Deploying Deep Neural Networks on Edge Devices for Grape Segmentation

Roesler, Mathias; Mohimont, Lucas; Alin, François; Gaveau, Nathalie; Steffenel, Luiz Angelo

doi:10.1007/978-3-030-88259-4_3

Search citation statements

Order By: Relevance

Paper Sections

Select...

Discussion1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

Publication Types

Select...

Book1

Other1

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A compromise between accuracy and inference speed is necessary for a practical implementation of the existing models for real-time usage. A previous segmentation model was already optimized for embedded execution in STM32 boards and Jetson Nano [23]. Better segmentation speed is expected with the current model.…”

Section: Discussionmentioning

confidence: 97%

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

Mohimont

Alin

Gaveau

et al. 2022

Ambient Intelligence and Smart Environments

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 97%