Tactical Visualization in Basketball Using Smartphone Video and Homographic Projection

ABSTRACTAs an effective tool for simulating spatiotemporal urban processes in the real world, urban cellular automata (CA) models involve multiple data layers and complicated calibration algorithms, which make their computational capability become a bottleneck. Numerous approaches and techniques have been applied to the development of high-performance urban CA models, among which the integration of vectorization and parallel computing has broad application prospects due to its powerful computational ability and scalability. Unfortunately, this hybrid algorithm becomes inefficient when the axis-aligned bounding box (AABB) of study areas contains many unavailable cells. This paper presents a minimum-volume oriented bounding box (OBB) strategy to solve the above problem. Specifically, geometric transformation (i.e. translation and rotation) is applied to find the OBB of the study area before implementing the hybrid algorithm, and a set of functions are established to describe the spatial coordinate relationship between the AABB and OBB layers. Experiments conducted in this study demonstrate that the OBB strategy can further reduce the computational time of urban CA models after vectorization and parallelism. For example, when the cell size is 15 m and the neighborhood size is 3 × 3, an approximately 10-fold speedup in computational time can result from vectorization in the MATLAB environment, followed by an 18-fold speedup after implementing parallel computing in a quad-core processor and, finally, a speedup of 25-fold by further using an OBB strategy. We thus argue that OBB strategy can make the integration of vectorization and parallel computing more efficient and may provide scalable solutions for significantly improving the applicability of urban CA models.

It is sometimes necessary to determine the optimal value for a direction dependent quantity. Using a search technique based on Powell's quadratic convergent method such an optimal direction can be approximated. The necessary geometric transformations in n-dimensional space are introduced. As an example we consider the approximation of the minimum bounding box of a set of three-dimensional points. Minimum bounding boxes can significantly improve accuracy and efficiency of the calculations in modern brachytherapy treatment planning of the volumes of objects or the dose distribution inside an object. A covariance matrix based approximation method for the minimum bounding box is compared with the results of the search method. The benefits of the use of optimal oriented bounding boxes in brachytherapy treatment planning systems are demonstrated and discussed.

This experiment investigated the effects of arbitrary visual representation on team identification and informational influence in anonymous computer-mediated communication (CMC). In a 2 (participant's gender: male vs. female) × 2 (partner's character: male vs. female) between-subjects experiment (N = 193), participants played a trivia game with an ostensible partner via computer. Results showed that the participants exhibited stronger team affiliation with the partner when their character and the partner's represented the same gender, even though their own character mismatched their physical sex. Furthermore, team identification enhanced perceived competence of the partner and increased the private acceptance of the partner's opinions. Implications for the Social Identity Model of Deindividuation Effects (SIDE) and the referent informational influence theory are discussed.

In recent years, there has been an increasing growth of using vision-based systems for tracking the players in team sports to evaluate and enhance their performance. Vision-based player tracking has high computational demands since it requires processing of a huge amount of video data based on the utilization of multiple cameras with high resolution and high frame rates. In this paper, we present a reconfigurable system to track the players in indoor sports automatically without user interaction. The proposed system can process live video data streams from multiple cameras as well as offline data from recorded video files. FPGA technology is used to accelerate this player tracking system by implementing the video acquisition, video preprocessing, player segmentation, and team identification & player detection modules in hardware, realizing a real-time system. The teams are identified and the players' positions are detected based on the colors of their jerseys. The detection results are sent from the FPGA to the host-PC where the players are tracked. Our results show that the achieved average player detection rate is up to 95.5%. The proposed system can process live video data using two GigE Vision cameras with a resolution of 1392×1040 pixels and 30 fps for each camera. A speed-up of 20 is achieved compared to an OpenCV-based software implementation on a host-PC equipped with a 2.93 GHz Intel i7 CPU.

In recent years, there has been an increasing growth of using vision-based systems for tracking the players in team sports to evaluate and enhance their performance. Player tracking using vision systems is a very challenging task due to the nature of sports games, which includes severe and frequent interactions (e.g. occlusions) between the players. Additionally, these vision systems have high computational demands since they require processing of a huge amount of video data based on the utilization of multiple cameras with high resolution and high frame rate. As a result, most of the existing systems based on general-purpose computers are not able to perform online real-time player tracking, but track the players offline using pre-recorded video files, limiting, e.g., direct feedback on the player performance during the game. In this paper, we present a reconfigurable system to track the players in indoor sports automatically and without user interaction. The proposed system performs real-time processing of the incoming video streams from the cameras, achieving online player tracking. The teams are identified, and the players’ positions are detected based on the colors of their jerseys. FPGA technology is used to handle the compute-intensive vision processing tasks by implementing the video acquisition, video preprocessing, player segmentation, and team identification & player detection modules in hardware, realizing an online real-time system. While the pixel processing is performed in the FPGA, the less compute-intensive player tracking is performed on a general purpose computer. The maximum achieved frame rate for the FPGA implementation is 96.7 fps using a mature Xilinx Virtex-4 FPGA, and can be increased to 136.4 fps using a Xilinx Virtex-7 device. The Player tracking requires an average time of 2.5 ms per frame in the host-PC. As a result, the proposed reconfigurable system supports a maximum frame rate of 78.9 fps using two cameras with a resolution of 1392 × 1040 pixels each. Our results show that the achieved average precision and recall for player detection are up to 84.02% and 96.6%, respectively. Including player tracking, the achieved average precision and recall are up to 94.85% and 94.72%, respectively. Using the proposed FPGA implementation, a speedup by a factor of 15.2 is achieved compared to an OpenCV-based software implementation on a PC equipped with a 2.93 GHz Intel i7-870 CPU.

To achieve an accurate measurement of tread size after fixed-length cutting, this paper proposes a point-cloud-based tread size measurement method. Firstly, a mathematical model of corner points and a reprojection error is established, and the optimal solution of the number of corner points is determined by the non-dominated sorting genetic algorithm II (NSGA-II), which reduces the reprojection error of the RGB-D camera. Secondly, to address the problem of the low accuracy of the traditional pixel metric ratio measurement method, the random sampling consensus point cloud segmentation algorithm (RANSAC) and the oriented bounding box (OBB) collision detection algorithm are introduced to complete the accurate detection of the tread size. By comparing the absolute error and relative error data of several groups of experiments, the accuracy of the detection method in this paper reaches 1 mm, and the measurement deviation is between 0.14% and 2.67%, which is in line with the highest accuracy standard of the national standard. In summary, the RGB-D visual inspection method constructed in this paper has the characteristics of low cost and high inspection accuracy, which is a potential solution to enhance the pickup guidance of tread size measurement.

Whereas Deep Neural Network(DNN) shows wonderful performance on large scale data, lacking interpretability limits their usage in scenarios relevant to security. To make visual explanations less noisy and more class-discriminative, in this work, we propose a visual explanation method of DNN, named Exclusive Feature Constrained Class Activation Mapping(EFC-CAM). A new exclusive feature constraint is introduced to optimize the weight calculated from Grad-CAM or initialized from a constant vector. To better measure visual explanation methods, we design an effective evaluation metric which does not need bounding boxes as auxiliary information. Extensive quantitative experiments and visual inspection on ImageNet and Fashion validation set show the effectiveness of the proposed method.

Leadership is a fundamental aspect of team functioning across a broad range of performance domains including sport, physical activity, exercise, and health. Indeed, there is increasing recognition that high-quality leadership at all levels within organizations is crucial to the growth and performance of teams. Over the past 25 years, the majority of research has examined leadership from the perspective of the top-down approach that relies on a leadercentric approach. However, this only represents one aspect of leadership within performance domains. Equally important, although far less examined, is the concept of shared leadership within teams, specifically termed 'athlete leadership' or 'peer leadership'. Leaders within teams have been suggested to have significant impact upon a range of team-related factors including satisfaction, cohesion, team dynamics, performance, health, and well-being. There is limited clarity, however, regarding the best mechanisms through which to develop the leadership capacity and potential within a team. This research topic focuses on exploring shared leadership within a range of different contexts. Specifically seeking to better understand current knowledge, approaches to leadership development, and future avenues for research in the domain of shared leadership.The articles that compose this research topic explore a range of perspectives and approaches to better understand shared leadership, the impact that shared leadership can have within a group or team context, and also how to best develop the leaders of the future.In the first study in the research topic Wu and Cormican (2021) focus upon exploring both whether shared leadership is positively related to team effectiveness and also when shared leadership is more likely to be effective. The study specifically focuses on achieving this through the use of a social network analysis approach working with a number of Chinese design teams. One of the unique features of this study is that it is among the first to investigate the temporal factors that impact upon the effectiveness of shared leadership.In the second study Edelmann, Boen and Fransen (2020) explore the underpinning mechanisms of the relationships between formal leaders and their team members, specifically focused upon employees from a range of different sized organizations in Belgium. The study offers an interesting insight into the use of empowering leadership styles by formal leaders and the impact these leadership styles have upon work-related factors such as work satisfaction. In addition, the article considers the appropriateness of previously identified leadership styles in sport to a non-sporting / organizational context.In the next study Butalia et al. ( 2021) consider how predictive captain selection is of leadership quality and leader acceptance. Specifically, the authors explore the views of coaches and athletes from both Flemish football and volleyball teams. The study offers interesting insights into the range of leadership characteristics that might be required in order to positively impact upon leadership quality and leader acceptance in sports teams.In the fourth study De Backer et al. ( 2022) offer an interesting perspective on whether the behaviour of the coach impacts upon, or can be used as a predictor for, the quality of athlete leadership experienced. Building upon organizational justice theory and a social identity approach the study specifically focuses on Belgian volleyball and basketball players and whether the perceived justice of the coach predicts the quality of athlete leadership experienced by the players. In the penultimate study of the research topic Lopez-Garjardo et al. (2021) analyzed the relationship between athletes' perceptions of athlete leadership quality, team identification, inside sacrifice and performance with sports team players across a range of different sports including soccer, beach soccer, basketball and volleyball. The study explores player perceptions utilizing a cross-sectional design survey, offering import and interesting conclusions on relationships between perceived quality of athlete leaders, inside sacrifice, and perceived performance, and between inside sacrifice and perceived performance.In the final article of the research topic Cotterill, Loughead, and Fransen (2022) review the current state of knowledge and understanding relating to leadership and leader development with athlete leader populations. Reviewing contemporary examples and current understanding of approaches to athlete leadership development. Also highlighting future areas for research and applied practice development. Finally, the authors outline that while significant advances in understanding have been made there is still a long way to go, with further clarity required regarding the knowledge, skills and expertise required to undertake the athlete leadership roles in sport, and crucially to better understand how the development of current and future athlete leaders can be maximised.

Automatic Face recognition of people is a challenging problem which has received much attention during the recent years due to its potential multimedia applications in different fields such as 3D videoconference, security applications or video indexing. However, there is no technique that provides a robust solution to all situations and different applications, yet. Face recognition includes a set of challenges like expression variations, occlusions of facial parts, similar identities, resolution of the acquired images, aging of the subjects and many others. Among all these challenges, most of the face recognition techniques have evolved in order to overcome two main problems: illumination and pose variation. Either of these influences can cause serious performance degradation in a 2D face recognition system.Some of the new face recognition strategies tend to overcome both research topics from a 3D perspective. The 3D data points corresponding to the surface of the face may be acquired using different alternatives: A multi camera system (stereoscopy), structured light, range cameras or 3D laser and scanner devices The main advantage of using 3D data is that geometry information does not depend on pose and illumination and therefore the representation of the object does not change with these parameters, making the whole system more robust. However, the main drawback of the majority of 3D face recognition approaches is that they need all the elements of the system to be well calibrated and synchronized to acquire accurate 3D data (texture and depth maps). Moreover, most of them also require the cooperation or collaboration of the subject during a certain period of time. All these requirements can be available during the training stage of many applications. When enrolling a new person in the database, it could be performed off-line, with the help o human interaction and with the cooperation of the subject to be enrolled. On the contrary, the previous conditions are not always available during the test stage. The recognition will be in most of the cases in a semicontrolled or uncontrolled scenario, where the only input of the system will probably consists of a 2D intensity image acquired from a single camera. This leads to a new paradigm where 2D-3D mixed face recognition approaches are used. The idea behind this kind of approaches is that these take profit of the 3D data during the training stage but then they can use either 3D data (when available) or 2D data during the recognition stage. Belonging to this category, some of 2D statistical approaches like Eigenfaces of Fisherfaces have been extended to fit in this new paradigm leading to the Partial Principal Component Analysis (P2CA) approach. This algorithm intends to cope with big pose variations (±90 ∘) by using 180∘ cylindrical texture maps for training the system but then only images acquired from a single, normal camera are used for the recognition. These training images provide pose information from different views (2.5D data). Nevertheless they can also be extended to a complete 3D multimodal system where depth and texture information is used. This chapter is structured as follows: First, a brief overview of the state-of-the-art in face recognition is introduced. The most relevant methods are grouped by multimedia scenarios and concrete applications. Afterwards, novel 2D-3D mixed face recognition approaches will be introduced.KeywordsFace RecognitionLocal Binary PatternMultimedia ApplicationActive Appearance ModelFace SpaceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Damage due to cracking can be detected through either manual visual methods or machine vision techniques for early prevention and maintenance. In recent years, image-based deep learning methods have emerged as potent tools for automatic crack detection. In this study, five deep learning object detection algorithms—faster R-CNN, single-shot detector (SSD), You Only Look Once (YOLO) v3 and v8, and RetinaNet—were systematically compared, and the results were analyzed. Object detection involves the generation of bounding boxes of various sizes for objects of interest. Because cracks are thin and small and thus difficult to capture in a unique bounding box, redundant measurements are common, but they compromise the accuracy and consistency of the model. Therefore, an improved confusion matrix based on linear features was employed in this study to evaluate the crack detection performance of the five object detection algorithms. In evaluation experiments, the overall accuracy levels of SSD were 90.6% on visible atmospherically resistant index (VARI) images, indicating effective concrete crack detection performance. Notably, SSD excels in cases involving small cracks and data imbalance, thus demonstrating a high level of model stability. This comparative analysis of the performances of different deep learning algorithms in crack detection contributes to the formulation of methods for automatic damage detection.

Improving TB studies has long been a overlooked area, partly because of the complexities involved in getting the infection at risk. The novelty of this job lies in the strategy in which both computer vision methods and laboratory-based work are carried out to improve the human race. In this job, the gap between clinical research and technical studies has been decreased by bringing both the job together. Image processing is a field that does not require contact processes to be detected with patients. Over the previous two centuries, several algorithms have been created to extract the contours of homogeneous areas within the digital image. It is possible to acquire the input for image processing algorithms from scanned Lungs X-ray images. To detect the lung region, the fundamental image processing methods are applied to the CT scan picture. In this project, Image segmentation of the input pictures is carried out using a suggested technique developed from the K Means algorithm and bounding box algorithm along with Morphological Image Processing to acquire the output pictures and outcome comparison.

Vibration measurement is essential for vibration monitoring and control. Noncontact vibration measurement is more applicable in practice than the contact measuring manner, but the noncontact methods usually pose a high requirement in the light field environment. To solve this issue, a new binocular vision method is proposed to enable noncontact vibration measurement with different light fields. In this new method, the multitarget objects in the same image are first recognized by a YOLOv5 model to generate the bounding boxes; meanwhile, a depth image is generated through binocular vision and kept synchronized with the target image. Then, based on each bounding box and its corresponding depth image, an optimal depth value decision algorithm is developed to determine the 3-D real-time coordinates of each object. As a result, the vibration of multitarget objects can be measured simultaneously. An experimental test system was built to evaluate the performance of the proposed method in indoor and outdoor light fields. The tests demonstrate accurate vibration measuring results, and the proposed noncontact method is able to detect very low-frequency vibrations.

Precise lesion analysis to detect diabetic retinopathy using Generative Adversarial Network(GAN) and Mask-RCNN

Accurate food intake tracking is key to a healthy lifestyle, especially for managing diet-related illnesses. Traditional self-reporting methods are often unreliable due to memory and portion size estimation errors. This study introduces a new system that uses object detection and depth mapping to measure the volume of Filipino food items. The system uses a custom dataset with images of three food classes taken from top and side views, each annotated with bounding boxes. It employs the YOLOv8 model for accurate object detection and depth estimation to create 3D food models for precise volume calculation. Achieving 95.4% detection accuracy and a 7.8% average volume error, the system shows promise for dietary monitoring applications. Experimental results prove the system's ability to process the custom dataset effectively, achieving accurate object detection and volume estimations. Through the integration of innovative computer vision methods with culturally appropriate food data, this solution provides a promising method for boosting dietary monitoring and nutritional evaluation in the Filipino community setting. While the model performed well on the three predefined food classes, misclassification of non-target items (e.g., Biko) highlights the absence of a background or rejection class in the training dataset.

Artificial intelligence algorithms have proven capable of replicating cognitive processes. Our aim was to replicate human roadmap generation for endoscopic neurosurgery with a live image-based machine vision method. Surgical videos of a highly standardized surgical approach are labeled and used for algorithm training. After object detection (YOLOv7) to generate bounding boxes for landmark anatomical structures, an autoencoder first encodes the currently detected structures into an estimated position within this anatomical roadmap and then enables extrapolation of structures that are expected to be encountered in forward or backward directions. Average precision of the model applied to the test videos at an intersection-over-union threshold of 0.5 is reported. In total, 166 anonymized endoscopic recording (3 × 10 6 labeled video frames) were included. We performed model development using 146 videos and held out 20 videos for evaluation (test set). The performance regarding bounding box detection among the 20 test set videos on average was 53.4. Evaluation of the performance of the autoencoder model in detecting the current position within the roadmap of the surgical approach is evaluated semiquantitatively, showing that the first detection of anatomical structures by the model corresponds well to their label distribution along the latent variable encoding the anatomical roadmap. We also provide videos demonstrating the mixed reality head's up display for anatomical navigation. Our method enables reliable identification of key anatomical structures during endoscopic endonasal trans-sphenoidal surgery in mixed reality. Through encoding detected landmark anatomical structures, a surgical roadmap is encoded. This approach allows for detection of visible anatomical structures and enables extrapolation toward the location of those yet to be dissected in deeper anatomical layers. Further development of such algorithms may pave the way toward adding a mixed reality, real-time anatomical navigation software to the neurosurgeon's armamentarium.