Automatic Tomato Harvesting Recognition System Based on Improved YOLOv8 Algorithm
Abstract：Harvesting robots can improve efficiency and reduce costs. Most harvesting robots use YOLOv5/v7 algorithms, but these algorithms have limitations in identifying maturity and are prone to mis-harvesting. To address this, an improved YOLOv8 algorithm is proposed, which enhances the accuracy of maturity recognition. Experimental analysis was conducted using a dataset composed of tomatoes as samples. The experimental results are reflected through metrics such as confusion matrix, precision confidence curve, F1 confidence curve, recall confidence curve, and labeled images. After improvement, the recognition rate reached as high as 91.4%, exceeding the original YOLOv8's 86%. Meanwhile, the system has high versatility and can be integrated into harvesting robots in the future.
Keywords：YOLOv8Deep LearningComputer VisionNeural NetworkObject Detection
Publication Date：2025-02-27
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 26-31 )