ORIGINAL RESEARCH article

Front. Plant Sci.

Sec. Plant Bioinformatics

Volume 16 - 2025 | doi: 10.3389/fpls.2025.1604514

Automatic detection of lucky bamboo nodes based on Improved YOLOv7

Provisionally accepted
Jing  ZhangJing ZhangRuoling  DengRuoling Deng*Chengzhi  CaiChengzhi CaiErpeng  ZouErpeng ZouHaitao  LiuHaitao LiuMingxin  HouMingxin HouXinzhi  ChenXinzhi ChenHuamin  LinHuamin LinZhenye  WeiZhenye Wei
  • Guangdong Ocean University, Zhanjiang, China

The final, formatted version of the article will be published soon.

The detection of lucky bamboo nodes plays an important role in the process of machining lucky bamboo into handicrafts and is also a crucial prerequisite. However, the existing methods of detecting lucky bamboo nodes mainly rely on manual labour, which is inefficient, labor-intensive, and costly. Therefore, a novel method based on the improved YOLOv7 neural network model was developed for rapid and precise detection of lucky bamboo nodes in this paper. Among them, the Squeeze-and-Excitation (SE) attention mechanism was embedded in the feature extraction part, and a new bounding box loss, Weighted Intersection over Union (WIoU), was introduced in the loss function calculation. Experimental results showed that the lucky bamboo node detection model established in this paper had an accuracy of 97.6% in detecting lucky bamboo nodes under different environmental conditions (blurred conditions, similarities of bamboo spot and node, sick bamboo node, and dried bamboo leaf). This study can provide an important reference for related research on the real-time detection system of lucky bamboo nodes. In practical applications, this model can be used in fields such as smart agriculture to automatically detect the growth status and growth conditions of lucky bamboo, thereby improving production efficiency and accuracy of crop management.

Keywords: Lucky bamboo, Handicraft, Convolutional Neural Network, YOLOv7, object detection, Bamboo node

Received: 02 Apr 2025; Accepted: 30 Jun 2025.

Copyright: © 2025 Zhang, Deng, Cai, Zou, Liu, Hou, Chen, Lin and Wei. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Ruoling Deng, Guangdong Ocean University, Zhanjiang, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.