Tea-YOLOv8s: A Tea Bud Detection Model Based on Deep Learning and Computer Vision

Abstract

Tea bud target detection is essential for mechanized selective harvesting. To address the challenges of low detection precision caused by the complex backgrounds of tea leaves, this paper introduces a novel model called Tea-YOLOv8s. First, multiple data augmentation techniques are employed to increase the amount of information in the images and improve their quality. Then, the Tea-YOLOv8s model combines deformable convolutions, attention mechanisms, and improved spatial pyramid pooling, thereby enhancing the model’s ability to learn complex object invariance, reducing interference from irrelevant factors, and enabling multi-feature fusion, resulting in improved detection precision. Finally, the improved YOLOv8 model is compared with other models to validate the effectiveness of the proposed improvements. The research results demonstrate that the Tea-YOLOv8s model achieves a mean average precision of 88.27% and an inference time of 37.1 ms, with an increase in the parameters and calculation amount by 15.4 M and 17.5 G, respectively. In conclusion, although the proposed approach increases the model’s parameters and calculation amount, it significantly improves various aspects compared to mainstream YOLO detection models and has the potential to be applied to tea buds picked by mechanization equipment.

Applications of Artificial Intelligence, Machine Learning, and Deep Learning in Plant Breeding

“…However, when applied to cotton pests and diseases identification, conventional YOLO algorithms encounter challenges in detecting cotton leaf diseases under natural conditions, difficulty in extracting features from small targets, and low efficiency (Terven and Cordova-Esparza, 2023). To overcome these challenges, this study presents an enhanced method for cotton peat and disease identification, built upon YOLOv8s (Xie and Sun, 2023). This method involves replacing the C2F modules in the backbone network with CFNet modules (Zhang G. et al, 2023) and substituting all C2F modules in the YOLOv8s header with VoV-GCSP modules .…”

Unveiling the Connection between Microbiota and Depressive Disorder through Machine Learning

“…To date, methods for diagnosing depressive disorder in patients have mainly relied on the usage of questionnaires, observation of their general physical state by the therapist, analysis of biochemistry, MRI, etc. [43][44][45][46]. The described functional changes in gut microbiota associated with depression make the metagenomic signatures a novel method for the diagnostics and monitoring of the disease, where the signature pairs can be utilized as defining biomarkers.…”

YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module

“…These blocks are pooled and concatenated, followed by convolution operations, to enhance the model's receptive field and retain key feature information, thereby improving the model's accuracy [49]. The SPPFCSPC module is an optimization of SPPCSPC based on the SPPF concept, reducing the computational requirements for the pooling layer's output by connecting three independent pooling operations, and improving the speed and detection accuracy of dense targets without changing the receptive field [50]. The results produced by this pooling method are comparable to those obtained using larger pooling kernels, thus optimizing the training and inference speed of the model.…”