \%$$ and an accuracy of $$96.32\%$$ that proves its effectiveness.

Activity recognition framework in sports videos

Recent advancements in activity recognition from sports videos have attracted wide scientific interest of the Computer Vision community. However, the activity recognition problem from cricket video sequences is largely under-represented in the literature. This paper aims to devise a convolutional neural network (CNN) based model for sports activity recognition. The model is trained on the pre-trained VGG16, VGG19, ResNet50, and Inception V3 Models and tested on the clustered cricket videos frames extracted from the data set especially prepared for this research. The clustering of the frames is done by using K-Mean clustering algorithm. K-Fold cross validation is done which gave an accuracy of 99% on clustered data and 91% on un-clustered data. The accuracy and time complexity of the proposed method is better as compared to the state of the art methods used for activity recognition from videos.

Automatic Summarization of Cricket Highlights using Audio Processing

The problem of automatic excitement detection in cricket videos is considered and applied for highlight generation. This paper focuses on detecting exciting events in video using complementary information from the audio and video domains. First, a method of audio and video elements separation is proposed. Thereafter, the “level-of-excitement” is measured using features such as amplitude, and spectral center of gravity extracted from the commentators speech’s amplitude to decide the threshold. Our experiments using actual cricket videos show that these features are well correlated with human assessment of excitability. Finally, audio/video information is fused according to time-order scenes which has “excitability” in order to generate highlights of cricket. The techniques described in this paper are generic and applicable to a variety of topic and video/acoustic domains.

Cricket Video Events Recognition using HOG, LBP and Multi-class SVM

The world has witnessed a growth in multimedia data, especially video data over the past few years due to increased internet bandwidth and higher processing power of computers. Having a large number of video data also require techniques to store, summarize, index and information retrieval. More attention has been given in recent years to develop techniques which summarize, index and retrieve sports videos due to its commercial aspects. This paper proposes a framework which classifies a cricket video into one of the four events namely Bowled Out, Caught Behind, Catch Out and LBW Out. The framework uses training videos from each category of event and summarizes the videos into key frames. HOG and LBP features are computed for key frames and fused to form a single feature vector which will be labeled accordingly which represents a single event in video. Feature vector is given to a Multi-Class SVM which classifies the video into one of the four events. The experimental results show that the Precision of our technique is 77.23%, Recall is 77.86%, F-Measure is 77.55% and the Accuracy is 65.62%. The evaluation metrics of our technique are promising, because in the literature there is no other technique present so far for event detection & classification in cricket videos.

Classification of cricket videos using finite state machines

The problem of classifying scenes from cricket video is addressed and a robust framework for this problem is proposed. It is proposed that the finite state machines (FSM) are suitable for detecting and classifying scenes and their usage is demonstrated for three types of events: wicket, six and four. This framework utilises the structural information of the scenes together with the low-level and mid-level features. Low-level features of the video including motion and audio energy, and a mid-level feature, body, are used in this approach. The transitions of the FSMs are determined by the features from each shot in the scene. The FSMs have been experimented on over 80 clips and convincing results have been achieved.

Classification of cricket videos using finite state machines

Classification of cricket videos using finite state machines

Emperor Penguin optimized event recognition and summarization for cricket highlight generation

Cricket highlight generation is the process of summarizing a full-length video to a shortened form which should preserve the important moments present in the original video. In this paper, a new approach has been proposed for recognizing the key events and summarization. Audio features are initially used for extracting the excitement clips. Then, the important events like replay, players, umpires, spectators, and players gathering are extracted from each clip. Here, a hybrid deep neural network with Emperor Penguin optimization (HDNN-EPO) is proposed for labeling the excitement concepts presented in the cricket video based on the observed events automatically. These labeled concepts are then selected based on the importance degree and concatenated in temporal order to form highlights. The efficiency of the proposed method is proved through the experimental results and it outperforms the other existing approaches. Also, the extracted highlights have been compared with the manually-generated highlights by the sports television channel.

Bird Swarm Optimization-based Stacked Autoencoder Deep Learning for Umpire Detection and Classification

One of the most watched and a played sport is cricket, especially in South Asian countries. In cricket, umpire has the power for making significant decisions about events in the field. With the growing increase of the utilization of technology in sports, this paper presents the umpire detection and classification by proposing an optimization algorithm. The overall procedure of the proposed approach involves three steps, like segmentation, feature extraction, and the classification. At first, the video frames are extracted from input cricket video, and the segmentation is performed based on Viola-Jones algorithm. Once the segmentation is done, the feature extraction is carried out using Histogram of Oriented Gradients (HOG), and Fuzzy Local Gradient Patterns (Fuzzy LGP). Finally, the extracted features are given to the classification step. Here, the classification is done using the proposed Bird Swarm Optimization-based stacked auto encoder deep learning classifier (BSO-Stacked Autoencoders), that categories into umpire or others. The performance of the umpire detection and classification based on BSO-Stacked Autoencoders is evaluated based on sensitivity, specificity, and accuracy. The proposed BSO-Stacked Autoencoder method achieves the maximal accuracy of 96.562%, the maximal sensitivity of 91.884%, and the maximal specificity of 99%, that indicates its superiority.

Automation of Cricket Scoreboard by Recognizing Umpire Gestures

Imagine how tiresome it is for the scorers to update the scoreboard after each ball delivery during a cricket match. They need to be alert during any point in the match, watch every single ball, record ball by ball events, modify the score and coordinate with the umpire the entire time. A system that can update the scoreboard automatically after every ball will lessen their effort by half; the time taken for the updation and the chances of errors will also be reduced. A novel method for umpire pose detection for updating the cricket scoreboard during real-time cricket matches is suggested in this work. The proposed system identifies the events happening in the pitch by recognizing the gestures of the umpire and then updates the scoreboard accordingly. The concept of transfer learning is used to accelerate the training of neural network for feature extraction. The Inception V3 network pretrained on the visual database ImageNet is culled as the primary prospect for feature extraction. Instead of initializing the model with random weights, initializing it with the pretrained weights reduces the training time and hence is more efficient. The proposed system is a combination of two SVM classifiers. The leadoff classifier tells apart the images that contain an umpire from the non-umpire images. These ‘umpire’ images are then carried forward to the event detection classifier while the ‘non-umpire’ images are repudiated. The second classifier is able to identify four gestures – ‘Six’, ‘Wide’, ‘No ball’ and ‘Out’ from the images, following which the scoreboard is updated. In addition to these four classes, one more label is defined to group those umpire frames within which the umpire does not show any signal, namely the ‘No Action’ class. The cricket video given as input is first split into number of shots and each frame is considered as a test image for the combined classifier system. A majority voter is used to confirm the final classification result which decreases the chances of misclassifications. The preliminary results suggest that the intended system is efficacious for the purpose of automating the updation of scoreboard during real time cricket matches.