Skip to content
DraconiticResearch
Search Sources API
190,851 studies31 sourcesUpdated 11 min ago
Peer-reviewedCC BY 4.0Frontiers in Plant Science

A real-time deep learning method for detection and localization of non-emerged cabbage seedlings

  • Xin Chen1
  • Kang Han2
  • Teng Liu3
  • Xiaotong Kong3
  • Aniruddha Maity4
  • Peng Peng1
  • Changan Di1
  • Jialin Yu3
  • Maolin Yu2
4 affiliations
  1. 1School of Mechanical Engineering, Nanjing University of Science and Technology
  2. 2National Engineering Research Center of Biomaterials, Nanjing Forestry University
  3. 3Shandong Laboratory of Advanced Agricultural Sciences, Peking University Institute of Advanced Agricultural Sciences
  4. 4Department of Crop, Soil and Environmental Sciences, Auburn University
Open at sourcePDFDOICite

Abstract

Real-time detection and localization of non-emerged seedlings play a pivotal role in effective vegetable crop management. Traditionally, checking the non-emergence of crop seedlings relies on labor-intensive and time-consuming manual inspections. To address this issue, this paper introduces a precise, rapid, and real-time method for detecting and locating non-emerged seedlings using an unmanned aerial vehicle (UAV). The proposed Enhanced YOLOv8n detector improves upon the base model through a more efficient backbone and a bidirectional feature-fusion neck, achieving a mAP50–95 of 81.4%, an 8% improvement over the base model, while preserving real-time inference capability. Furthermore, integrating the Enhanced YOLOv8n, the YOLO tracking algorithm, and image processing algorithms enabled the development of a robust real-time detection and localization method for non-emerged seedlings. The recognition accuracy for non-emerged cabbage seedlings reached 96.9%. Notably, this method can distinguish the quantity of consecutive non-emerged seedlings, demanding only one-fifth of the manual effort, demonstrating substantial potential for practical applications. In summary, the UAV-deployed real-time detection and localization method exhibits excellent capability in detecting and locating non-emerged cabbage seedlings, thus significantly reducing the manpower needed for crop management.

Related

  1. A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability
    Marcello Di Giammarco, Antonella Santone, Mario Cesarelli +2
    PLOS OnePeer-reviewedCC BYFull textNeuroscienceMedical imaging & radiologyPLOSEurope PMCPMC
  2. Antennal detection of host plant volatiles as a function of sex and physiological state in the cabbage stem flea beetle, Psylliodes chrysocephala
    Margot Tixeront, Fabienne Dupuy, Anne Marie Cortesero +2
    Frontiers in Ecology and EvolutionPeer-reviewedCC BY 4.0Full textZoology & animal behaviourHAL
  3. Nitrotoxin metabolism in bacteria may have emerged from a diverse oxidoreductase reservoir
    P. Barman, S. Sinha, R. Chakraborty
    bioRxivPreprintCC BY-NC-NDFull textMicrobiologybioRxiv
  4. The interplay between detection and localization in human vision
    F. Coupette, D. H. Brainard, H. E. Smithson +1
    bioRxivPreprintCC BY-NCFull textNeurosciencebioRxiv
  5. Lightweight YOLOv8n marigold corolla detection and picking-point localization method based on ECR progressive channel compression and dual attention mechanisms
    Yingfan Wang, Baojian Ma, Zhenghao Wu +2
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Plant biologyFrontiersCrossref

Cite

BibTeXRIS
BibTeX
@article{chen2026realtime,
  title = {{A real-time deep learning method for detection and localization of non-emerged cabbage seedlings}},
  author = {Xin Chen and Kang Han and Teng Liu and Xiaotong Kong and Aniruddha Maity and Peng Peng and Changan Di and Jialin Yu and Maolin Yu},
  journal = {Frontiers in Plant Science},
  year = {2026},
  month = oct,
  doi = {10.3389/fpls.2026.1984989},
  url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1984989/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - A real-time deep learning method for detection and localization of non-emerged cabbage seedlings
AU  - Xin Chen
AU  - Kang Han
AU  - Teng Liu
AU  - Xiaotong Kong
AU  - Aniruddha Maity
AU  - Peng Peng
AU  - Changan Di
AU  - Jialin Yu
AU  - Maolin Yu
PY  - 2026
DA  - 2026/10/28
JO  - Frontiers in Plant Science
DO  - 10.3389/fpls.2026.1984989
UR  - https://www.frontiersin.org/articles/10.3389/fpls.2026.1984989/full
AB  - Real-time detection and localization of non-emerged seedlings play a pivotal role in effective vegetable crop management. Traditionally, checking the non-emergence of crop seedlings relies on labor-intensive and time-consuming manual inspections. To address this issue, this paper introduces a precise, rapid, and real-time method for detecting and locating non-emerged seedlings using an unmanned aerial vehicle (UAV). The proposed Enhanced YOLOv8n detector improves upon the base model through a more efficient backbone and a bidirectional feature-fusion neck, achieving a mAP50–95 of 81.4%, an 8% improvement over the base model, while preserving real-time inference capability. Furthermore, integrating the Enhanced YOLOv8n, the YOLO tracking algorithm, and image processing algorithms enabled the development of a robust real-time detection and localization method for non-emerged seedlings. The recognition accuracy for non-emerged cabbage seedlings reached 96.9%. Notably, this method can distinguish the quantity of consecutive non-emerged seedlings, demanding only one-fifth of the manual effort, demonstrating substantial potential for practical applications. In summary, the UAV-deployed real-time detection and localization method exhibits excellent capability in detecting and locating non-emerged cabbage seedlings, thus significantly reducing the manpower needed for crop management.
SN  - 1664-462X
ER  -