Next Article in Journal
Noise Radar Technology: Waveforms Design and Field Trials
Next Article in Special Issue
The Q-Pass Index: A Multifactorial IMUs-Based Tool to Assess Passing Skills in Basketball
Previous Article in Journal
Objective Assessment of Regional Stiffness in Vastus Lateralis with Different Measurement Methods: A Reliability Study
Previous Article in Special Issue
Quantitative and Qualitative Running Gait Analysis through an Innovative Video-Based Approach
Article

Enhancement of Speed and Accuracy Trade-Off for Sports Ball Detection in Videos—Finding Fast Moving, Small Objects in Real Time

1
Institute of Computer Science, Leipzig University, 04109 Leipzig, Germany
2
Machine Learning and Data Analytics Lab, Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91052 Erlangen, Germany
3
Media Seasons, 04105 Leipzig, Germany
4
Faculty of Computer Science and Media, Leipzig University of Applied Sciences, 04277 Leipzig, Germany
*
Author to whom correspondence should be addressed.
Academic Editor: Basilio Pueo
Sensors 2021, 21(9), 3214; https://doi.org/10.3390/s21093214
Received: 15 February 2021 / Revised: 25 April 2021 / Accepted: 26 April 2021 / Published: 6 May 2021
(This article belongs to the Collection Sensor Technology for Sports Science)
The detection and localization of the ball in sport videos is crucial to better understand events and actions occurring in those sports. Despite recent advances in the field of object detection, the automatic detection of balls remains a challenging task due to the unsteady nature of balls in images. In this paper, we address the detection of small, fast-moving balls in sport video data and introduce a real-time ball detection approach based on the YOLOv3 object detection model. We apply specific adjustments to the network architecture and training process in order to enhance the detection accuracy and speed: We facilitate an efficient integration of motion information, avoiding a complex modification of the network architecture. Furthermore, we present a customized detection approach that is designed to primarily focus on the detection of small objects. We integrate domain-specific knowledge to adapt image pre-processing and a data augmentation strategy that takes advantage of the special features of balls in images in order to improve the generalization ability of the detection network. We demonstrate that the general trade-off between detection speed and accuracy of the YOLOv3 model can be enhanced in consideration of domain-specific prior knowledge. View Full-Text
Keywords: sports ball detection; small object detection; YOLO; data augmentation; speed-accuracy trade-off sports ball detection; small object detection; YOLO; data augmentation; speed-accuracy trade-off
Show Figures

Figure 1

MDPI and ACS Style

Hiemann, A.; Kautz, T.; Zottmann, T.; Hlawitschka, M. Enhancement of Speed and Accuracy Trade-Off for Sports Ball Detection in Videos—Finding Fast Moving, Small Objects in Real Time. Sensors 2021, 21, 3214. https://doi.org/10.3390/s21093214

AMA Style

Hiemann A, Kautz T, Zottmann T, Hlawitschka M. Enhancement of Speed and Accuracy Trade-Off for Sports Ball Detection in Videos—Finding Fast Moving, Small Objects in Real Time. Sensors. 2021; 21(9):3214. https://doi.org/10.3390/s21093214

Chicago/Turabian Style

Hiemann, Alexander, Thomas Kautz, Tino Zottmann, and Mario Hlawitschka. 2021. "Enhancement of Speed and Accuracy Trade-Off for Sports Ball Detection in Videos—Finding Fast Moving, Small Objects in Real Time" Sensors 21, no. 9: 3214. https://doi.org/10.3390/s21093214

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop