Real time weed identification with enhanced mobilevit model for mobile devices

Abstract Deep learning model optimization have notably enhanced weed identification accuracy. However, there is a short-fall in detailed research on optimizing models for weed identification with images from mobile embedded systems. Also, existing methods generally use large, slow multi-layer convol...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyan Liu, Qingru Sui, Zhihui Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12036-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849388071475216384
author Xiaoyan Liu
Qingru Sui
Zhihui Chen
author_facet Xiaoyan Liu
Qingru Sui
Zhihui Chen
author_sort Xiaoyan Liu
collection DOAJ
description Abstract Deep learning model optimization have notably enhanced weed identification accuracy. However, there is a short-fall in detailed research on optimizing models for weed identification with images from mobile embedded systems. Also, existing methods generally use large, slow multi-layer convolutional networks (CNNs), which are impractical for use on mobile embedded devices. To address those issues, we propose a lightweight weed identification model based on an enhanced MobileViT architecture, effectively balancing high accuracy with real-time performance. Our approach begins with the application of a multi-scale retinal enhancement algorithm featuring color restoration to preprocess image data. This step improves the clarity of images, particularly those with blurred edges or significant shadow interference. Following this, we introduce an optimized MobileViT model that incorporates the Efficient Channel Attention (ECA) module into the weed feature extraction network. This design ensures robust feature extraction capabilities while simultaneously reducing the model’s parameters and computational complexity. The MobileViT model within our feature extraction network is engineered to concurrently learn local and global semantic information. This capability allows it to accurately distinguish subtle differences between weeds and crops by leveraging a minimal number of modules. To demonstrate the effectiveness of our model, it achieved an F1 score of 98.51% and an average identification time of 89 milliseconds per image. These results underscore its suitability for lightweight deployment, maintaining high accuracy while minimizing model complexity.
format Article
id doaj-art-463b4fc8c94b4ae4b2361e7ea0ee9c96
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-463b4fc8c94b4ae4b2361e7ea0ee9c962025-08-20T03:42:25ZengNature PortfolioScientific Reports2045-23222025-07-0115111210.1038/s41598-025-12036-0Real time weed identification with enhanced mobilevit model for mobile devicesXiaoyan Liu0Qingru Sui1Zhihui Chen2Changchun Sci-Tech UniversityChangchun Sci-Tech UniversityChangchun Sci-Tech UniversityAbstract Deep learning model optimization have notably enhanced weed identification accuracy. However, there is a short-fall in detailed research on optimizing models for weed identification with images from mobile embedded systems. Also, existing methods generally use large, slow multi-layer convolutional networks (CNNs), which are impractical for use on mobile embedded devices. To address those issues, we propose a lightweight weed identification model based on an enhanced MobileViT architecture, effectively balancing high accuracy with real-time performance. Our approach begins with the application of a multi-scale retinal enhancement algorithm featuring color restoration to preprocess image data. This step improves the clarity of images, particularly those with blurred edges or significant shadow interference. Following this, we introduce an optimized MobileViT model that incorporates the Efficient Channel Attention (ECA) module into the weed feature extraction network. This design ensures robust feature extraction capabilities while simultaneously reducing the model’s parameters and computational complexity. The MobileViT model within our feature extraction network is engineered to concurrently learn local and global semantic information. This capability allows it to accurately distinguish subtle differences between weeds and crops by leveraging a minimal number of modules. To demonstrate the effectiveness of our model, it achieved an F1 score of 98.51% and an average identification time of 89 milliseconds per image. These results underscore its suitability for lightweight deployment, maintaining high accuracy while minimizing model complexity.https://doi.org/10.1038/s41598-025-12036-0Weed identificationMobileViTCNNEmbedded devicesModel optimization
spellingShingle Xiaoyan Liu
Qingru Sui
Zhihui Chen
Real time weed identification with enhanced mobilevit model for mobile devices
Scientific Reports
Weed identification
MobileViT
CNN
Embedded devices
Model optimization
title Real time weed identification with enhanced mobilevit model for mobile devices
title_full Real time weed identification with enhanced mobilevit model for mobile devices
title_fullStr Real time weed identification with enhanced mobilevit model for mobile devices
title_full_unstemmed Real time weed identification with enhanced mobilevit model for mobile devices
title_short Real time weed identification with enhanced mobilevit model for mobile devices
title_sort real time weed identification with enhanced mobilevit model for mobile devices
topic Weed identification
MobileViT
CNN
Embedded devices
Model optimization
url https://doi.org/10.1038/s41598-025-12036-0
work_keys_str_mv AT xiaoyanliu realtimeweedidentificationwithenhancedmobilevitmodelformobiledevices
AT qingrusui realtimeweedidentificationwithenhancedmobilevitmodelformobiledevices
AT zhihuichen realtimeweedidentificationwithenhancedmobilevitmodelformobiledevices