Lychee Instance Segmentation at Different Growth Stages Using YOLOv8-seg Model

This paper presents an approach to lychee instance segmentation through different development stages using the YOLOv8-seg model. A new dataset comprising 1006 lychee images from various growth phases (flowering, young fruit, green fruit, and ripe fruit) was introduced and manually labeled. We tested...

Full description

Saved in:
Bibliographic Details
Published in2024 9th International Conference on Integrated Circuits, Design, and Verification (ICDV) pp. 125 - 129
Main Authors Kim, Thai Dinh, Duc, Quang-Anh Nguyen, Nguyen, Tuan-Minh, Nguyen, Minh-Anh, Pham, Ho-Bao, Do, Tien-Thanh
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2024
Subjects
Accuracy
Deep learning
Embedded systems
Flowering plants
Focusing
Instance segmentation
Integrated circuit synthesis
Lychee
smart agriculture
YOLO
Online AccessGet full text

Cover

More Information
Summary:This paper presents an approach to lychee instance segmentation through different development stages using the YOLOv8-seg model. A new dataset comprising 1006 lychee images from various growth phases (flowering, young fruit, green fruit, and ripe fruit) was introduced and manually labeled. We tested 5 versions of YOLOv8-seg on this dataset. The findings reveal that YOLOv8x-seg, with 71.8M parameters, achieves the highest average mAP50 accuracy of 84.1 \%, while YOLOv8n-seg, with only 3.4M parameters, attains an mAP50 of 83.7 \%. These results suggest that YOLOv8n-seg suits real-world applications on less powerful hardware.
DOI:10.1109/ICDV61346.2024.10617329