Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism

At present, the monitoring technology of the growth status of sika deer antlers faces many challenges in a complex breeding environment (such as light change, object occlusion, etc.). More importantly, an effective method for the segmentation of sika deer antlers is still lacking, which hinders the...

Full description

Saved in:
Bibliographic Details
Main Authors: Haotian Gong, Jinfan Wei, Yu Sun, Zhipeng Li, He Gong, Juanjuan Fan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Animals
Subjects:
Online Access:https://www.mdpi.com/2076-2615/15/10/1388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255095644553216
author Haotian Gong
Jinfan Wei
Yu Sun
Zhipeng Li
He Gong
Juanjuan Fan
author_facet Haotian Gong
Jinfan Wei
Yu Sun
Zhipeng Li
He Gong
Juanjuan Fan
author_sort Haotian Gong
collection DOAJ
description At present, the monitoring technology of the growth status of sika deer antlers faces many challenges in a complex breeding environment (such as light change, object occlusion, etc.). More importantly, an effective method for the segmentation of sika deer antlers is still lacking, which hinders the development of subsequent quality classification of sika deer antlers. In order to fill the research gap and lay a foundation for future sika deer antler quality classification, this paper proposed an improved semantic segmentation model based on U-Net, named SDAS-Net. In order to improve the segmentation accuracy and generalization ability of the model in a complex environment, we introduced a two-dimensional discrete wavelet transform module (2D-DWT) in the encoder head to reduce noise interference and enhance the ability to capture features. In order to compensate for the loss of feature information caused by 2D-DWT, we embedded the Star Blocks module in the encoder. In addition, the efficient mixed channel attention (EMCA) module was introduced to adaptively enhance key feature channels in the decoder, and the dual cross-attention mechanism (DCA) module was used to fuse high-dimensional features in skip connections. To verify the validity of the model, we constructed a 1055-image sika deer antler dataset (SDR). The experimental results show that compared with the baseline model, the performance of the SDAS-Net model is significantly improved, reaching 92.12% in MIoU and 93.63% in the PA index, and the number of parameters is only increased by 6.9%. The results show that the SDAS-Net model can effectively deal with the task of sika deer antler segmentation in a complex breeding environment while maintaining high precision.
format Article
id doaj-art-2bdbed6e22cf4266af26e93a8d54105a
institution OA Journals
issn 2076-2615
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Animals
spelling doaj-art-2bdbed6e22cf4266af26e93a8d54105a2025-08-20T01:56:57ZengMDPI AGAnimals2076-26152025-05-011510138810.3390/ani15101388Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention MechanismHaotian Gong0Jinfan Wei1Yu Sun2Zhipeng Li3He Gong4Juanjuan Fan5College of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Animal Science and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaAt present, the monitoring technology of the growth status of sika deer antlers faces many challenges in a complex breeding environment (such as light change, object occlusion, etc.). More importantly, an effective method for the segmentation of sika deer antlers is still lacking, which hinders the development of subsequent quality classification of sika deer antlers. In order to fill the research gap and lay a foundation for future sika deer antler quality classification, this paper proposed an improved semantic segmentation model based on U-Net, named SDAS-Net. In order to improve the segmentation accuracy and generalization ability of the model in a complex environment, we introduced a two-dimensional discrete wavelet transform module (2D-DWT) in the encoder head to reduce noise interference and enhance the ability to capture features. In order to compensate for the loss of feature information caused by 2D-DWT, we embedded the Star Blocks module in the encoder. In addition, the efficient mixed channel attention (EMCA) module was introduced to adaptively enhance key feature channels in the decoder, and the dual cross-attention mechanism (DCA) module was used to fuse high-dimensional features in skip connections. To verify the validity of the model, we constructed a 1055-image sika deer antler dataset (SDR). The experimental results show that compared with the baseline model, the performance of the SDAS-Net model is significantly improved, reaching 92.12% in MIoU and 93.63% in the PA index, and the number of parameters is only increased by 6.9%. The results show that the SDAS-Net model can effectively deal with the task of sika deer antler segmentation in a complex breeding environment while maintaining high precision.https://www.mdpi.com/2076-2615/15/10/1388sika deer antlersemantic segmentationU-Net2D-DWTEMCA
spellingShingle Haotian Gong
Jinfan Wei
Yu Sun
Zhipeng Li
He Gong
Juanjuan Fan
Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
Animals
sika deer antler
semantic segmentation
U-Net
2D-DWT
EMCA
title Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
title_full Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
title_fullStr Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
title_full_unstemmed Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
title_short Semantic Segmentation of Sika Deer Antler Image by U-Net Based on Two-Dimensional Discrete Wavelet Transform Fusion and Multi-Attention Mechanism
title_sort semantic segmentation of sika deer antler image by u net based on two dimensional discrete wavelet transform fusion and multi attention mechanism
topic sika deer antler
semantic segmentation
U-Net
2D-DWT
EMCA
url https://www.mdpi.com/2076-2615/15/10/1388
work_keys_str_mv AT haotiangong semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism
AT jinfanwei semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism
AT yusun semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism
AT zhipengli semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism
AT hegong semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism
AT juanjuanfan semanticsegmentationofsikadeerantlerimagebyunetbasedontwodimensionaldiscretewavelettransformfusionandmultiattentionmechanism