Retracted] Video Tactical Intelligence Analysis Method of Karate Competition Based on Convolutional Neural Network

Modern military environments place an increased emphasis on the collection and analysis of intelligence at the tactical level. The deployment of analytical tools at the tactical level helps support the Warfighter's need for rapid collection, analysis, and dissemination of intelligence. However, given the lack of experience and staffing at the tactical level, most of the available intelligence is not exploited. Tactical environments are staffed by a new generation of intelligence analysts who are well-versed in modern collaboration environments and social networking. An opportunity exists to enhance tactical intelligence analysis by exploiting these personnel strengths, but is dependent on appropriately designed information sharing technologies. Existing social information sharing technologies enable users to publish information quickly, but do not unite or organize information in a manner that effectively supports intelligence analysis. In this paper, we present an alternative approach to structuring and supporting tactical intelligence analysis that combines the benefits of existing concepts, and provide detail on a prototype system embodying that approach. Since this approach employs familiar collaboration support concepts from social media, it enables new-generation analysts to identify the decision-relevant data scattered among databases and the mental models of other personnel, increasing the timeliness of collaborative analysis. Also, the approach enables analysts to collaborate visually to associate heterogeneous and uncertain data within the intelligence analysis process, increasing the robustness of collaborative analyses. Utilizing this familiar dynamic collaboration environment, we hope to achieve a significant reduction of time and skill required to glean actionable intelligence in these challenging operational environments.

The current action recognition analysis method is easily affected by factors such as background, illumination, and target angle, which not only has low accuracy, but also relies on prior knowledge. Research on the identification and analysis of technical and tactical movements in football. According to the characteristics of football video, a multi-resolution three-dimensional convolutional neural network is constructed by combining the convolutional neural network and the three-dimensional neural network. The supervised training algorithm is used to update the network weights and thresholds, and the video images are input into the input layer. After the convolutional layer, sub-sampling layer and fully connected layer and other network layers to obtain action recognition results. The principal component analysis method is used to reduce the dimension to process the action data set, and the Fourier transform method is used to filter out the principal component noise. The experimental results show that the method can effectively identify the technical and tactical movements of athletes from complex football game videos, and analyze the applied technical and tactical strategies. The average value of accuracy, recall and precision of technical and tactical analysis is as high as 0.96, 0.97, and 0.95, and the recognition and analysis effect has significant advantages.

This paper attempts to develop a data mining tool to guide sports training, promote physical education and facilitate technical and tactical analysis. For this purpose, information techniques like mathematical statistics and big data analysis were employed to collect and analyse the information on competitive sports. Based on database and computer algorithm, the author designed a data mining tool applicable to the information of various competitive sports. The proposed tool can mine out valuable information from the big data, enabling trainers to realize targeted and efficient physical education. The mined information also helps improve the analysis of techniques and tactics of competitive sports. The research findings promote the application of information technology in physical education and competitive sports.

A survey was conducted with two sub-samples of respondents, karate athletes representatives (members of the national team) and karate athletes competitors in the kumite (sports fight). The survey was conducted on a stratified sample of 32 respondents divided into two groups, 16 karate representatives and 16 karate competitors, males, seniors from the Republic of Macedonia. The main purpose of the research is to determine the differences in the psychological characteristics between the two sub-samples of the respondents. In the research, a total of 13 variables for the assessment of psychological characteristics were applied: for estimation of emotional characteristics six (6) variables, three (3) variables for assessment of the motivational dispositions, for assessment of the specific intellectual characteristics (3) three variables and one variable for assessing the general intellectual characteristic. The basic statistical parameters are determined using the basic descriptive statistics for the two groups of respondents separately, while for determining the differences in the arithmetic means of the psychological characteristics, a T-test for small independent samples was applied. From the analysis of the data from the basic descriptive statistical parameters, it was established that in all applied variables, homogeneity of the results as well as normal distribution was obtained, with very small deviations present in two variables. The results of the T - test obtained in the survey show statistically significant differences in the entire analyzed space between the two groups, with the exception of two variables (L - social desire and P - psychoticism), i.e. differences were found in 11 variables from a total of 13 examined variables.

IntroductionThis paper presents an innovative Intelligent Robot Sports Competition Tactical Analysis Model that leverages multimodal perception to tackle the pressing challenge of analyzing opponent tactics in sports competitions. The current landscape of sports competition analysis necessitates a comprehensive understanding of opponent strategies. However, traditional methods are often constrained to a single data source or modality, limiting their ability to capture the intricate details of opponent tactics.MethodsOur system integrates the Swin Transformer and CLIP models, harnessing cross-modal transfer learning to enable a holistic observation and analysis of opponent tactics. The Swin Transformer is employed to acquire knowledge about opponent action postures and behavioral patterns in basketball or football games, while the CLIP model enhances the system's comprehension of opponent tactical information by establishing semantic associations between images and text. To address potential imbalances and biases between these models, we introduce a cross-modal transfer learning technique that mitigates modal bias issues, thereby enhancing the model's generalization performance on multimodal data.ResultsThrough cross-modal transfer learning, tactical information learned from images by the Swin Transformer is effectively transferred to the CLIP model, providing coaches and athletes with comprehensive tactical insights. Our method is rigorously tested and validated using Sport UV, Sports-1M, HMDB51, and NPU RGB+D datasets. Experimental results demonstrate the system's impressive performance in terms of prediction accuracy, stability, training time, inference time, number of parameters, and computational complexity. Notably, the system outperforms other models, with a remarkable 8.47% lower prediction error (MAE) on the Kinetics dataset, accompanied by a 72.86-second reduction in training time.DiscussionThe presented system proves to be highly suitable for real-time sports competition assistance and analysis, offering a novel and effective approach for an Intelligent Robot Sports Competition Tactical Analysis Model that maximizes the potential of multimodal perception technology. By harnessing the synergies between the Swin Transformer and CLIP models, we address the limitations of traditional methods and significantly advance the field of sports competition analysis. This innovative model opens up new avenues for comprehensive tactical analysis in sports, benefiting coaches, athletes, and sports enthusiasts alike.

The purpose of this study was to evaluate physiological performance parameters of the elite karate-kumite athletes via the simulated karate performance test (SKPT).Sixteen elite male karate athletes from The Turkish National Team participated in the study-(age: 23.31±4.27years, height: 173.4±4.91cm,weight: 68.8±8.17kg, BMI: 22.85±1.96kg/cm 2 ).The SKPT protocol included 5 sets of 3 minutes simulated karate competition bouts, which included randomly timed 4 karate techniques (2 hands and 2 foot) in 7 seconds.With higher level of performance, the duration of the attacks increased whereas the rest periods shortened, but the total duration of the level remained constant (3 minutes).The blood lactate concentrations, heart rate, ventilation and oxygen consumption of the athletes were evaluated pre, mid and post SKPT.Statistically significant differences were found in all recorded parameters (p<0.05).During the simulated test peak oxygen consumption values were 41,69 ± 4,82 ml/kg/min at the 9 th minute.Whereas heart rate, ventilation and oxygen consumption decreased to warm up values at the end of recovery, blood lactate values remained elevated during the whole recovery period.In conclusion, the simulation protocol implemented in this study has been found to produce physiological strain similar to real competition and can be used for performance evaluation of elite karate athletes.

Handwritten digit recognition, a task in computer vision, is critical for applications such as postal automation, banking, and digitization of forms. Traditional approaches have leveraged statistical models, but the rise of deep learning, particularly Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM), has revolutionized the field. However, a comprehensive performance comparison of CNN and LSTM architectures in the context of handwritten digit classification remains underexplored. This study aimed to address this gap by evaluating and comparing CNN and LSTM models for the classification of handwritten digits. Two machine learning models – Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) were trained with the preprocessed handwritten digit dataset. The CNN model was designed with multiple convolutional and pooling layers, along with dropout for regularization. The LSTM model was designed with LSTM layers to capture sequential patterns in the data, followed by a dense layer for classification. The models were implemented in python, evaluated and compared based on accuracy, precision, recall and F1-score. The evaluation and comparison results indicate that CNN achieved 99.31% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score, while LSTM achieved 98.90% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score. The results demonstrated that CNN outperformed LSTM in terms of accuracy and misclassification errors, making it the optimal choice for image-based handwritten digit recognition. This finding underscores the efficiency of CNN in addressing challenges related to digit recognition, contributing to the advancement of automated digit classification systems and improving the accuracy of image-based classification tasks.

Image registration is a challenging and critical task in computer vision and image processing. As the typical multi-modal image, infrared and visible image have greatly difference in gray scale, which makes the registration method based on hand-crafted features have a low accuracy. In this paper, we introduce a method based on hypercolumns and matching strategy. Combining different layers features in Convolutional Neural Network using hypercolumns, we can get more comprehensive and essential features to achieve a higher accuracy. Meanwhile we use coordinate difference acquired by automatic selection as the spatial distance constraint. Firstly, the key points are extracted by corner detection from the infrared and visible images. Then the features of the key points are extracted using the hypercolumns. Finally, similarity metric is performed by spatial geometric constraints. The experimental results show that the accuracy of our method is higher than that of the traditional method.

Nowadays, the information processing capabilities and resource storage capabilities of computers have been greatly improved, which also provides support for the neural network technology. Convolutional neural networks have good characterization capabilities in computer vision tasks, such as image recognition technology. Aiming at the problem of high similarity image recognition and classification in a specific field, this paper proposes a high similarity image recognition and classification algorithm fused with convolutional neural networks. First, we extract the image texture features, train different types, and different resolution image sets and determine the optimal texture different parameter values. Second, we decompose the image into subimages according to the texture difference, extract the energy features of each subimage, and perform classification. Then, the input image feature vector is converted into a one-dimensional vector through the alternating 5-layer convolution and 3-layer pooling of convolutional neural networks. On this basis, different sizes of convolution kernels are used to extract different convolutions of the image features, and then use convolution to achieve the feature fusion of different dimensional convolutions. Finally, through the increase in the number of training and the increase in the amount of data, the network parameters are continuously optimized to improve the classification accuracy in the training set and in the test set. The actual accuracy of the weights is verified, and the convolutional neural network model with the highest classification accuracy is obtained. In the experiment, two image data sets of gems and apples are selected as the experimental data to classify and identify gems and determine the origin of apples. The experimental results show that the average identification accuracy of the algorithm is more than 90%.

Hybrid Gabor Convolutional Networks

Convolutional Neural Networks (CNN) have dramatically boosted the performance of various computer vision tasks except visual tracking due to the lack of training data. In this paper, we pre-train a deep CNN offline to classify the 1 million images from 256 classes with very leaky non-saturating neurons for training acceleration, which is transformed to a discriminative classifier by adding an additional classification layer. In addition, we propose a novel approach for combining increasingly our CNN classifiers in a “cascade” structure through a modification of the AdaBoost framework, and then transfer the selected discriminative features from the ensemble of CNN classifiers to the robust visual tracking task, by updating online to robustly discard the background regions from promising object-like region to cope with appearance changes of the target. Extensive experimental evaluations on an open tracker benchmark demonstrate outstanding performance of our tracker by improving tracking success rate and tracking precision on an average of 9.2% and 13.9% at least over other state-of-the-art trackers.

Lossy image compression methods always introduce various unpleasant artifacts into the compressed results, especially at low bit-rates. In recent years, many effective soft decoding methods for JPEG compressed images have been proposed. However, to the best of our knowledge, very few works have been done on soft decoding of JPEG 2000 compressed images. Inspired by the outstanding performance of Convolution Neural Network (CNN) in various computer vision tasks, we presents a soft decoding method for JPEG 2000 by using multiple bit-rate-driven deep CNNs. More specifically, in training stage, we train a series of deep CNNs using lots of high quality training images and the corresponding JPEG 2000 compressed images at different coding bit-rates. In testing stage, for an input compressed image, the CNN trained with the nearest coding bit-rate is selected to perform soft decoding. Extensive experiments demonstrate the effectiveness of the presented soft decoding framework, which greatly improves the visual quality and objective scores of JPEG 2000 compressed images.

Automatic Optical Inspection (AOI) is any method of detecting defects during a Printed Circuit Board (PCB) manufacturing process. Early AOI methods were based on classic image processing algorithms using a reference PCB. The traditional methods require very complex and inflexible preprocessing stages. With recent advances in the field of deep learning, especially Convolutional Neural Networks (CNN), automating various computer vision tasks has been established. Limited research has been carried out in the past on using CNN for AOI. The present systems are inflexible and require a lot of preprocessing steps or a complex illumination system to improve the accuracy. This paper studies the effectiveness of using CNN to detect soldering bridge faults in a PCB assembly. The paper presents a method for designing an optimized CNN architecture to detect soldering faults in a PCBA. The proposed CNN architecture is compared with the state-of-the-art object detection architecture, namely YOLO, with respect to detection accuracy, processing time, and memory requirement. The results of our experiments show that the proposed CNN architecture has a 3.0% better average precision, has 50% less number of parameters and infers in half the time as YOLO. The experimental results prove the effectiveness of using CNN in AOI by using images of a PCB assembly without any reference image, any complex preprocessing stage, or a complex illumination system. Doi: 10.28991/HIJ-2022-03-01-01 Full Text: PDF

Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input images to score maps and keypoints can be selected with non-maximum suppression. This paper discusses and compares several recent methods that use CNNs for keypoint detection. Experiments are performed both on the CNN based approaches, as well as a selection of conventional methods. In addition to qualitative measures defined on keypoints and descriptors, the bag-of-words (BoW) model is used to implement an image retrieval application, in order to determine how the methods perform in practice. The results show that each type of features are best in different contexts.

Hearing disabilities affect people all over the world. Nearly 360 million people have a disabling hearing loss. In the recent years, there has been a rapid increase in the number of deaf and dumb victims due to birth defects, accidents and oral diseases. Since deaf and dumb people cannot communicate with a hearing person, they have to depend on some sort of visual communication. Sign Language is not understood by the majority of hearing people. The objective of our project is to form a bridge between the hearing-impaired community and the hearing community; to further commence a two-way communication. We propose a two-way sign language translator that converts Voice to sign language and vice versa in real time. We process the video frame by frame using the OpenCV Library in Python. Furthermore, we use background subtraction method called Gaussian Mixture-based Background/Foreground Segmentation Algorithm on each frame to subtract the background. Contours of this processed image are then passed into a Deep Neural Net (DNN) to classify the frame to the corresponding written language equivalent words. For conversion from sign language to voice, we use basic Natural Language Processing and gtts to accurately conserve the grammar in the sign language. The enrolment rate and literacy among the hearing-impaired children is far below the average for the population at large. This technology will then help the normal schools better integrate the hearing-impaired community thus making education more accessible and cheaper for them. Speech Emotion Recognition (SER) is a vital aspect of human-computer interaction and emotional intelligence applications. This SER that employs Mel- frequency cepstral coefficients (MFCC) as the basis for feature extraction, followed by a Convolutional Neural Network (CNN) with a customized architecture for emotion classification. The methodology 2 involves transforming audio samples into MFCC images, enabling the application of CNNs typically used in computer vision tasks. This fusion of traditional audio analysis with deep learning techniques harnesses the power of MFCC's spectral representation and CNN's spatial pattern recognition. By modifying the CNN architecture, the model can better discern emotional cues in the MFCC images, enhancing SER performance. This strategy offers SER a viable path forward, with the ability to identify complex emotional expressions. In order to increase the accuracy of emotion recognition, it tackles the requirement for feature-rich representations and sophisticated modelling techniques. KEYWORDS: OpenCV, DNN, SER, CNN, MFCC