Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (2) , (1)
1
2

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.
Fichier principal
Vignette du fichier
EAISA2022_paper_6 (1).pdf (1.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03647740 , version 1 (20-04-2022)

Identifiers

  • HAL Id : hal-03647740 , version 1

Cite

Lucas Mohimont, François Alin, Nathalie Gaveau, Luiz Angelo Steffenel. Lite CNN Models for Real-Time Post-Harvest Grape Disease Detection. Workshop on Edge AI for Smart Agriculture (EAISA 2022), Jun 2022, Biarritz, France. ⟨hal-03647740⟩
71 View
54 Download

Share

Gmail Facebook Twitter LinkedIn More