A Recognition Method for Marigold Picking Points Based on the Lightweight SCS-YOLO-Seg Model

A Recognition Method for Marigold Picking Points Based on the Lightweight SCS-YOLO-Seg Model

Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentat...

Full description

Saved in:
Bibliographic Details
Main Authors: Baojian Ma, Zhenghao Wu, Yun Ge, Bangbang Chen, He Zhang, Hao Xia, Dongyun Wang
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
marigold
segmentation
lightweight model
picking point recognition
automated harvesting
Online Access:https://www.mdpi.com/1424-8220/25/15/4820
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentation model. The approach enhances the baseline YOLOv8n-seg architecture by replacing its backbone with StarNet and introducing C2f-Star, a novel lightweight feature extraction module. These modifications achieve substantial model compression, significantly reducing the model size, parameter count, and computational complexity (GFLOPs). Segmentation efficiency is further optimized through a dual-path collaborative architecture (Seg-Marigold head). Following mask extraction, picking points are determined by intersecting the optimized elliptical mask fitting results with the stem skeleton. Experimental results demonstrate that SCS-YOLO-Seg effectively balances model compression with segmentation performance. Compared to YOLOv8n-seg, it maintains high accuracy while significantly reducing resource requirements, achieving a picking point identification accuracy of 93.36% with an average inference time of 28.66 ms per image. This work provides a robust and efficient solution for vision systems in automated marigold harvesting.
ISSN:1424-8220

Similar Items