Cricket Video Research Articles

Scene Classification for Sports Video Summarization Using Transfer Learning.

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.

Generating Highlights of Cricket Video using Commentators and Spectators Voice

Videos are one of the important and richest sources of data on internet. In this growing world of digital technology video summarization will be handy in analysing the video data. Recently Natural Language Processing has attracted more researchers to work to meet the current emerging challenges. Among the various issues, video summarization got more focus and in this regard, many applications and works have been evolved. Video Summarization is the process of creating a small video describing the actual video within short duration(s). The paper focuses on generating highlights of a cricket video by analysing the voice of commentator and spectators. The experimental results have shown good performance when compared with human generated summary.

A Novel Hybrid Adaptive Filter to Improve Video Keyframe Clustering to Support Event Resolution in Cricket Videos

Automated summary generation of sports videos poses many challenges of detecting exciting events of a game. In our research, we focus on the table of content-based video summarization for cricket videos to facilitate efficient indexing of cricket events. Initially, we have identified event boundaries accurately to detect the event start and end points. To distinguish the different types of events, we need to analyze the sequence of the camera focus area. By observing the characteristics, we have categorized the camera focus area into several categories. To overcome the challenge of low accuracy we have introduced a novel algorithm for adaptive filtering for the comparison of hue histogram. The results prove that this algorithm is sufficient for accurate image clustering and this may be used in other sports event clustering as well.

Multimodal framework based on audio‐visual features for summarisation of cricket videos

Sports broadcasters generate an enormous amount of video content on the cyberspace due to massive viewership all over the world. Analysis and consumption of this huge repository urges the broadcasters to apply video summarisation to extract the exciting segments from the entire video to capture user's interest and reap the storage and transmission benefits. Therefore, in this study an automatic method for key-events detection and summarisation based on audio-visual features is presented for cricket videos. Acoustic local binary pattern features are used to capture excitement level in the audio stream, which is used to train a binary support vector machine (SVM) classifier. Trained SVM classifier is used to label audio frame as an excited or non-excited frame. Excited audio frames are used to select candidate key-video frames. A decision tree-based classifier is trained to detect key-events in the input cricket videos that are then used for video summarisation. Performance of the proposed framework has been evaluated on a diverse dataset of cricket videos belonging to different tournaments and broadcasters. Experimental results indicate that the proposed method achieves an average accuracy of 95.5%, which signifies its effectiveness.

Event Detection and Summarization of Cricket Videos

Event Detection and Summarization of Cricket Videos

A Unified Framework for Cricket Video Shot Classification using Low Level Features

Objectives: Classification of various shots from the cricket video is a fundamental and useful step in cricket video summarization. Methods: We proposed a unified framework for cricket video shots classification. Shots are classified in to Field, Pitch and Boundary, Close-Up, Crowd, Fielders’ gathering and Sky. It requires domain knowledge of cricket sport. Classification of shot into specific category requires extraction of appropriate low level features from the frames. Findings: Multi-perception neural network is then trained and tested with data sets which consist of set of feature vector. Findings: Shot classification accuracy can be increased by adding other features like motion, edge change ratio, texture etc. Basic processing for shot classification is time consuming so parallel approach for the same will be helpful to reduce the execution time. Results: Result analysis shows that system accuracy of shot classification is 75% on an average. Keywords: Classifier, Feature Extraction, Feature Vector, Key Frame, Shot, Training and Testing Data Set

Automated Classification of Cricket Pitch Frames in Cricket Video

Automated detection of the cricket pitch is a fundamental step in content-based indexing and summarization of cricketvideos. In this paper, we propose visual-content based algorithms to automate the extraction of video frames with thecricket pitch in focus from input cricket videos. As a preprocessing step, we first select a subset of frames with a viewof the cricket field. This reduces the search space by eliminating frames that contain a view of the audience, close-upshots of specific players, advertisements, etc. The subset of frames containing the cricket field is then processed using astatistical modeling of the grayscale (brightness) histogram (SMoG). Since, in the present day, most videos are shot incolor and SMoG does not utilize this information, we propose an alternative: color quantization based region of interestextraction (CQRE). Experimental results demonstrate that successive application of the two methods outperforms eitherone applied exclusively, regardless of the quality of the input. The SMoG-CQRE combination for cricket pitch detectionyields an average accuracy of 98:6% in the best case (a high resolution video with good contrast) and an average accuracyof 87:9% in the worst case (a low resolution video with poor contrast). Since, the extraction of pitch frames only formsthe first step in analyzing key action frames in a match, we also present an an algorithm for player detection in theseframes.

Optical cues used in predation by jumping spiders, Phidippus audax (Araneae, Salticidae)

Jumping spiders are known to rely on visual information when making predatory decisions, but the relative roles of global and local motion, shape and interior spatial detail in eliciting attack remain poorly resolved. We manipulated videos of crickets and presented jumping spiders, Phidippus audax, with choice tests. Consistent with previous studies, spiders more often approached videos depicting moving prey versus motionless prey. Spiders attended to local motion characteristics, preferring videos of natural cricket motion over videos of a snapshot of a cricket that moved across the screen with the same start-and-stop global motion pattern as the natural cricket. However, spiders showed no evidence of preference between moving images that differed in shape and interior spatial detail: a cricket snapshot and a rectangle of the same size and colour. These results indicate that spiders either cannot detect differences between the stimuli, or can detect differences but show no preference. To distinguish between these possibilities, we used an aversive conditioning protocol. Conditioning was effective, as we could train spiders to choose a moving snapshot over a natural cricket. However, we were unable to induce discrimination between cricket snapshots and rectangles, suggesting that spiders were unable to distinguish these images even when motivated to do so. There was no significant difference in the spiders' propensity to choose cricket videos with natural stop-and-start motion versus those without pauses, so we found no evidence that the commonly observed pausing behaviour of walking prey influences the propensity of spiders to attack. Taken together, our results support the hypothesis that movement is more important than image shape for predatory decisions of this jumping spider.

Wicket Fall Concept Mining From Cricket Video Using A-Priori Algorithm

In this paper, we propose an algorithm to detect semantic concepts from cricket video. In our previous work, we have proposed key frame detection based approach for semantic event detection and classification. The proposed scheme works in two parts. In first part a top-down event detection and classification is performed using hierarchical tree. In second part, higher level concept is identified by applying A-Priori algorithm. In part 1, key frames are identified based on Hue Histogram difference at level 1. At level 2, logo transitions classify the frames as real-time or replay. At level 3, we classify the real time frames as field view, pitch view or non field view based on thresholds like Dominant Soli Pixel Ration (DSPR) and Dominant Grass Pixel Ration (DGPR). At level 4, we detect close up and crowd frames based upon edge detection. At level 5a, we classify the close up frames into player of team A, player of team B and umpire based upon skin colour and corresponding jersey colour. At level 5b, we classify the crowd frames into spectators, player’s gathering of team A or player’s gathering of team B. In part two, labels are associated with each frame event, which is used as input to A-Priori algorithm for concept mining. Results at the end of paper show the robustness of our approach.

Semantic concept mining in cricket videos for automated highlight generation

This paper presents a novel approach towards automated highlight generation of broadcast sports video sequences from its extracted events and semantic concepts. A sports video is hierarchically divided into temporal partitions namely, megaslots, slots, and semantic entities, namely concepts, and events. The proposed method extracts event sequence from video and classifies each sequence into a concept by sequential association mining. The extracted concepts and events within the concepts are selected according to their degree of importance to include those in the highlights. A parameter degree of abstraction is proposed, which gives a choice to the user about how concisely the extracted concepts should be produced for a specified highlight duration. We have successfully extracted highlights from recorded video of cricket match and compared our results with the manually-generated highlights by sports television channel.