Advanced 3D Depth Imaging Techniques for Morphometric Analysis of Detected On-Tree Apples Based on AI Technology

Eungchan Kim, Sang-Yeon Kim, Chang-Hyup Lee, Sungjay Kim, Jiwon Ryu, Geon-Hee Kim, Seul-Ki Lee and Ghiseok Kim ()
Additional contact information
Eungchan Kim: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
Sang-Yeon Kim: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
Chang-Hyup Lee: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
Sungjay Kim: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
Jiwon Ryu: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea
Geon-Hee Kim: Department of Mechanical Materials Convergence System Engineering, Hanbat National University, Daejeon 34158, Republic of Korea
Seul-Ki Lee: Fruit Research Division, National Institute of Horticultural and Herbal Science, Wanju 55365, Republic of Korea
Ghiseok Kim: Department of Biosystems Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea

Agriculture, 2025, vol. 15, issue 11, 1-27

Abstract: This study developed non-destructive technology for predicting apple size to determine optimal harvest timing of field-grown apples. RGBD images were collected in field environments with fluctuating light conditions, and deep learning techniques were integrated to analyze morphometric parameters. After training various models, the EfficientDet D4 and Mask R-CNN ResNet101 models demonstrated the highest detection accuracy. Morphometric metrics were measured by linking boundary box information with 3D depth information to determine horizontal and vertical diameters. Without occlusion, mean absolute percentage error (MAPE) using boundary box-based methods was 6.201% and 5.164% for horizontal and vertical diameters, respectively, while mask-based methods achieved improved accuracy with MAPE of 5.667% and 4.921%. Volume and weight predictions showed MAPE of 7.183% and 6.571%, respectively. For partially occluded apples, amodal segmentation was applied to analyze morphometric parameters according to occlusion rates. While conventional models showed increasing MAPE with higher occlusion rates, the amodal segmentation-based model maintained consistent accuracy regardless of occlusion rate, demonstrating potential for automated harvest systems where fruits are frequently partially obscured by leaves and branches.

Keywords: 3D depth imaging; artificial intelligence; morphometric analysis; object detection; instance segmentation; amodal segmentation; multivariate regression (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/11/1148/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/11/1148/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:11:p:1148-:d:1665561

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().