Implementation and Analysis of a Computer Vision-Based Ball Detection System for Robot Soccer in ROS Simulation
DOI:
https://doi.org/10.25139/ijair.v7i1.10502Keywords:
Computer Vision, Deep Learning, Soccer Robot, Ball Detection, YOLO AlgorithmAbstract
This research investigates a computer vision-based ball detection system designed for robotic soccer applications, with a focus on assessing its efficiency across varying distances from 1 to 12 meters. The study utilizes the YOLOO (You Only Look Once) algorithm to evaluate the robot's detection accuracy, response times, and navigational performance in real time. A dataset composed of 3,400 images was created to facilitate the training and validation of the detection system under diverse lighting conditions. Findings revealed that the system achieved optimal detection accuracy of 70% at 1 meter, which decreased to 31% as the distance increased to 12 meters. The average response time for detection was recorded at 120 milliseconds for close distances, escalating to 228 milliseconds for farther distances. These results indicate the necessity for further enhancements in computer vision capabilities to improve interaction in dynamic settings such as robotic soccer. The study underscores both the potential and limitations of current detection methodologies, offering pathways for future advancements in robotic automation within competitive environments.
Downloads
References
M. Rizal and R. Rahmat, "Advancements in Edge Detection Techniques for Image Processing Systems," International Journal of Artificial Intelligence and Robotics, vol. 3, no. 1, pp. 1-12, 2021.
H. Susilawati and L. Putri, "Bolt Detection on Railway Rails Using ResNet-50 V1 with SSD: A Deep Learning Approach," International Journal of Artificial Intelligence and Robotics, vol. 5, no. 1, pp. 23-30, 2023.
H. Zhang, A. Z. Sun, and Y. P. P. V. Y. Xu, "A Robust Detection Method Based on YOLOv3 for Soccer Robots," IEEE Access, vol. 9, pp. 19612-19625, 2021.
M. K. L. P. Tan, J. Y. H. Kho, and B. C. K. Tan, "Real-Time Ball Detection for Soccer Robots," in Proceedings of ICCAS, pp. 176-181, 2019.
R. Pourhasan and A. Ghaffari, "Computer Vision Algorithms for Object Tracking in Soccer Games," International Journal of Computer Vision and Image Processing, vol. 10, no. 4, pp. 10-24, 2020.
S. Hussain and M. Khalid, "Robust Object Tracking Based on Deep Learning Techniques," Journal of Robotics, vol. 5, no. 3, pp. 45-58, 2021.
R. Singh and A. Jain, "Real-Time Object Detection Using SSD and MobileNet," International Journal of Advanced Research in Computer Science, vol. 12, no. 1, pp. 23-30, 2021.
A. D. Sari and H. Setiawan, "Development of a Soccer Robot Simulator Using Image Processing Techniques," International Journal of Robotics and Automation, vol. 3, no. 1, pp. 89-95, 2022.
J. Wang and Y. Liu, "A Survey on Object Detection Methods: Comprehensive Overview of the State of the Art," Journal of Artificial Intelligence Research, vol. 75, pp. 45-78, 2022.
R. A. K. Rahman and R. H. A. Rahim, "Image Processing Techniques for Sports Applications," International Journal of Computer Applications, vol. 164, no. 12, pp. 1-8, 2013.
S. C. A. Omoregie and O. M. Ogwueleka, "Detection and Classification of Soccer Balls Using Image Processing Techniques," International Journal of Engineering Research and Technology, vol. 9, no. 1, pp. 25-32, 2020.
M. G. G. Z. Al-Najjar, M. Shawkat, and A. S. Jebril, "Real-Time Detection of Soccer Ball Using OpenCV," Journal of Machine Learning and Computing, vol. 8, no. 3, pp. 52-56, 2018.
R. Gupta and A. N. Sharma, "A Survey of Object Detection Techniques in Computer Vision," International Journal of Robotics and Automation, vol. 2, no. 2, pp. 1-11, 2018.
K. R. S. S. T. Thakur and R. S. Jain, "Smart Ball Detection and Tracking in Soccer using Deep Learning," International Journal of Computer Applications, vol. 975, no. 8887, pp. 13-18, 2020.
O. Michalek, M. S. Patel, and B. R. S. N. Tullio, "A Comparative Study of Tracking Algorithms for Object Detection in Sports," Sensors, vol. 21, no. 2, pp. 63-75, 2021.
N. D. O. Canadas and K. B. B. L. O. Goncalves, "Real-Time Object Detection for Robotic Soccer Using a Modified YOLOv4," Journal of Robotics, vol. 78, pp. 123-136, 2021.
Y. X. S. Y. Kim, T. Y. S. Lee, and J. C. R. Lee, "Deep Learning Approaches for Soccer Ball Detection," International Journal of Sports Engineering and Technology, vol. 10, no. 4, pp. 1-10, 2022.
R. A. S. I. Abu, R. P. A. Rahman, and Z. A. E. Ismail, "Automated Soccer Ball Detection Using Machine Learning Techniques," International Journal of Advanced Computer Science and Applications, vol. 10, no. 9, pp. 78-86, 2019.
H. F. S. Savage and P. Z. H. Wong, "Application of Deep Learning in Vision-Based Robotics – A Survey," Robotics and Autonomous Systems, vol. 102, pp. 123-129, 2018.
S. H. S. Hanafi and S. O. M. Ali, "Dynamic Ball Detection for Soccer Robots Using CNN," Journal of Robotic Systems, vol. 5, no. 1, pp. 33-47, 2021.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with International Journal of Artificial Intelligence & Robotics (IJAIR) agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
