Shot Detection Research Articles

Deep Learning in Cricket: A Comprehensive Survey of Shot Detection and Performance Analysis

Cricket shot detection and performance analysis have become increasingly significant in the realm of sports analytics. This paper presents a comprehensive survey of recent advancements in cricket shot detection and performance analysis using deep learning techniques. Through a systematic review of ten research papers, various methodologies, algorithms, and approaches employed in the field were examined. The surveyed papers showcase the application of deep convolutional neural networks (CNNs), transfer learning, and multimodal feature integration for accurate shot detection and outcome classification. Additionally, the survey highlights common processes such as data preprocessing, model training, and evaluation metrics, while also discussing the integration of features extracted from video, audio, and image modalities. Through a detailed literature review, this paper analyzes the similarities and differences in approaches, methodologies, and results across the surveyed papers. Furthermore, this survey identifies opportunities for future research and development to advance the field of cricket shot detection and performance analysis. Overall, this survey provides valuable insights into the state-of-the-art techniques and challenges in utilizing deep learning for cricket analytics, offering guidance for researchers and practitioners in the domain.

Identify Cricket Shots using Machine Learning

Cricket shot detection is a game-changing technology that offers deep insights into player performance and match data, completely changing the way the sport is played. The main elements and importance of cricket shot detection systems are explored in this abstract. Using computer vision and machine learning techniques, the system examines video footage of cricket matches to accurately detect and classify every shot made by batsmen. Shot types (such as cover drive, pull, or leg glance), shot trajectories, and success rates are among the important data it retrieves. Numerous stakeholders in the cricketing ecosystem find diverse uses for cricket shot detection. It provides coaches and professional athletes with an unmatched post-match analysis tool that helps with strategic planning and performance enhancement.The method is used by team analysts to create winning strategies by gaining insight into opponents' shot patterns. Shot detection provides compelling visualizations and real-time shot labels in the broadcasting domain, enhancing the viewing experience. While talent scouts and cricket organizations use technology to find players and nurture talent, cricket enthusiasts profit from comprehensive shot data. This abstract highlight cricket shot detection's potential and adaptability, highlighting how it can revolutionize the cricket industry. Technology keeps improving the game, empowering players, and enthralling spectators with a deeper comprehension of the sport. Several sports have received a lot of attention and popularity recently. Many people were pining for live sports action during the height of the recent outbreak because there were no sporting activities. With millions of devoted fans who watch the games with emotion, cricket is one of the most respected sports in India. Enticed by the game, fans frequently conduct in-depth evaluations of certain players, focusing on their skills and shot choices. A greater number of people are interested in assessing players' performances in order to make wise choices for fantasy teams, especially in light of the popularity of fantasy leagues and related services. Automation presents a potential solution to the significantly time-consuming and manual process of detecting cricket batters' shots. In order to accomplish its goals, this study uses deep learning in the form of Convolutional Neural Networks (CNNs) to present an efficient method for evaluating cricket strokes

Implementation of hand‐object pose estimation using SSD and YOLOV5 model for object grasping by SCARA robot

AbstractEnforcement of advanced deep learning methods in hand‐object pose estimation is an imperative method for grasping the objects safely during the human–robot collaborative tasks. The position and orientation of a hand‐object from a two‐dimensional image is still a crucial problem under various circumstances like occlusion, critical lighting, and salient region detection and blur images. In this paper, the proposed method uses an enhanced MobileNetV3 with single shot detection (SSD) and YOLOv5 to ensure the improvement in accuracy and without compromising the latency in the detection of hand‐object pose and its orientation. To overcome the limitations of higher computation cost, latency and accuracy, the Network Architecture Search and NetAdapt Algorithm is used in MobileNetV3 that perform the network search for parameter tuning and adaptive learning for multiscale feature extraction and anchor box offset adjustment due to auto‐variance of weight in the level of each layers. The squeeze‐and‐excitation block reduces the computation and latency of the model. Hard‐swish activation function and feature pyramid networks are used to prevent over fitting the data and stabilizing the training. Based on the comparative analysis of MobileNetV3 with its predecessor and YOLOV5 are carried out, the obtained results are 92.8% and 89.7% of precision value, recall value of 93.1% and 90.2%, mAP value of 93.3% and 89.2%, respectively. The proposed methods ensure better grasping for robots by providing the pose estimation and orientation of hand‐objects with tolerance of −1.9 to 2.15 mm along x, −1.55 to 2.21 mm along y, −0.833 to 1.51 mm along z axis and −0.233° to 0.273° along z‐axis.

Deep SORT Related Studies

Computer vision is the field of computer science in which computers are made capable to see and recognize like human being. Deep learning is using multiple layers for the purpose of understanding and recognizing various objects. Deep Simple Real Time Tracker is the area in which the objects are tracked in real time from multiple images and videos. Many researchers have contributed to the field and various algorithms have been proposed. The current study presents the deep SORT related studies in which the various algorithms have been presented for the sake of understanding and starting point for the researchers interested in computer vision and deep sorting. The single shot detection, feature extraction, have been explained along with the research conducted. Feature selection and extraction, matching recognition, object tracking through frames have been appended to the current study.

Event detection in football: Improving the reliability of match analysis.

With recent technological advancements, quantitative analysis has become an increasingly important area within professional sports. However, the manual process of collecting data on relevant match events like passes, goals and tacklings comes with considerable costs and limited consistency across providers, affecting both research and practice. In football, while automatic detection of events from positional data of the players and the ball could alleviate these issues, it is not entirely clear what accuracy current state-of-the-art methods realistically achieve because there is a lack of high-quality validations on realistic and diverse data sets. This paper adds context to existing research by validating a two-step rule-based pass and shot detection algorithm on four different data sets using a comprehensive validation routine that accounts for the temporal, hierarchical and imbalanced nature of the task. Our evaluation shows that pass and shot detection performance is highly dependent on the specifics of the data set. In accordance with previous studies, we achieve F-scores of up to 0.92 for passes, but only when there is an inherent dependency between event and positional data. We find a significantly lower accuracy with F-scores of 0.71 for passes and 0.65 for shots if event and positional data are independent. This result, together with a critical evaluation of existing methodologies, suggests that the accuracy of current football event detection algorithms operating on positional data is currently overestimated. Further analysis reveals that the temporal extraction of passes and shots from positional data poses the main challenge for rule-based approaches. Our results further indicate that the classification of plays into shots and passes is a relatively straightforward task, achieving F-scores between 0.83 to 0.91 ro rule-based classifiers and up to 0.95 for machine learning classifiers. We show that there exist simple classifiers that accurately differentiate shots from passes in different data sets using a low number of human-understandable rules. Operating on basic spatial features, our classifiers provide a simple, objective event definition that can be used as a foundation for more reliable event-based match analysis.

Joint learning of video scene detection and annotation via multi-modal adaptive context network

The tasks of scene detection and annotation have gained impressive attention for understanding video content. The main challenges lie in mitigating the error propagation of shot detection, recognizing cuts and gradual transitions, fusing hierarchical multi-modal cues, and solving these two tasks simultaneously. To address these challenges, we propose the Multi-modal Adaptive Context Network (MACN) to jointly learn scene detection and annotation from a window partitioning perspective. As a shared task-agnostic part, we perform Window-based Cross-modal Representation (WCR) to distill complex semantic correlations from multi-modal sources for each window. Considering the long-term temporal dependency of variable-length scenes, we further develop Adaptive Context-aware Representation (ACR) to improve the performance for specific tasks. Different from previous works, scene detection is formulated as locating the starting window and its associated location offset and transition duration. Meanwhile, we assemble two multi-label sub-classifiers in different levels to predict the labels for each scene candidate. Experimental comparisons to state-of-the-art algorithms on the TAVS and ClipShots indicate that the proposed method yields promising performance in both tasks. Our code and test sample videos are released at MACN.

Single shot detection of alterations across multiple ionic currents from assimilation of cell membrane dynamics

The dysfunction of ion channels is a causative factor in a variety of neurological diseases, thereby defining the implicated channels as key drug targets. The detection of functional changes in multiple specific ionic currents currently presents a challenge, particularly when the neurological causes are either a priori unknown, or are unexpected. Traditional patch clamp electrophysiology is a powerful tool in this regard but is low throughput. Here, we introduce a single-shot method for detecting alterations amongst a range of ion channel types from subtle changes in membrane voltage in response to a short chaotically driven current clamp protocol. We used data assimilation to estimate the parameters of individual ion channels and from these we reconstructed ionic currents which exhibit significantly lower error than the parameter estimates. Such reconstructed currents thereby become sensitive predictors of functional alterations in biological ion channels. The technique correctly predicted which ionic current was altered, and by approximately how much, following pharmacological blockade of BK, SK, A-type K+ and HCN channels in hippocampal CA1 neurons. We anticipate this assay technique could aid in the detection of functional changes in specific ionic currents during drug screening, as well as in research targeting ion channel dysfunction.

Tomato fruit disease detection based on improved single shot detection algorithm

Tomato fruit disease detection based on improved single shot detection algorithm

The Practice and exploration of deep learning algorithm in the creation and realization of intangible cultural heritage animation

Abstract The rapid development of modern technology and civilization has made the survival of non-heritage culture more and more serious, and the protection and inheritance of intangible cultural heritage is a heavy task and a long way to go. This paper takes the feasibility of non-heritage animation creation as an entry point, analyzes the ideological mechanism in the process of non-heritage animation creation, and explores the economic realization brought by deep learning technology assisting non-heritage animation creation. For the lens scene switching in the process of non-heritage animation creation, this paper utilizes the CNN network for the initial positioning of the lens boundary. It establishes the tangent detection model of a non-heritage animation lens by combining it with the 3D-CNN network. To understand the diversity of non-heritage animation creation styles, this paper establishes a model for style migration of non-heritage cultural images based on the VGG-Net network and conducts experimental investigations. The results show that when the hyperparameter value of the model is set to λ = 3, γ = 1.2, the model retains only 5.19% of the candidate boundary frames, and the accuracy of the detection of the non-heritage animation creation tangent shots is 0.939. The total loss value in the process of style migration fluctuates around 0.005, and the subjective evaluation score of the images generated by the style migration network is 4.82. The deep learning algorithm that promotes the creation of non-heritage animation can expand the content and characteristics of non-heritage animation creation and can also realize the economic realization of non-heritage animation.

The Construction of a Multimodal Teaching Content Analysis System for English in Colleges and Universities

Abstract Based on multimodal theory, this paper constructs a multimodal content analysis system for college English with the digital model of teaching content, teaching interactive technology, and virtual reality technology as the main functional modules. The digital transformation of teaching content is done through the use of the particle swarm optimization algorithm and Wiki collaboration, and the learning objects in the learning content library are processed and transformed. The main technical aspects of shot detection, key frame determination, feature extraction, and feature matching are improved to establish the interactive function of English teaching videos. The quadratic error measurement algorithm enhances the edge folding algorithm and streamlines the 3D model to realize the virtual teaching simulation function. Students majoring in business English at a university in Kunming, Yunnan Province, China, are used as research objects to carry out the teaching application practice of this paper’s system. The total average English unit scores of the experimental class increased from 68.2 to 72.1 in the pre-test, and the recognition, comprehension, and utilization dimensions of the learning effect were higher than those of the control class by 0.46, 0.66, and 0.51, respectively, which showed a significant difference (P<0.05). The experimental group of subject students also had a better experience using the system in this paper.

Enhancing Agricultural Pest Management with YOLO V5: A Detection and Classification Approach

Due to the growing population and the numerous ecological challenges that affect crop yields, the need to modernize the crop production process has become increasingly critical. Swiftly managing potential threats to crops can have a substantial impact on overall crop production. Pests represent a significant menace, capable of causing substantial losses if not effectively controlled in a timely manner. In this study, a deep learning-based method for pest identification is introduced. The approach leverages the YOLO (You Only Look Once) object recognition SSD (single shot detection )algorithm in combination with the pre-trained DARKNET architecture to categorize pests into nine distinct classes. The study utilizes a publicly available dataset sourced from Kaggle, which comprises a total of 7,046 images. The outcomes reveal overall 83% of overall accuracy rate, with a notably low training and validation loss of 0.02%. Moreover, our model exhibits a notable enhancement in localization results, delivering a precision of 0.83, a recall of 0.83, an mAP-0.5 of 0.833, and an mAP-0.5:0.95 of 0.783.

Server node video processing based on feature depth analysis algorithm

ABSTRACT The complex and diverse server video data leads to the problem of effective retrieval of these data. The current shot edge detection algorithm and key frame extraction algorithm in server node video processing have problems such as poor extraction performance and poor adaptability. Therefore, the research combined the feature depth analysis to improve the two, and the performance was verified by experiments. The shot detection algorithm is verified by modifying the secondary detection model. This method can detect lens mutation, gradual change and other phenomena well, and the accuracy rate can reach 99.7%. The precision under the gradient lens is 92.08%, far higher than 63.50% and 85.39% of ISIFT and CS-DFS. In the verification experiment using Convolution Neural Networks (CNNs) key frame extraction algorithm, the number of key frame extractions of the proposed algorithm can reach up to 88 frames. Compared with other methods, the accuracy of the algorithm studied can reach 99.67%, which is higher than the comparison algorithm. In general, the improved algorithm proposed in the study has high adaptability to edge detection and the ability to express key frame video, and has high practicability in actual server node video processing.

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

In this article, a hierarchical method for action recognition based on temporal and spatial features is proposed. In current HAR methods, camera movement, sensor movement, sudden scene changes, and scene movement can increase motion feature errors and decrease accuracy. Another important aspect to take into account in a HAR method is the required computational cost. The proposed method provides a preprocessing step to address these challenges. As a preprocessing step, the method uses optical flow to detect camera movements and shots in input video image sequences. In the temporal processing block, the optical flow technique is combined with the absolute value of frame differences to obtain a time saliency map. The detection of shots, cancellation of camera movement, and the building of a time saliency map minimise movement detection errors. The time saliency map is then passed to the spatial processing block to segment the moving persons and/or objects in the scene. Because the search region for spatial processing is limited based on the temporal processing results, the computations in the spatial domain are drastically reduced. In the spatial processing block, the scene foreground is extracted in three steps: silhouette extraction, active contour segmentation, and colour segmentation. Key points are selected at the borders of the segmented foreground. The last used features are the intensity and angle of the optical flow of detected key points. Using key point features for action detection reduces the computational cost of the classification step and the required training time. Finally, the features are submitted to a Recurrent Neural Network (RNN) to recognise the involved action. The proposed method was tested using four well-known action datasets: KTH, Weizmann, HMDB51, and UCF101 datasets and its efficiency was evaluated. Since the proposed approach segments salient objects based on motion, edges, and colour features, it can be added as a preprocessing step to most current HAR systems to improve performance.

Estimation of 3D anatomically précised hand poses using single shot corrective CNN

A crucial component of human-computer interaction is 3D hand posture assessment. The most recent advancements in computer vision have made estimating 3D hand positions simpler by using deep sensors. The main challenge still stems from unrealistic 3D hand poses because the existing models only use the training dataset to learn the kinematic rules, which is ambiguous, and it is a difficult task to estimate realistic 3D hand poses from datasets because they are not free from anatomical errors. The suggested model in this study is trained using a closed-form expression that encodes the biomechanical rules, thus it does not entirely reliant on the pictures from the annotated dataset. This work also used a Single Shot Detection and Correction convolutional neural network (SSDC-CNN) to handle the issues in imposing anatomically correctness from the architecture level. The ResNetPlus is implemented to improve representation capability with enhanced the efficiency of error back-propagation of the network. The datasets of the Yoga Mudras, like HANDS2017, and MSRA have been used to train and test the future model. As observed from the ground truth the previous hand models have many anatomical errors but, the proposed hand model is anatomically error free hand model compared to previous hand models. By considering the ground truth hand pose, the recommended hand model has shown good accuracy when compared to the state-of-art hand models.

A fast and robust shot detection method in HEVC/H.265 compressed video

A fast and robust shot detection method in HEVC/H.265 compressed video

Ml Based Hand Gesture Recognition

The projects focus on Gesture recognition using the media pipe hands Lite framework where the custom data set of 10 gesture Images is trained with an in built media pipe hands model which contains 2CNN models-A palm detection model running on single Shot detection architecture and a hand landmark generator running on regression model architecture. The data set is successfully trained and tested with the proposed method and an accuracy of 98 percent is obtained. Keywords: Gesture Recognition, Media pipe, Hands De-tection, CNN, Regression Model, Hand Landmark Detection, Machine Learning, Image Processing.

A Comparative Study of Object Detection using YOLO and SSD Algorithms

One of the most significant and difficult areas of computer vision is object detection, which is used in many aspects of daily life, including security monitoring, autonomous vehicle operation, and so on, to find instances of semantic objects belonging to a particular class. In this survey, we first look at the current approaches of typical detection models and discuss the benchmark datasets in order to comprehensively and deeply comprehend the major development status of the object detection pipeline. This project explains how convolutional neural network-based deep learning techniques are used for object detection. In this study, deep learning methods for cutting-edge object identification systems are evaluated. Any kind of visual medium is represented by a computer as a collection of numerical numbers. In order to inspect the contents of images, they need image processing techniques. In order to determine which is the quickest and most effective object detection algorithm, this research analyzes two popular algorithms: Single Shot Detection (SSD) and You Only Look Once (YOLO). The COCO (Common Object in Context) dataset is used in this comparative research to assess the effectiveness of the two algorithms and to analyze their strengths and weaknesses in terms of factors like accuracy, precision, and speed. Based on the findings analysis, it can be said that YOLO-v3 outperforms SSD in the same testing scenario. Keywords- Object Detection, Deep learning, CNN, COCO, YOLO, SSD

Gunshot detection neural network implemented on a low-cost microcontroller

Nowadays, criminal activity is on the rise, and it usually involves some type of firearm. There are automated shot detection systems but in the end, they still require human intervention to decide if it is an actual gunshot. Distinguishing between two similar sounds, such as the detonation of a firearm or a firecracker, is not always possible with the naked ear. There are multiple publications on artificial intelligence to identify gunshots; however, they use convolutional neural networks, which, despite being highly effective, require a system with extensive computational resources. This document presents a fully connected neural network implemented on a microcontroller that can identify up to 90% of firearm detonations. This document will be of interest to students or researchers interested in the design of neural networks for sound recognition on embedded systems.

Improved Particle Swarm Optimization with Deep Learning-Based Municipal Solid Waste Management in Smart Cities

Objectives: The Internet of Things (IoT) framework is crucial for improving monitoring applications for smart cities and controlling municipal operations in real time. The most significant issue with applications to smart cities has been the handling of solid waste, which may have negative consequences on the health and well-being of people. Waste management has become a problem that developing and developed nations must face. The management of solid waste is a significant and exciting issue that affects habitats all around the world. Thus, it is necessary to create an efficient method to eliminate these issues or, at the very least, reduce them to a manageable level. Theoretical framework: This work proposed an Improved Particle Swarm Optimization with Deep Learning-based Municipal Solid Waste Management (IPSODL-MSWM) in smart cities. Methods: The IPSODL-MSWM approach aims to identify various types of solid waste materials and enable sustainable waste management. A Single Shot Detection (SSD) model enables efficient object detection in the IPSODL-MSWM paradigm. Then, feature vectors were generated using the MobileNetV2 model based on a deep Convolutional Neural Network (CNN). IPSO has been obtained by using a hybrid Genetic Algorithm (GA) and PSO algorithm. Results and Conclusion: The IPSODL method has been employed for automatic hyperparameter tuning since manual trial-and-error hyperparameter tuning is time-consuming. Implications of the research: The IPSODL-MSWM approach uses Support Vector Machine (SVM) for accurate municipal excess categorization in this work. This implies sustainable waste management model for better smart city development. Originality/value: With an optimal accuracy of 99.45%, many simulations show the IPSODL-MSWM model's enhanced capability for classification.

One-shot learning Batak Toba character recognition using siamese neural network

Siamese neural network (SINN) is an image processing model that compares the scores of two patterns. The SINN algorithm is a combination of the use of the double convolutional neural network (CNN) algorithm. By combined SINN with a one-shot learning algorithm, we can build an image model without requiring thousands of images for training. The test results from the SINN algorithm and one-shot learning show that this process was successful in matching the two data but was unable to produce labels from the data being tested. Because of this, the researcher decided to continue the implementation process using the CNN algorithm combined with single shot detection (SSD). By using a dataset of 5000, the recognition and translation of the Toba Batak script was successful. The percentage of average accuracy results from CNN and SSD in recognizing Toba Batak characters is 84.08% for single characters and 74.13% for mixed characters. While the percentage of average accuracy results for testing the breadth first search algorithm is 75.725%.