Detecting and Tracking Player in Football Videos Using Two-Stage Mask R-CNN Approach

Amir Mahmud Husein; Chalvin; Kalvintirta Ciptady Ciptady; Raymond  Suryadi; Mawaddah  Harahap

doi:10.34306/conferenceseries.v4i1.643

Authors

Amir Mahmud Husein Prima Indonesia University
Chalvin Prima Indonesia University
Kalvintirta Ciptady Ciptady Prima Indonesia University
Raymond Suryadi Prima Indonesia University
Mawaddah Harahap Prima Indonesia University

DOI:

https://doi.org/10.34306/conferenceseries.v4i1.643

Keywords:

Deep Learning, DenseNet, Football, ResNet-101, Mask R-CNN

Abstract

Football is one of the most popular sports worldwide and capable of attracting the attention of millions of fans to a single match in the top leagues. The English Premier League, Spanish LaLiga, German Bundesliga, Italian Serie A, and French Ligue 1 are the five best leagues in the world today. There was an experiment where researchers want to analyze the efficiency and accuracy percentage of tracking and detection using the deep learning method of the Mask R-CNN model in classifying positive and negative X-Ray images in football matches. In this study, we applied Mask R-CNN for the segmentation and detection of football players. This model was based on two different backbones, namely ResNet101 and DenseNet. Both backbones produced accuracy values that were not significantly different, but the DenseNet approach performed better than ResNet101 based on testing results in the validation and testing sets. Based on comprehensive experiment results on the dataset, it has been shown that the Mask R-CNN approach with DenseNet can achieve better results compared to Mask R-CNN with ResNet101. Due to insufficient understanding of the characteristics of image types and the uneven distribution of various types of data sourced from random videos, there was still room for improvement in the trained model.

References

Sun P, Zhao X, Zhao Y, Jia N, Cao D. Intelligent Optimization Algorithm of 3D Tracking Technology in Football Player Moving Image Analysis. Wirel Commun Mob Comput. 2022;2022(1).

A. G. Prawiyogi, M. Hammet, and A. Williams, “Visualization Guides in the Understanding of Theoretical Material in Lectures,” Int. J. Cyber IT Serv. Manag., vol. 3, no. 1, pp. 54–60, 2023.

Radke D, Orchard A. Presenting Multiagent Challenges in Team Sports Analytics Blue Sky Ideas Track. Proc Int Jt Conf Auton Agents Multiagent Syst AAMAS. 2023;2023-May:1781–5.

D. Iriani, S. Parman, A. F. Hafizh, I. Rachmawati, and Y. A. Solihah, “Ambient Media Advertisement of Catur Insan Cendekia University to Improve Brand Awareness,” ADI J. Recent Innov., vol. 5, no. 1Sp, pp. 97–110, 2023.

Liu N, Liu L, Sun Z. Football Game Video Analysis Method with Deep Learning. Comput Intell Neurosci. 2022;2022.

K. Diantoro, D. Supriyanti, Y. P. A. Sanjaya, and S. Watini, “Implications of Distributed Energy Development in Blockchain-Based Institutional Environment,” Aptisi Trans. Technopreneursh., vol. 5, no. 2sp, pp. 209–220, 2023.

Yang T, Jiang C, Li P. Video Analysis and System Construction of Basketball Game by Lightweight Deep Learning under the Internet of Things. Comput Intell Neurosci. 2022;2022.

B. P. K. Bintoro, N. Lutfiani, and D. Julianingsih, “Analysis of the Effect of Service Quality on Company Reputation on Purchase Decisions for Professional Recruitment Services,” APTISI Trans. Manag., vol. 7, no. 1, pp. 35–41, 2023.

Du Y, Zhao Q, Lu X. Semantic Extraction of Basketball Game Video Combining Domain Knowledge and In-Depth Features. Sci Program. 2021;2021.

S. B. Goyal, E. P. Harahap, and N. A. Santoso, “Analysis of financial technology implementation on the quality of banking services in indonesia: Swot analysis,” IAIC Trans. Sustain. Digit. Innov., vol. 4, no. 1, pp. 77–82, 2022.

He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell. 2020;42(2):386–97.

Q. Aini, I. Sembiring, A. Setiawan, I. Setiawan, and U. Rahardja, “Perceived Accuracy and User Behavior: Exploring the Impact of AI-Based Air Quality Detection Application (AIKU),” Indones. J. Appl. Res., vol. 4, no. 3, pp. 209–218, 2023.

Garza G. Mask R-CNN for Ship Detection & Segmentation. Towar Data Sci. 2019;

Kulkarni KM, Shenoy S. Table tennis stroke recognition using two-dimensional human pose estimation. IEEE Comput Soc Conf Comput Vis Pattern Recognit Work. 2021;4571–9.

U. Rahardja, Q. Aini, P. A. Sunarya, D. Manongga, and D. Julianingsih, “The Use of TensorFlow in Analyzing Air Quality Artificial Intelligence Predictions PM2. 5,” Aptisi Trans. Technopreneursh., vol. 4, no. 3, pp. 313–324, 2022.

Hurault S, Ballester C, Haro G. Self-Supervised Small Soccer Player Detection and Tracking. MMSports 2020 - Proc 3rd Int Work Multimed Content Anal Sport. 2020;20:9–18.

Wang T, Li T. Deep Learning-Based Football Player Detection in Videos. Comput Intell Neurosci. 2022;2022.

Liu J. Convolutional Neural Network-Based Human Movement Recognition Algorithm in Sports Analysis. Front Psychol. 2021;12.

Liu T, García-de-Alcaraz A, Wang H, Hu P, Chen Q. Impact of Scoring First on Match Outcome in the Chinese Football Super League. Front Psychol. 2021;12.

Uchida I, Scott A, Shishido H, Kameda Y. Automated offside detection by spatio-temporal analysis of football videos. MMSports 2021 - Proc 4th Int Work Multimed Content Anal Sport co-located with ACM MM 2021. 2021;17–24.

S. Mehta and L. Magdalena, “Education 4.0: Online Learning Management Using Education Smart Courses,” IAIC Trans. Sustain. Digit. Innov., vol. 4, no. 1, pp. 70–76, 2022.

Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2017;39(6):1137–49.

A. Gunawan and R. K. Hudiono, “Industrial Revolution 4.0’s Information Technology’s Impact on the Growth of MSMEs in the Manufacturing Industries Sector,” Int. Trans. Educ. Technol., vol. 1, no. 2, pp. 157–164, 2023.

Liu H, Aderon C, Wagon N, Liu H, MacCall S, Gan Y. Deep Learning-based Automatic Player Identification and Logging in American Football Videos. 2022; Available from: http://arxiv.org/abs/2204.13809

Wei CT, Weng SK. A court line extraction algorithm for badminton tournament videos with horizontal line projection learning. IET Image Process. 2023;17(10):2907–24.