Lightweight Tennis Ball Detection Algorithm Based on Robomaster EP

Abstract

To address the problems of poor recognition effect, low detection accuracy, many model parameters and computation, complex network structure, and unfavorable portability to embedded devices in traditional tennis ball detection algorithms, this study proposes a lightweight tennis ball detection algorithm, YOLOv5s-Z, based on the YOLOv5s algorithm and Robomater EP. The main work is as follows: firstly, the lightweight network G-Backbone and G-Neck network layers are constructed to reduce the number of parameters and computation of the network structure. Secondly, convolutional coordinate attention is incorporated into the G-Backbone to embed location information into channel attention, which enables the network to obtain location information of a larger area through multiple convolutions and enhances the expression ability of mobile network learning features. In addition, the Concat module in the original feature fusion is modified into a weighted bi-directional feature pyramid W-BiFPN with settable learning weights to improve the feature fusion capability and achieve efficient weighted feature fusion and bi-directional cross-scale connectivity. Finally, the Loss function EIOU Loss is introduced to split the influence factor of the aspect ratio and calculate the length and width of the target frame and anchor frame, respectively, combined with Focal-EIOU Loss to solve the problem of imbalance between complex and easy samples. Meta-ACON’s activation function is introduced to achieve an adaptive selection of whether to activate neurons and improve the detection accuracy. The experimental results show that compared with the YOLOv5s algorithm, the YOLOv5s-Z algorithm reduces the number of parameters and computation by 42% and 44%, respectively, reduces the model size by 39%, and improves the mean accuracy by 2%, verifying the effectiveness of the improved algorithm and the lightweight of the model, adapting to Robomaster EP, and meeting the deployment requirements of embedded devices for the detection and identification of tennis balls.

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

“…From the formula, it can be seen that the difference between the predicted and target box aspect ratio is reacted using v , instead of the true difference between the width and height respectively and its confidence, so it sometimes prevents the model from optimizing the similarity effectively. the design of CIoU loss for the aspect ratio added to the loss is not very reasonable, and the part of CIoU loss that reacts to the consistency of aspect ratio is replaced by the consistency for the length and width respectively loss, which is the efficient‐intersection over union (EIoU) loss [36].…”

Design and Experiments of a Vision-Guided Integrated Cavity Tray Seedling Culling and Replanting System

“…In addition, deep learning technology is rapidly developing, and the robustness of the model can be improved by data augmentation, such as geometric transformations (cropping and deformation), color transformations (noise and blurring), and the use of generative adversarial networks (GAN) [40]. The model can also be lightweight by reducing the number of model parameters and improving its deployment in hardware devices [40], [41].…”

Deep Learning for Pothole Detection on Indonesian Roadways

“…During region proposal, two-stage models focus on likely item locations and update predictions to increase detection accuracy. YOLO [32], [33] and SSD [34], [35] are object recognition models that estimate item bounding boxes and class probabilities in a single pass over an input image. These single-step models are fast and appropriate for real-time applications.…”