TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Comparative analysis and optimization of detection algorithms for apples on orchards with complex backgrounds
 
Options

Comparative analysis and optimization of detection algorithms for apples on orchards with complex backgrounds

Publikationstyp
Conference Paper
Date Issued
2024-10
Sprache
English
Author(s)
Kevric, Ermin
Wei, Jiahua 
Technische Logistik W-6  
Braun, Philipp Maximilian  orcid-logo
Technische Logistik W-6  
Rose, Hendrik Wilhelm 
Technische Logistik W-6  
TORE-URI
https://hdl.handle.net/11420/57082
Start Page
190
End Page
195
Citation
IEEE International Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2024
Contribution to Conference
IEEE International Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2024  
Publisher DOI
10.1109/MetroAgriFor63043.2024.10948864
Scopus ID
2-s2.0-105003532490
Publisher
IEEE
ISBN
979-8-3503-5544-4
979-8-3503-5545-1
Developing systems for accurate apple detection plays a significant role in precision agriculture tasks and orchard management practices, hence having a direct impact on the economics of orchard fields. Thus, this research compares between different detection algorithms as it plays the baseline for subsequent tasks of counting, apple grasping and growth monitoring. In this work, four different state-of-the-art (SOTA) object detection models have been compared for apple detection: Faster R-CNN, YOLOv5, YOLOv8 and RT-DETR. The models were examined for their accuracy in apple detection and their invariance to the background apples. As Faster R-CNN and YOLOv5 are commonly used algorithms in this domain, they were chosen alongside YOLOv8. Furthermore, as the transformer-based detectors like RT-DETR outperform YOLO on large datasets, their comparison for apple detection is also warranted. The models are evaluated on the MinneApple dataset and a manually collected dataset. In addition, the effect of attention mechanisms in YOLOv8 architecture, hyperparameter optimization and data augmentation were explored. The evaluation showed that RT-DETR outperformed all models for mAP0.50:0.95 on the MinneApple and custom dataset for the trained image size. Furthermore, given the smaller background interference at a larger mAP, the RT-DETR model not only outperformed YOLO and Faster R-CNN models, but was also more background invariant.
Subjects
computer vision
Faster R-CNN
MinneApple dataset
Object Detection
RT-DETR
YOLO
DDC Class
600: Technology
Funding(s)
Smarte Automatisierungssysteme und -services für den Obstanbau an der Niederelbe  
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback