Deep Learning-Based Algorithm for Recognizing Tennis Balls

Abstract

In this paper, we adjust the hyperparameters of the training model based on the gradient estimation theory and optimize the structure of the model based on the loss function theory of Mask R-CNN convolutional network and propose a scheme to help a tennis picking robot to perform target recognition and improve the ability of the tennis picking robot to acquire and analyze image information. By collecting suitable image samples of tennis balls and training the image samples using Mask R-CNN convolutional network an algorithmic model dedicated to recognizing tennis balls is output; the final data of various loss functions after gradient descent are recorded, the iterative graph of the model is drawn, and the iterative process of the neural network at different iteration levels is observed; finally, this improved and optimized algorithm for recognizing tennis balls is compared with other algorithms for recognizing tennis balls and a comparison is made. The experimental results show that the improved algorithm based on Mask R-CNN recognizes tennis balls with 92% accuracy between iteration levels 30 and 35, which has higher accuracy and recognition distance compared with other tennis ball recognition algorithms, confirming the feasibility and applicability of the optimized algorithm in this paper.

Optimization of table tennis target detection algorithm guided by multi-scale feature fusion of deep learning

“…Wu et al (2022) optimized the structure of Mask R-CNN, helped tennis picking robot to perform target recognition, and improved its ability to acquire and analyze image information. The experimental results show that the improved algorithm based on Mask R-CNN achieves 92% accuracy in tennis recognition at the iteration level of 30 to 35, which is higher in accuracy and recognition distance than other tennis recognition algorithms 42 . Peng et al (2023) proposed a heart rate measurement method based on face recognition.…”

Recognizing and Recovering Ball Motion Based on Low-Frame-Rate Monocular Camera

“…Therefore, our experimental data are closer to the actual application. Meanwhile, the detection rate of our method is better than that of the method in [6], which indicates that our method is more suitable for sphere detection than the deep-learning-based algorithm on blurred images. The above comparison shows that the sphere detection effect of our method is satisfactory.…”

“…In this scenario, a standard method is fitting streaks using circles and ellipses. In [3][4][5][6], by calculating the gradient of images, Huajie Wen et al obtained circle edges directly, thus significantly reducing the difficulty of subsequent analysis of sphere position. In [7], Jung et al used half circle fitting that considers light direction to extract center points of flying golf balls on images.…”