Comparison of One-Stage Object Detection Models for Weed Detection in Mulched Onions

Paolo Rommel Sanchez, Hong Zhang, Shen Shyang Ho, Eldon De Padua

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Deep learning-based computer vision enabled farming robots to detect and control weeds in the field accurately. This study compared the performance of Scaled-YOLOv4-CSP, YOLOv5s, and SSD Mobilenet V2 for image-based weed detection in mulched onions. The study showed that YOLOv5s is more suitable for the purpose. At 0.915 mAP0.5, it ties with Scaled-YOLOv4-CSP at first place on weed detection performance. Meanwhile, YOLOv5s consumed significantly fewer resources during training and implementation, giving it an advantage in real-time weed detection. Its mean inference time of 7.72 milliseconds is also less than half of the other two models. Lastly, the study demonstrated that increasing the number of samples with a more balanced class distribution by upsizing the dataset through data augmentation would improve the overall performance of the object detection model.

Original languageEnglish (US)
Title of host publicationIST 2021 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728173719
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Imaging Systems and Techniques, IST 2021 - Virtual, New York, United States
Duration: Aug 24 2021Aug 26 2021

Publication series

NameIST 2021 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

Conference

Conference2021 IEEE International Conference on Imaging Systems and Techniques, IST 2021
Country/TerritoryUnited States
CityVirtual, New York
Period8/24/218/26/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Decision Sciences (miscellaneous)

Fingerprint

Dive into the research topics of 'Comparison of One-Stage Object Detection Models for Weed Detection in Mulched Onions'. Together they form a unique fingerprint.

Cite this