Ball Detection Algorithms Enhancement in Sport Robots
Mohammad Esfandiarpour, Seyed Mani Mirshabani, Ehsan Maani Miandoab
- 发表年份
- 2024
- 引用次数
- 6
摘要
This paper presents a comparative analysis of four different ball detection algorithms that can be utilized in a wide range of sports robots. The study compares the performance of these algorithms in terms of accuracy, robustness, noise sensitivity, and computational time consumption. Studied algorithms are Color detection, Hough Circle, Frame differencing, and YOLOv8. Additionally, to overcome the algorithms’ drawbacks, two different combinations of algorithms are proposed. The first approach is a combination of color detection and Hough circle, and the other one is a combination of color detection and YOLO. Then, these two hybrid methods are compared to previous algorithms and it is revealed that proposed algorithms are more accurate and efficient than well-known object detection algorithms. Employing these algorithms will lead to more accuracy in sports robots.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002