Browse » Sports » Basketball

Top Basketball Datasets

Basketball datasets and computer vision models can be used to provide real-time analytics and post-game analysis of key basketball statistics. You can use computer vision for automatically gather data from college (i.e NCAA) or professional (i.e NBA) games such as number of passes, number of shots, possession time of a team, possession time of a player, assists, dunks and much more. See an example tutorial video of using computer vision to track players using YOLOv5:

A compilation of many pictures of basketballs. Sourced for use in the Eagle Eye Capstone project.

Here are a few use cases for this project:

  1. Sports Analytics: Use the "Basketball Players" model to automatically track players' movements, ball possession, and referee decisions during live games or post-game analysis. This data can be used by coaches, analysts, and teams to inform and improve strategies, tactics, and player performance.

  2. Real-time Game Commentary: Integrate the model into sports broadcasting platforms, providing real-time updates and statistics to commentators, allowing them to focus on in-depth analysis and storytelling while the model handles identification and stat-tracking.

  3. Automated Sports Highlights: Utilize the model to automatically create highlights from basketball games by identifying key moments, such as successful shots, blocks, and referee decisions. This can streamline post-production process for sports media outlets and social media channels.

  4. Training and Skill Development: Leverage the "Basketball Players" model to create feedback tools for players, identifying areas of improvement in team dynamics and individual technique during practice sessions or games.

  5. Fan Experience: Employ the model in smartphone apps or AR devices, providing fans with real-time information on their favorite teams and players during live games, enhancing their overall experience and engagement.

Here are a few use cases for this project:

  1. Automatic Game Analysis: Analyze basketball matches in real-time or post-game to provide insights such as player movements, ball possession, and scoring opportunities. This could benefit sports analysts, coaches, and teams in improving their strategies and understanding of individual players' performance.

  2. Player Performance Tracking: Monitor and evaluate individual player performance during practice sessions or games using identified player and ball classes. This could help in personalized training, skill development, and detecting strengths and weaknesses of each player.

  3. Crowd Management and Security: Enhance stadium security and manage crowds during basketball events. The model can be used to detect unauthorized persons entering the court, monitor player and crowd interactions, and ensure overall safety during games.

  4. Interactive Basketball Applications: Develop interactive apps or games that use augmented reality (AR) or virtual reality (VR) to simulate real-life basketball playing experiences. The computer vision model could help track ball movement and player positions for a more immersive and realistic gaming experience.

  5. Marketing and Advertising: Analyze audience engagement during basketball games for targeted marketing and advertising campaigns. By detecting the presence of specific players, the model could help identify the most popular players and recommend athlete endorsements or product placements to relevant brands.

VOT2015 Dataset

The dataset comprises 60 short sequences showing various objects in challenging backgrounds. The sequences were chosen from a large pool of sequences including the ALOV dataset, OTB2 dataset, non-tracking datasets, Computer Vision Online, Professor Bob Fisher’s Image Database, Videezy, Center for Research in Computer Vision, University of Central Florida, USA, NYU Center for Genomics and Systems Biology, Data Wrangling, Open Access Directory and Learning and Recognition in Vision Group, INRIA, France. The VOT sequence selection protocol was applied to obtain a representative set of challenging sequences. The dataset is automatically downloaded by the evaluation kit when needed, there is no need to separately download the sequences for the challenge.

Annotations The sequences were annotated by the VOT committee using rotated bounding boxes in order to provide highly accurate ground truth values for comparing results. The annotations are stored in a text file with the format:

frameN: X1, Y1, X2, Y2, X3, Y3, X4, Y4 where Xi and Yi are the coordinates of corner i of the bounding box in frame N, the N-th row in the text file.

The bounding box was be placed on target such that at most ~30% of pixels within the bounding box corresponded to the background pixels, while containing most of the target. For example, in annotating a person with extended arms, the bounding box was placed such that the arms were not included. Note that in some sequences parts of objects rather than entire objects have been annotated. A rotated bounding box was used to address non-axis alignment of the target. The annotation guidelines have been applied at the judgement of the annotators.

Some targets were partially occluded or were partially out of the image frame. In these cases the bounding box were “inferred” by the annotator to fully contain the object, including the occluded part. For example, if a person’s legs were occluded, the bounding box should also include the non-visible legs.

The annotations have been conducted by three groups of annotators. Each annotator group annotated one third of the dataset and these annotations have been cross-checked by two other groups. The final annotations were checked by the coordinator of the annotation process. The final bounding box annotations have been automatically rectified by replacing a rotated bounding box by an axis-aligned if the ratio of the shortest and longest bounding-box side exceeded 0.95.


Gustavo Fernandez (coordinator) Jingjing Xiao Georg Nebehay Roman Pflugfelder Koray Aytac