Papers › Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup

Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup

23 Jul 2020arXiv:2007.11876archive 2025-07-28

Gabriel Van Zandycke, Christophe De Vleeschouwer

This paper considers the task of detecting the ball from a single viewpoint in the challenging but common case where the ball interacts frequently with players while being poorly contrasted with respect to the background. We propose a novel approach by formulating the problem as a segmentation task solved by an efficient CNN architecture. To take advantage of the ball dynamics, the network is fed with a pair of consecutive images. Our inference model can run in real time without the delay induced by a temporal analysis. We also show that test-time data augmentation allows for a significant increase the detection accuracy. As an additional contribution, we publicly release the dataset on which this work is based.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

pacifinapacific/awesome_sportanalysis_paper mentioned on GitHubSyntology: not harvested report
nttcom/wasb-sbdt pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationSports Ball Detection and Tracking

Datasets

Introduced by this paper, per the archive.

DeepSport Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sports Ball Detection and Tracking Badminton BallSeg Accuracy (%) 72.2 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Badminton BallSeg Average Precision (%) 68.4 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Badminton BallSeg F1 (%) 79.9 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball BallSeg Accuracy (%) 20.5 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball BallSeg Average Precision (%) 5.3 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball BallSeg F1 (%) 16.8 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer BallSeg Accuracy (% ) 92.6 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer BallSeg Average Precision (%) 20.0 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer BallSeg F1 (%) 36.1 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis BallSeg Accuracy (%) 57.5 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis BallSeg Average Precision (%) 56.8 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis BallSeg F1 (%) 71.7 #6 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball BallSeg Accuracy (%) 17.5 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball BallSeg Average Precision (%) 8.5 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball BallSeg F1 (%) 19.5 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections