YOLOv5-LiNet: A lightweight network for fruits instance segmentation
To meet the goals of computer vision-based understanding of images adopted in agriculture for improved fruit production, it is expected of a recognition model to be robust against complex and changeable environment, fast, accurate and lightweight for a low power computing platform deployment. For th...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9980778/?tool=EBI |
_version_ | 1811159888387112960 |
---|---|
author | Olarewaju Mubashiru Lawal |
author_facet | Olarewaju Mubashiru Lawal |
author_sort | Olarewaju Mubashiru Lawal |
collection | DOAJ |
description | To meet the goals of computer vision-based understanding of images adopted in agriculture for improved fruit production, it is expected of a recognition model to be robust against complex and changeable environment, fast, accurate and lightweight for a low power computing platform deployment. For this reason, a lightweight YOLOv5-LiNet model for fruit instance segmentation to strengthen fruit detection was proposed based on the modified YOLOv5n. The model included Stem, Shuffle_Block, ResNet and SPPF as backbone network, PANet as neck network, and EIoU loss function to enhance detection performance. YOLOv5-LiNet was compared to YOLOv5n, YOLOv5-GhostNet, YOLOv5-MobileNetv3, YOLOv5-LiNetBiFPN, YOLOv5-LiNetC, YOLOv5-LiNet, YOLOv5-LiNetFPN, YOLOv5-Efficientlite, YOLOv4-tiny and YOLOv5-ShuffleNetv2 lightweight model including Mask-RCNN. The obtained results show that YOLOv5-LiNet having the box accuracy of 0.893, instance segmentation accuracy of 0.885, weight size of 3.0 MB and real-time detection of 2.6 ms combined together outperformed other lightweight models. Therefore, the YOLOv5-LiNet model is robust, accurate, fast, applicable to low power computing devices and extendable to other agricultural products for instance segmentation. |
first_indexed | 2024-04-10T05:48:19Z |
format | Article |
id | doaj.art-23ff969c6d144a59a1c8e65668537ec6 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-10T05:48:19Z |
publishDate | 2023-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-23ff969c6d144a59a1c8e65668537ec62023-03-05T05:31:28ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01183YOLOv5-LiNet: A lightweight network for fruits instance segmentationOlarewaju Mubashiru LawalTo meet the goals of computer vision-based understanding of images adopted in agriculture for improved fruit production, it is expected of a recognition model to be robust against complex and changeable environment, fast, accurate and lightweight for a low power computing platform deployment. For this reason, a lightweight YOLOv5-LiNet model for fruit instance segmentation to strengthen fruit detection was proposed based on the modified YOLOv5n. The model included Stem, Shuffle_Block, ResNet and SPPF as backbone network, PANet as neck network, and EIoU loss function to enhance detection performance. YOLOv5-LiNet was compared to YOLOv5n, YOLOv5-GhostNet, YOLOv5-MobileNetv3, YOLOv5-LiNetBiFPN, YOLOv5-LiNetC, YOLOv5-LiNet, YOLOv5-LiNetFPN, YOLOv5-Efficientlite, YOLOv4-tiny and YOLOv5-ShuffleNetv2 lightweight model including Mask-RCNN. The obtained results show that YOLOv5-LiNet having the box accuracy of 0.893, instance segmentation accuracy of 0.885, weight size of 3.0 MB and real-time detection of 2.6 ms combined together outperformed other lightweight models. Therefore, the YOLOv5-LiNet model is robust, accurate, fast, applicable to low power computing devices and extendable to other agricultural products for instance segmentation.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9980778/?tool=EBI |
spellingShingle | Olarewaju Mubashiru Lawal YOLOv5-LiNet: A lightweight network for fruits instance segmentation PLoS ONE |
title | YOLOv5-LiNet: A lightweight network for fruits instance segmentation |
title_full | YOLOv5-LiNet: A lightweight network for fruits instance segmentation |
title_fullStr | YOLOv5-LiNet: A lightweight network for fruits instance segmentation |
title_full_unstemmed | YOLOv5-LiNet: A lightweight network for fruits instance segmentation |
title_short | YOLOv5-LiNet: A lightweight network for fruits instance segmentation |
title_sort | yolov5 linet a lightweight network for fruits instance segmentation |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9980778/?tool=EBI |
work_keys_str_mv | AT olarewajumubashirulawal yolov5linetalightweightnetworkforfruitsinstancesegmentation |