Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Technical Advances in Plant Science
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1508258
This article is part of the Research Topic Optimizing Deep Learning for Effective Plant Species Recognition and Conservation View all 8 articles

Pepper-YOLO: An Lightweight Model for Green Pepper Detection and Picking Point Localization in Complex Environments

Provisionally accepted
Yikun Huang Yikun Huang Yulin Zhong Yulin Zhong Deci Zhong Deci Zhong Changcai Yang Changcai Yang Lifang Wei Lifang Wei Zoupei Zhou Zoupei Zhou Riqing Chen Riqing Chen *
  • Fujian Agriculture and Forestry University, Fuzhou, Fujian Province, China

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

    In the cultivation of green chili peppers, the similarity between the fruit and background color, along with severe occlusion between fruits and leaves, significantly reduces the efficiency of harvesting robots. While increasing model depth can enhance detection accuracy, complex models are often difficult to deploy on low-cost agricultural devices. This paper presents an improved lightweight Pepper-YOLO model based on YOLOv8n-Pose, designed for simultaneous detection of green chili peppers and picking points. The proposed model introduces a reversible dual pyramid structure with cross-layer connections to enhance highand low-level feature extraction while preventing feature loss, ensuring seamless information transfer between layers. Additionally, RepNCSPELAN4 is utilized for feature fusion, improving multi-scale feature representation. Finally, the C2fCIB module replaces the CIB module to further optimize the detection and localization of large-scale pepper features. Experimental results indicate that Pepper-YOLO achieves an object detection accuracy of 82.2% and a harvesting point localization 1 Yikun Huang et al.accuracy of 88.1% in complex scenes, with a Euclidean distance error of less than 12.58 pixels. Additionally, the model reduces the number of parameters by 38.3% and lowers complexity by 28.9%, resulting in a final model size of 4.3MB. Compared to state-of-the-art methods, our approach demonstrates better parameter efficiency, as shown in Figure 1. In summary, Pepper-YOLO exhibits high precision and realtime performance in complex environments, with a lightweight design that makes it well-suited for deployment on low-cost devices.

    Keywords: Green Pepper Detection, Pepper-YOLO, Picking Point Localization, Lightweight model, Picking robot

    Received: 09 Oct 2024; Accepted: 05 Dec 2024.

    Copyright: © 2024 Huang, Zhong, Zhong, Yang, Wei, Zhou and Chen. 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: Riqing Chen, Fujian Agriculture and Forestry University, Fuzhou, 350002, Fujian Province, 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.