Sports Understanding

DeepSportradar is a benchmark suite of computer vision tasks, datasets and benchmarks for automated sport understanding. DeepSportradar currently supports four challenging tasks related to basketball: ball 3D localization, camera calibration, player instance segmentation and player re-identification. For each of the four tasks, a detailed description of the dataset, objective, performance metrics, and the proposed baseline method are provided. Source: DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations Image Source: https://github.com/deepsportradar/instance-segmentation-challenge

The sports industry is witnessing an increasing trend of utilizing multiple synchronized sensors for player data collection, enabling personalized training systems with multi-perspective real-time feedback. Badminton could benefit from these various sensors, but there is a scarcity of comprehensive badminton action datasets for analysis and training feedback. Addressing this gap, this paper introduces a multi-sensor badminton dataset for forehand clear and backhand drive strokes, based on interviews with coaches for optimal usability. The dataset covers various skill levels, including beginners, intermediates, and experts, providing resources for understanding biomechanics across skill levels. It encompasses 7,763 badminton swing data from 25 players, featuring sensor data on eye tracking, body tracking, muscle signals, and foot pressure. The dataset also includes video recordings, detailed annotations on stroke type, skill level, sound, ball landing, and hitting location, as well as survey and interview data. We validated our dataset by applying a proof-of-concept machine learning model to all annotation data, demonstrating its comprehensive applicability in advanced badminton training and research.

Dataset Description High-level explanation of dataset characteristics: This dataset includes electromyographic (EMG) signals captured using the BiTalino device. EMG signals were recorded during three conditions: rest, additional weight exercise, and squat activity. Data were collected from four young subjects aged between 20 and 24 years, including both athletes and non-athletes. Motivations and summary of its content: The collection of this data focuses on understanding muscular responses, specifically around the anterior cruciate ligament (ACL), during different types of exercise. The information obtained aims to contribute to the development of predictive models for muscular injuries and enhance the effectiveness of training and treatment programs. Potential use cases of the dataset: This dataset can be used to develop predictive models that assess the risk of muscular injuries around the ACL using EMG signal analysis. Additionally, it can be employed to optimize personalized training programs, monitor muscular recovery, and improve biomechanics in both athletes and non-athletes. ### Methodology Materials: For precise capture of EMG signals, a BiTalino device was used configured at a sampling frequency of 1 kHz. This device utilizes three electrodes to acquire EMG signals. Data acquisition: Four young volunteers, two athletes, and two non-athletes aged between 20 and 24 years were recruited. EMG signals were recorded during three tests: rest, basic squats, and squats with additional weight. Standard electrode placement procedures were followed to minimize noise and ensure measurement accuracy. Signal processing: Raw EMG data were converted to millivolts (mV) using the formula provided by BiTalino to normalize signal amplitude. Subsequently, filters were applied to remove environmental noise and highlight relevant characteristics of muscle activity. ### Results Various metrics derived from EMG signals were analyzed, including mean frequency, average peak amplitude, and average envelope amplitude. Results indicated significant differences between athletes and non-athletes in terms of muscle activation during different exercise conditions. ### Conclusions This project aims to develop predictive models based on EMG signal analysis to assess the risk of muscular injuries around the ACL. It is expected that these tools will provide a solid scientific foundation for the prevention and treatment of sports injuries, benefiting coaches, physiotherapists, and sports physicians in making informed decisions. ### Source Document where the dataset was presented: README OF THE PAPER

Sport is one of the most popular and revenue-generating forms of entertainment. Therefore, analyzing data related to this domain introduces several opportunities for Question Answering (QA) systems, such as supporting tactical decision-making. But, to develop and evaluate QA systems, researchers and developers need datasets that contain questions and their corresponding answers. In this paper, we focus on this issue. We propose QASports, the first large sports question answering dataset for extractive answer questions. QASports contains more than 1.5 million triples of questions, answers, and context about three popular sports: soccer, American football, and basketball. We describe the QASports processes of data collection and questions and answers generation. We also describe the characteristics of the QASports data. Furthermore, we analyze the sources used to obtain raw data and investigate the usability of QASports by issuing "wh-queries". Moreover, we describe scenarios for using QASports, highlighting its importance for training and evaluating QA systems.