Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection-Reference-Cited by-同舟云学术

Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection

Published:2022-06-14 Issue: Volume: Page:
ISSN:1875-4163
Container-title:Ambient Intelligence and Smart Environments
language:
Short-container-title:

Author:

Mohimont Lucas¹²,Alin François¹,Gaveau Nathalie²,Steffenel Luiz Angelo¹

Affiliation:

1. Université de Reims Champagne Ardenne, LICIIS - LRC CEA DIGIT, 51687 Reims Cedex 2, France

2. Université de Reims Champagne Ardenne, RIBP - EA4707 - USC - INRAE 1488 51100 Reims Cedex 2, France

Abstract

Post-harvest fruit grading is a necessary step to avoid disease related loss in quality. In this paper, a hierarchical method is proposed to (1) remove the background and (2) detect images that contains grape diseases(botrytis, oidium, acid rot). Satisfying segmentation performances were obtained by the proposed Lite Unet model with 92.9% IoU score and an average speed of 0.16s/image. A pretrained MobileNet-V2 model obtained 94% F1 score on disease classification. An optimized CNN reached a score of 89% with less than 10 times less parameters. The implementation of both segmentation and classification models on low-powered device would allow for real-time disease detection at the press.

Publisher

IOS Press

Link

https://ebooks.iospress.nl/pdf/doi/10.3233/AISE220029

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Machine Learning Algorithms Aided Disease Diagnosis and Prediction of Grape Leaf;Intelligent Systems;2023-10-06

2. Clustering Based Segmentation with 1D-CNN Model for Grape Fruit Disease Detection;2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS);2023-02-24

3. On the Use of a Semantic Segmentation Micro-Service in AR Devices for UI Placement;2022 IEEE Games, Entertainment, Media Conference (GEM);2022-11-27