skip to main content
10.1145/3656766.3656919acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicbarConference Proceedingsconference-collections
research-article

Research on strawberry category detection method based on improved YOLOv7 model

Published: 01 June 2024 Publication History

Abstract

Strawberry is a sweet, juicy and nutrient-rich fruit with high nutritional and economic value. However, due to factors such as fast ripening cycle, different shapes and sizes, and overlapping of fruits, category detection of strawberry fruits poses a major challenge. To solve this problem, we proposed a method suitable for multi-strawberry category detection based on yolov7 model. Firstly, a switchable atrous convolution (sac) with a wider receptive field was introduced into the yolov7 backbone network, and the E-ELAN structure in yolov7 was replaced with a newly constructed E-ESLAN structure to reduce the possibility that the variable size target feature map could not transmit to the target detector.In addition, we use a efficient decoupled head (edh) with implicit knowledge learning to further obtain implicit feature information, so as to improve the adaptability of strawberry category detection under severe occlusion environment. We select Strawberry-DS dataset suitable for strawberry category target detection to verify the performance of the proposed method. The experimental results show that our proposed method performs well on the collected datasets. Compared with yolov7-tiny model, the precision, mAP5 and mAP5∼95 of the improved method are improved by 3.5%,5.3% and 3.4% respectively, while the recall value is decreased by 1%. Compared with yolov5, yolov6 and yolov8, the proposed improvement method improves mAP5 by 6.9%, 3.3% and 2.3%, respectively.

References

[1]
Zaidi S S A, Ansari M S, Aslam A, Kanwal N, Asghar M and Lee B. 2022. A survey of modern deep learning based object detection models[J]. Digital Signal Processing, 126: 103514.
[2]
Krishnan G H, Rajasenbagam T. 2021. A comprehensive survey for weed classification and detection in agriculture lands[J]. Journal of Information Technology, 3 (4): 281-289.
[3]
Lin P, Lee W S, Chen Y M, Peres N and Fraisse C. 2020. A deep-level region-based visual representation architecture for detecting strawberry flowers in an outdoor field[J]. Precision Agriculture, 21: 387-402.
[4]
Yu Y, Zhang K, Yang L and Zhang D. 2019. Fruit detection for strawberry harvesting robot in non-structural environment based on Mask-RCNN[J]. Computers and Electronics in Agriculture, 163: 104846.
[5]
Li Y, Xue J, Zhang M, Yin J, Liu Y, Qiao X, Zheng D and Li Z. 2023. YOLOv5-ASFF: A Multistage Strawberry Detection Algorithm Based on Improved YOLOv5[J]. Agronomy, 13 (7): 1901.
[6]
He Z, Karkee M, Zhang Q. 2022. Detecting and localizing strawberry centers for robotic harvesting in field environment[J]. IFAC-PapersOnLine, 55 (32): 30-35.
[7]
Elhariri E, El-Bendary N, Saleh S M. Strawberry-DS: Dataset of annotated strawberry fruits images with various developmental stages[J]. Data in Brief, 2023, 48: 109165.
[8]
Wang C Y, Bochkovskiy A and Liao H Y M. 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7464-7475.
[9]
Qiao S, Chen L C and Yuille A. 2021. Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10213-10224.
[10]
Li C, Li L, Geng Y, Geng Y, Jiang H, Cheng M, Zhang B, Ke Z, Xu X and Chu X. Yolov6 v3. 0: A full-scale reloading[J]. arXiv preprint arXiv:2301.05586, 2023.

Index Terms

  1. Research on strawberry category detection method based on improved YOLOv7 model

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICBAR '23: Proceedings of the 2023 3rd International Conference on Big Data, Artificial Intelligence and Risk Management
    November 2023
    1156 pages
    ISBN:9798400716478
    DOI:10.1145/3656766
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 01 June 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICBAR 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 14
      Total Downloads
    • Downloads (Last 12 months)14
    • Downloads (Last 6 weeks)3
    Reflects downloads up to 19 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media