A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation
Fish vaccination plays a vital role in the prevention of fish diseases. Inappropriate injection positions will cause a low immunization rate and even death. Currently, traditional visual algorithms have poor robustness and low accuracy due to the specificity of the placement of turbot fins in the ap...
Published in: | Fishes |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/fishes7060385 https://doaj.org/article/bcd9d03b5b6447eab4dce369a413a506 |
id |
ftdoajarticles:oai:doaj.org/article:bcd9d03b5b6447eab4dce369a413a506 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:bcd9d03b5b6447eab4dce369a413a506 2023-05-15T18:15:50+02:00 A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation Wei Luo Chen Li Kang Wu Songming Zhu Zhangying Ye Jianping Li 2022-12-01T00:00:00Z https://doi.org/10.3390/fishes7060385 https://doaj.org/article/bcd9d03b5b6447eab4dce369a413a506 EN eng MDPI AG https://www.mdpi.com/2410-3888/7/6/385 https://doaj.org/toc/2410-3888 doi:10.3390/fishes7060385 2410-3888 https://doaj.org/article/bcd9d03b5b6447eab4dce369a413a506 Fishes, Vol 7, Iss 385, p 385 (2022) turbot vaccination deeplabv3+ attention mechanism measurement aquaculture Biology (General) QH301-705.5 Genetics QH426-470 article 2022 ftdoajarticles https://doi.org/10.3390/fishes7060385 2022-12-30T19:32:03Z Fish vaccination plays a vital role in the prevention of fish diseases. Inappropriate injection positions will cause a low immunization rate and even death. Currently, traditional visual algorithms have poor robustness and low accuracy due to the specificity of the placement of turbot fins in the application of automatic vaccination machines. To address this problem, we propose a new method for estimating the injection position of the turbot based on semantic segmentation. Many semantic segmentation networks were used to extract the background, fish body, pectoral fin, and caudal fin. In the subsequent step, the segmentations obtained from the best network were used for calculating body length (BL) and body width (BW). These parameters were employed for estimating the injection position. The proposed Atten-Deeplabv3+ achieved the best segmentation results for intersection over union (IoU) on the test set, with 99.3, 96.5, 85.8, and 91.7 percent for background, fish body, pectoral fin, and caudal fin, respectively. On this basis, the estimation error of the injection position was 0.2 mm–4.4 mm, which is almost within the allowable injection area. In conclusion, the devised method was able to correctly differentiate the fish body from the background and fins, meaning that the extracted area could be successfully used for the estimation of injection position. Article in Journal/Newspaper Scophthalmus maximus Turbot Directory of Open Access Journals: DOAJ Articles Fishes 7 6 385 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
turbot vaccination deeplabv3+ attention mechanism measurement aquaculture Biology (General) QH301-705.5 Genetics QH426-470 |
spellingShingle |
turbot vaccination deeplabv3+ attention mechanism measurement aquaculture Biology (General) QH301-705.5 Genetics QH426-470 Wei Luo Chen Li Kang Wu Songming Zhu Zhangying Ye Jianping Li A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
topic_facet |
turbot vaccination deeplabv3+ attention mechanism measurement aquaculture Biology (General) QH301-705.5 Genetics QH426-470 |
description |
Fish vaccination plays a vital role in the prevention of fish diseases. Inappropriate injection positions will cause a low immunization rate and even death. Currently, traditional visual algorithms have poor robustness and low accuracy due to the specificity of the placement of turbot fins in the application of automatic vaccination machines. To address this problem, we propose a new method for estimating the injection position of the turbot based on semantic segmentation. Many semantic segmentation networks were used to extract the background, fish body, pectoral fin, and caudal fin. In the subsequent step, the segmentations obtained from the best network were used for calculating body length (BL) and body width (BW). These parameters were employed for estimating the injection position. The proposed Atten-Deeplabv3+ achieved the best segmentation results for intersection over union (IoU) on the test set, with 99.3, 96.5, 85.8, and 91.7 percent for background, fish body, pectoral fin, and caudal fin, respectively. On this basis, the estimation error of the injection position was 0.2 mm–4.4 mm, which is almost within the allowable injection area. In conclusion, the devised method was able to correctly differentiate the fish body from the background and fins, meaning that the extracted area could be successfully used for the estimation of injection position. |
format |
Article in Journal/Newspaper |
author |
Wei Luo Chen Li Kang Wu Songming Zhu Zhangying Ye Jianping Li |
author_facet |
Wei Luo Chen Li Kang Wu Songming Zhu Zhangying Ye Jianping Li |
author_sort |
Wei Luo |
title |
A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
title_short |
A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
title_full |
A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
title_fullStr |
A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
title_full_unstemmed |
A Method for Estimating the Injection Position of Turbot ( Scophthalmus maximus ) Using Semantic Segmentation |
title_sort |
method for estimating the injection position of turbot ( scophthalmus maximus ) using semantic segmentation |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/fishes7060385 https://doaj.org/article/bcd9d03b5b6447eab4dce369a413a506 |
genre |
Scophthalmus maximus Turbot |
genre_facet |
Scophthalmus maximus Turbot |
op_source |
Fishes, Vol 7, Iss 385, p 385 (2022) |
op_relation |
https://www.mdpi.com/2410-3888/7/6/385 https://doaj.org/toc/2410-3888 doi:10.3390/fishes7060385 2410-3888 https://doaj.org/article/bcd9d03b5b6447eab4dce369a413a506 |
op_doi |
https://doi.org/10.3390/fishes7060385 |
container_title |
Fishes |
container_volume |
7 |
container_issue |
6 |
container_start_page |
385 |
_version_ |
1766189063614758912 |