Dual-YOLO Network: Recognition of Thinning Targets and Growing Point for Tobacco Seedlings

To address the identification requirements for tobacco thinning targets and their growth points in automated tobacco thinning operations, a dual-model collaborative recognition approach integrating target detection and instance segmentation was proposed. First, for thinning target identification, a lightweight you only look once dilated dual-path network (YOLO-DDPNet) segmentation network was developed by integrating a DDPNet module into the YOLOv8 architecture. This network achieved a tobacco seedling segmentation accuracy of 98.7% (3.6% higher than YOLOv8n), enabling thinning target screening by comparing the segmentation mask areas of tobacco seedlings within a seedling hole. Second, for seedling growth point detection, the original C2f module in YOLOv8 was replaced with C3x while incorporating the SE attention mechanism and SPPCSPC multiscale feature fusion module to construct a lightweight YOLO-TGPD detection network. This network attained a growth point detection accuracy of 94.3% (8.2% higher than YOLOv8n). Notably, this study pioneered the synergistic use of segmentation and detection strategies to simultaneously complete thinning target screening and growth point detection. The proposed model outperformed advanced models (e.g., YOLOv9 and YOLOv11) on the tobacco seedling dataset, holding significant potential for advancing tobacco thinning automation technology.