# Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion

arXiv: https://arxiv.org/abs/1906.02042 · HTML: https://mlsanity.com/paper/1906.02042/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports](https://mlsanity.com/paper/2306.13074/) (2023)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [Player Tracking and Identification in Ice Hockey](https://mlsanity.com/paper/2110.03090/) (2021)
- [Basketball-SORT: An Association Method for Complex Multi-object Occlusion Problems in Basketball Multi-object Tracking](https://mlsanity.com/paper/2406.19655/) (2024)
- [TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos](https://mlsanity.com/paper/2503.18282/) (2025)
- [Optical tracking in team sports](https://mlsanity.com/paper/2204.04143/) (2022)
- [Automated player identification and indexing using two-stage deep learning network](https://mlsanity.com/paper/2204.13809/) (2022)
- [Evaluating deep tracking models for player tracking in broadcast ice hockey video](https://mlsanity.com/paper/2205.10949/) (2022)
- [See It Before You Grab It: Deep Learning-based Action Anticipation in Basketball](https://mlsanity.com/paper/2512.15386/) (2025)

## Abstract (arXiv)

Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.