Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm

Sun, Tao; Cui, Longfei; Zong, Lixuan; Zhang, Songchao; Jiao, Yuxuan; Xue, Xinyu; Jin, Yongkui

doi:10.3390/agronomy14040657

Open AccessEditor’s ChoiceArticle

Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm

by

Tao Sun

^1,†,

Longfei Cui

^1,†

,

Lixuan Zong

²,

Songchao Zhang

¹

,

Yuxuan Jiao

¹,

Xinyu Xue

^1,* and

Yongkui Jin

¹

Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China

²

Faculty of Engineering, Hong Kong Polytechnic University, Hong Kong 999077, China

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Agronomy 2024, 14(4), 657; https://doi.org/10.3390/agronomy14040657

Submission received: 20 February 2024 / Revised: 14 March 2024 / Accepted: 18 March 2024 / Published: 24 March 2024

(This article belongs to the Section Weed Science and Weed Management)

Download

Browse Figures

Versions Notes

Abstract

The high cost of manual weed control and the overuse of herbicides restrict the yield and quality of soybean. Intelligent mechanical weeding and precise application of pesticides can be used as effective alternatives for weed control in the field, and these require accurate distinction between crops and weeds. In this paper, images of soybean seedlings and weeds in different growth areas are used as datasets. In the aspect of soybean recognition, this paper designs a YOLOv8nGP algorithm with a backbone network optimisation based on GhostNet and an unconstrained pruning method with a 60% pruning rate. Compared with the original YOLOv8n, the YOLOv8nGP improves the Precision (P), Recall (R), and F1 metrics by 1.1% each, reduces the model size by 3.6 mb, and the inference time was 2.2 ms, which could meet the real-time requirements of field operations. In terms of weed recognition, this study utilises an image segmentation method based on the Normalized Excess Green Index (NExG). After filtering the soybean seedlings, the green parts of the image are extracted for weed recognition, which reduces the dependence on the diversity of the weed datasets. This study combines deep learning with traditional algorithms, which provides a new solution for weed recognition of soybean seedlings.

Keywords: weed; soybean; YOLOv8; lightweight; NExG; recognition

Share and Cite

MDPI and ACS Style

Sun, T.; Cui, L.; Zong, L.; Zhang, S.; Jiao, Y.; Xue, X.; Jin, Y. Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm. Agronomy 2024, 14, 657. https://doi.org/10.3390/agronomy14040657

AMA Style

Sun T, Cui L, Zong L, Zhang S, Jiao Y, Xue X, Jin Y. Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm. Agronomy. 2024; 14(4):657. https://doi.org/10.3390/agronomy14040657

Chicago/Turabian Style

Sun, Tao, Longfei Cui, Lixuan Zong, Songchao Zhang, Yuxuan Jiao, Xinyu Xue, and Yongkui Jin. 2024. "Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm" Agronomy 14, no. 4: 657. https://doi.org/10.3390/agronomy14040657

APA Style

Sun, T., Cui, L., Zong, L., Zhang, S., Jiao, Y., Xue, X., & Jin, Y. (2024). Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm. Agronomy, 14(4), 657. https://doi.org/10.3390/agronomy14040657

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP + NExG Algorithm

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI