DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations

TL;DR

DeepSportradar-v1 introduces high-quality, annotated datasets and benchmarks for computer vision tasks in sports, specifically basketball, aiming to bridge the gap between research and real-world applications.

Contribution

It provides a comprehensive suite of datasets, benchmarks, and baseline methods for four challenging basketball-related computer vision tasks, fostering further research and development.

Findings

High-resolution datasets with detailed annotations

Baseline methods established for each task

Organized competition to promote advanced solutions

Abstract

With the recent development of Deep Learning applied to Computer Vision, sport video understanding has gained a lot of attention, providing much richer information for both sport consumers and leagues. This paper introduces DeepSportradar-v1, a suite of computer vision tasks, datasets and benchmarks for automated sport understanding. The main purpose of this framework is to close the gap between academic research and real world settings. To this end, the datasets provide high-resolution raw images, camera parameters and high quality annotations. 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. To encourage further research on advanced methods for sport understanding, a competition is organized as part of the MMSports workshop from the ACM Multimedia 2022 conference, where participants have to develop state-of-the-art methods to solve the above tasks. The four datasets, development kits and baselines are publicly available.