Open Collections

UBC Faculty Research and Publications

Multimodal Data Fusion for Precise Lettuce Phenotype Estimation Using Deep Learning Algorithms Hou, Lixin; Zhu, Yuxia; Wang, Mengke; Wei, Ning; Dong, Jiachi; Tao, Yaodong; Zhou, Jing; Zhang, Jian (Professor of biology)

Abstract

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R² of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping.

Item Metadata

Title
Multimodal Data Fusion for Precise Lettuce Phenotype Estimation Using Deep Learning Algorithms
Creator
Hou, Lixin; Zhu, Yuxia; Wang, Mengke; Wei, Ning; Dong, Jiachi; Tao, Yaodong; Zhou, Jing; Zhang, Jian (Professor of biology)
Publisher
Multidisciplinary Digital Publishing Institute
Date Issued
2024-11-15
Description
Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R² of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping.
Subject
deep learning; phenotype; lettuce; RGB-D
Genre
Article
Type
Text
Language
eng
Date Available
2024-11-29
Provider
Vancouver : University of British Columbia Library
Rights
CC BY 4.0
DOI
10.14288/1.0447378
URI
http://hdl.handle.net/2429/89761
Affiliation
Science, Irving K. Barber Faculty of (Okanagan); Non UBC; Biology, Department of (Okanagan)
Citation
Plants 13 (22): 3217 (2024)
Publisher DOI
10.3390/plants13223217
Peer Review Status
Reviewed
Scholarly Level
Faculty; Researcher
Rights URI
https://creativecommons.org/licenses/by/4.0/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

CC BY 4.0