MPG-YOLO: Enoki Mushroom Precision Grasping with Segmentation and Pulse Mapping

The flatness of the cut surface in enoki mushrooms (Flammulina filiformis Z.W. Ge, X.B. Liu & Zhu L. Yang) is a key factor in quality classification. However, conventional automatic cutting equipment struggles with deformation issues due to its inability to adjust the grasping force based on individual mushroom sizes. To address this, we propose an improved method that integrates visual feedback to dynamically adjust the execution end, enhancing cut precision. Our approach enhances YOLOv8n-seg with Star Net, SPPECAN (a reconstructed SPPF with efficient channel attention), and C2fDStar (C2f with Star Net and deformable convolution) to improve feature extraction while reducing computational complexity and feature loss. Additionally, we introduce a mask ownership judgment and merging optimization algorithm to correct positional offsets, internal disconnections, and boundary instabilities in grasping area predictions. Based on this, we optimize grasping parameters using an improved centroid-based region width measurement and establish a region width-to-PWM mapping model for the precise conversion from visual data to gripper control. Experiments in real-situation settings demonstrate the effectiveness of our method, achieving a mean average precision (mAP50:95) of 0.743 for grasping area segmentation, a 4.5% improvement over YOLOv8, with an average detection speed of 10.3 ms and a target width measurement error of only 0.14%. The proposed mapping relationship enables adaptive end-effector control, resulting in a 96% grasping success rate and a 98% qualified cutting surface rate. These results confirm the feasibility of our approach and provide a strong technical foundation for the intelligent automation of enoki mushroom cutting systems.