TY - GEN
T1 - Comparison of One-Stage Object Detection Models for Weed Detection in Mulched Onions
AU - Sanchez, Paolo Rommel
AU - Zhang, Hong
AU - Ho, Shen Shyang
AU - De Padua, Eldon
N1 - Funding Information:
ACKNOWLEDGMENT This research was partially supported by Engineering Research and Development for Technology Program by the Department of Science and Technology and the University of the Philippines Los Baños.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85124341724&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124341724&partnerID=8YFLogxK
U2 - 10.1109/IST50367.2021.9651352
DO - 10.1109/IST50367.2021.9651352
M3 - Conference contribution
AN - SCOPUS:85124341724
T3 - IST 2021 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
BT - IST 2021 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Imaging Systems and Techniques, IST 2021
Y2 - 24 August 2021 through 26 August 2021
ER -