Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network

Abstract Strawberry grading by picking robots can eliminate the manual classification, reducing labor costs and minimizing the damage to the fruit. Strawberry size or weight is a key factor in grading, with accurate weight estimation being crucial for proper classification. In this paper, we collect...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiming Chen, Wei Wang, Junchao Chen, Jizhou Deng, Yuanping Xiang, Bo Qiao, Xinghui Zhu, Changyun Li
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92641-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265230536343552
author Yiming Chen
Wei Wang
Junchao Chen
Jizhou Deng
Yuanping Xiang
Bo Qiao
Xinghui Zhu
Changyun Li
author_facet Yiming Chen
Wei Wang
Junchao Chen
Jizhou Deng
Yuanping Xiang
Bo Qiao
Xinghui Zhu
Changyun Li
author_sort Yiming Chen
collection DOAJ
description Abstract Strawberry grading by picking robots can eliminate the manual classification, reducing labor costs and minimizing the damage to the fruit. Strawberry size or weight is a key factor in grading, with accurate weight estimation being crucial for proper classification. In this paper, we collected 1521 sets of strawberry RGB-D images using a depth camera and manually measured the weight and size of the strawberries to construct a training dataset for the strawberry weight regression model. To address the issue of incomplete depth images caused by environmental interference with depth cameras, this study proposes a multimodal point cloud completion method specifically designed for symmetrical objects, leveraging RGB images to guide the completion of depth images in the same scene. The method follows a process of locating strawberry pixel regions, calculating centroid coordinates, determining the symmetry axis via PCA, and completing the depth image. Based on this approach, a multimodal fusion regression model for strawberry weight estimation, named MMF-Net, is developed. The model uses the completed point cloud and RGB image as inputs, and extracts features from the RGB image and point cloud by EfficientNet and PointNet, respectively. These features are then integrated at the feature level through gradient blending, realizing the combination of the strengths of both modalities. Using the Percent Correct Weight (PCW) metric as the evaluation standard, this study compares the performance of four traditional machine learning methods, Support Vector Regression (SVR), Multilayer Perceptron (MLP), Linear Regression, and Random Forest Regression, with four point cloud-based deep learning models, PointNet, PointNet++, PointMLP, and Point Cloud Transformer, as well as an image-based deep learning model, EfficientNet and ResNet, on single-modal datasets. The results indicate that among traditional machine learning methods, the SVR model achieved the best performance with an accuracy of 77.7% (PCW@0.2). Among deep learning methods, the image-based EfficientNet model obtained the highest accuracy, reaching 85% (PCW@0.2), while the PointNet + + model demonstrated the best performance among point cloud-based models, with an accuracy of 54.3% (PCW@0.2). The proposed multimodal fusion model, MMF-Net, achieved an accuracy of 87.66% (PCW@0.2), significantly outperforming both traditional machine learning methods and single-modal deep learning models in terms of precision.
format Article
id doaj-art-80c27e42124241bda62dd78060260742
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-80c27e42124241bda62dd780602607422025-08-20T01:54:30ZengNature PortfolioScientific Reports2045-23222025-04-0115111910.1038/s41598-025-92641-1Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion networkYiming Chen0Wei Wang1Junchao Chen2Jizhou Deng3Yuanping Xiang4Bo Qiao5Xinghui Zhu6Changyun Li7Hunan Agricultural UniversityHunan Agricultural UniversityTencent Music EntertainmentHunan Agricultural UniversityHunan Agricultural UniversityHunan Agricultural UniversityHunan Agricultural UniversityHunan Agricultural UniversityAbstract Strawberry grading by picking robots can eliminate the manual classification, reducing labor costs and minimizing the damage to the fruit. Strawberry size or weight is a key factor in grading, with accurate weight estimation being crucial for proper classification. In this paper, we collected 1521 sets of strawberry RGB-D images using a depth camera and manually measured the weight and size of the strawberries to construct a training dataset for the strawberry weight regression model. To address the issue of incomplete depth images caused by environmental interference with depth cameras, this study proposes a multimodal point cloud completion method specifically designed for symmetrical objects, leveraging RGB images to guide the completion of depth images in the same scene. The method follows a process of locating strawberry pixel regions, calculating centroid coordinates, determining the symmetry axis via PCA, and completing the depth image. Based on this approach, a multimodal fusion regression model for strawberry weight estimation, named MMF-Net, is developed. The model uses the completed point cloud and RGB image as inputs, and extracts features from the RGB image and point cloud by EfficientNet and PointNet, respectively. These features are then integrated at the feature level through gradient blending, realizing the combination of the strengths of both modalities. Using the Percent Correct Weight (PCW) metric as the evaluation standard, this study compares the performance of four traditional machine learning methods, Support Vector Regression (SVR), Multilayer Perceptron (MLP), Linear Regression, and Random Forest Regression, with four point cloud-based deep learning models, PointNet, PointNet++, PointMLP, and Point Cloud Transformer, as well as an image-based deep learning model, EfficientNet and ResNet, on single-modal datasets. The results indicate that among traditional machine learning methods, the SVR model achieved the best performance with an accuracy of 77.7% (PCW@0.2). Among deep learning methods, the image-based EfficientNet model obtained the highest accuracy, reaching 85% (PCW@0.2), while the PointNet + + model demonstrated the best performance among point cloud-based models, with an accuracy of 54.3% (PCW@0.2). The proposed multimodal fusion model, MMF-Net, achieved an accuracy of 87.66% (PCW@0.2), significantly outperforming both traditional machine learning methods and single-modal deep learning models in terms of precision.https://doi.org/10.1038/s41598-025-92641-1Deep learningPoint cloud completionWeight EstimationFeature fusion
spellingShingle Yiming Chen
Wei Wang
Junchao Chen
Jizhou Deng
Yuanping Xiang
Bo Qiao
Xinghui Zhu
Changyun Li
Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
Scientific Reports
Deep learning
Point cloud completion
Weight Estimation
Feature fusion
title Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
title_full Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
title_fullStr Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
title_full_unstemmed Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
title_short Estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
title_sort estimating strawberry weight for grading by picking robot with point cloud completion and multimodal fusion network
topic Deep learning
Point cloud completion
Weight Estimation
Feature fusion
url https://doi.org/10.1038/s41598-025-92641-1
work_keys_str_mv AT yimingchen estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT weiwang estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT junchaochen estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT jizhoudeng estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT yuanpingxiang estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT boqiao estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT xinghuizhu estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork
AT changyunli estimatingstrawberryweightforgradingbypickingrobotwithpointcloudcompletionandmultimodalfusionnetwork