An improved YOLOv8-seg-based method for key part segmentation of tobacco plants

Abstract

Accurate segmentation of key tobacco structures is essential for enabling automated harvesting. However, complex backgrounds, variable lighting conditions, and blurred boundaries between the stem and petiole significantly hinder segmentation accuracy in field environments. To overcome these challenges, we propose an enhanced instance segmentation approach based on YOLOv8-seg, incorporating depth-based background filtering and architectural improvements. Specifically, depth information from RGB-D images is employed to spatially filter non-target background regions, thereby enhancing foreground clarity. In addition, a Hybrid Dilated Residual Attention Block (HDRAB) is integrated into the YOLOv8-seg backbone to improve boundary discrimination between petioles and stems, while a Lightweight Shared Detail-Enhanced Convolution Detection Head (LSDECD) is designed to efficiently capture fine-grained texture features. Experimental results demonstrate that depth filtering increases mAP50 bb and mAP50 seg by 7.9% and 6.3%, respectively, while the architectural enhancements further raise them to 89.5% and 91.1%, surpassing the YOLOv8-seg baseline by 5.2% and 10.0%. Compared with mainstream models such as Mask R-CNN and SOLOv2, the proposed method achieves superior segmentation accuracy with low computational cost, highlighting its potential for practical deployment in automated tobacco harvesting.

Code and data availability

The supplied blocks describe a custom tobacco RGB-D image dataset (2,366 images, Labelme annotations) and an improved YOLOv8-seg model, but contain no data availability statement, code deposit, or authors' public URL for the dataset, annotations, or trained model. The only URL present is the Intel RealSense D435 camera

No evidence-backed public reproduction asset is currently recorded.