Papers › DeepBall: Deep Neural-Network Ball Detector

DeepBall: Deep Neural-Network Ball Detector

19 Feb 2019arXiv:1902.07304archive 2025-07-28

Jacek Komorowski, Grzegorz Kurzejamski, Grzegorz Sarwas

The paper describes a deep network based object detector specialized for ball detection in long shot videos. Due to its fully convolutional design, the method operates on images of any size and produces \emph{ball confidence map} encoding the position of detected ball. The network uses hypercolumn concept, where feature maps from different hierarchy levels of the deep convolutional network are combined and jointly fed to the convolutional classification layer. This allows boosting the detection accuracy as larger visual context around the object of interest is taken into account. The method achieves state-of-the-art results when tested on publicly available ISSIA-CNR Soccer Dataset.

PaperPDFCode

Code

RvI101/Ball-Action-Recognition mentioned on GitHubtf report
RvI101/DeepBall-Keras mentioned on GitHubtf 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

General ClassificationObjectSports Ball Detection and Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sports Ball Detection and Tracking Badminton DeepBall Accuracy (%) 38.6 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Badminton DeepBall Average Precision (%) 60.0 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Badminton DeepBall F1 (%) 52.4 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball DeepBall Accuracy (%) 12.9 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball DeepBall Average Precision (%) 0 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Basketball DeepBall F1 (%) 0 #8 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer DeepBall Accuracy (% ) 92.7 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer DeepBall Average Precision (%) 26.3 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Soccer DeepBall F1 (%) 44.5 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis DeepBall Accuracy (%) 32.3 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis DeepBall Average Precision (%) 47.0 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Tennis DeepBall F1 (%) 47.4 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball DeepBall Accuracy (%) 50.7 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball DeepBall Average Precision (%) 49.2 #7 of 8 Archive leaderboard report
Sports Ball Detection and Tracking Volleyball DeepBall F1 (%) 64.4 #7 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