FCS-Net:基于 RGB 和热红外图像密集特征融合的肉鸡羽毛状况评分法

IF 4.4 1区 农林科学 Q1 AGRICULTURAL ENGINEERING
{"title":"FCS-Net:基于 RGB 和热红外图像密集特征融合的肉鸡羽毛状况评分法","authors":"","doi":"10.1016/j.biosystemseng.2024.09.002","DOIUrl":null,"url":null,"abstract":"<div><p>Assessing the feather condition of broilers is crucial for monitoring the animal welfare status and detecting the occurrence of feather pecking activities. Currently, the feather condition of individual broilers is manually scored by trained experts. To provide a more objective and efficient tool for feather condition scoring, a novel deep learning-based model, named Feather Condition Scoring Network (FCS-Net), was proposed based on RGB and thermal infrared images. The FCS-Net model combined the ResNet18 architecture with the proposed Dense Feature Fusion (DFF) module, which can effectively learn the feature mapping relationship between RGB and thermal infrared images. Before inputting the images into the network, an image registration process was conducted to align the RGB and thermal infrared images. The results showed that the FCS-Net model had a good performance for feather condition scoring, with the <em>Accuracy</em> of 97.02%, the <em>Precision</em> of 96.99%, the <em>Recall</em> of 97.04%, the <em>F</em><sub>1</sub> of 97.01%, and the <em>Inference speed</em> of 15.34 fps. Compared to the ResNet18_RGB model, which only utilise RGB images, the FCS-Net model showed notable improvements in <em>Accuracy</em> by 4.02%, <em>Precision</em> by 3.90%, <em>Recall</em> by 4.08%, and <em>F</em><sub>1</sub> by 4.01%. Moreover, it was observed that the FCS-Net model focused more on the back region of the broilers through heatmap visualization. Furthermore, the algorithm was compared with six typical image recognition algorithms including VGG16, ResNet18, SE-ResNet18, DenseNet121, Mobilenet_V2, and Shufflenet_V2_<em>x</em>1_0, as well as the state-of-the-art (SOTA) feather condition assessment methods. The results showed that the FCS-Net model achieved better performance than the six algorithms and the SOTA feather condition assessment methods. This study provided a valuable reference for automated monitoring of feather condition scoring of broilers in smart farming.</p></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FCS-Net: Feather condition scoring of broilers based on dense feature fusion of RGB and thermal infrared images\",\"authors\":\"\",\"doi\":\"10.1016/j.biosystemseng.2024.09.002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Assessing the feather condition of broilers is crucial for monitoring the animal welfare status and detecting the occurrence of feather pecking activities. Currently, the feather condition of individual broilers is manually scored by trained experts. To provide a more objective and efficient tool for feather condition scoring, a novel deep learning-based model, named Feather Condition Scoring Network (FCS-Net), was proposed based on RGB and thermal infrared images. The FCS-Net model combined the ResNet18 architecture with the proposed Dense Feature Fusion (DFF) module, which can effectively learn the feature mapping relationship between RGB and thermal infrared images. Before inputting the images into the network, an image registration process was conducted to align the RGB and thermal infrared images. The results showed that the FCS-Net model had a good performance for feather condition scoring, with the <em>Accuracy</em> of 97.02%, the <em>Precision</em> of 96.99%, the <em>Recall</em> of 97.04%, the <em>F</em><sub>1</sub> of 97.01%, and the <em>Inference speed</em> of 15.34 fps. Compared to the ResNet18_RGB model, which only utilise RGB images, the FCS-Net model showed notable improvements in <em>Accuracy</em> by 4.02%, <em>Precision</em> by 3.90%, <em>Recall</em> by 4.08%, and <em>F</em><sub>1</sub> by 4.01%. Moreover, it was observed that the FCS-Net model focused more on the back region of the broilers through heatmap visualization. Furthermore, the algorithm was compared with six typical image recognition algorithms including VGG16, ResNet18, SE-ResNet18, DenseNet121, Mobilenet_V2, and Shufflenet_V2_<em>x</em>1_0, as well as the state-of-the-art (SOTA) feather condition assessment methods. The results showed that the FCS-Net model achieved better performance than the six algorithms and the SOTA feather condition assessment methods. This study provided a valuable reference for automated monitoring of feather condition scoring of broilers in smart farming.</p></div>\",\"PeriodicalId\":9173,\"journal\":{\"name\":\"Biosystems Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biosystems Engineering\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1537511024002046\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biosystems Engineering","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1537511024002046","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

摘要

评估肉鸡的羽毛状况对于监测动物福利状况和检测啄羽行为的发生至关重要。目前,个体肉鸡的羽毛状况由训练有素的专家进行人工评分。为了提供一种更客观、更高效的羽毛状况评分工具,我们提出了一种基于 RGB 和热红外图像的新型深度学习模型,名为羽毛状况评分网络(FCS-Net)。FCS-Net 模型将 ResNet18 架构与所提出的密集特征融合(DFF)模块相结合,可有效学习 RGB 和热红外图像之间的特征映射关系。在将图像输入网络之前,进行了图像配准处理,以对齐 RGB 和热红外图像。结果表明,FCS-Net 模型在羽毛状况评分方面表现良好,准确率为 97.02%,精确率为 96.99%,召回率为 97.04%,F1 为 97.01%,推理速度为 15.34 fps。与只使用 RGB 图像的 ResNet18_RGB 模型相比,FCS-Net 模型的准确率显著提高了 4.02%,精确率提高了 3.90%,召回率提高了 4.08%,F1 提高了 4.01%。此外,通过热图可视化观察还发现,FCS-Net 模型更关注肉鸡的背部区域。此外,该算法还与六种典型的图像识别算法进行了比较,包括 VGG16、ResNet18、SE-ResNet18、DenseNet121、Mobilenet_V2 和 Shufflenet_V2_x1_0,以及最先进的(SOTA)羽毛状况评估方法。结果表明,FCS-Net 模型的性能优于六种算法和 SOTA 羽绒状况评估方法。该研究为智能养殖中肉鸡羽毛状况评分的自动监测提供了有价值的参考。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FCS-Net: Feather condition scoring of broilers based on dense feature fusion of RGB and thermal infrared images

Assessing the feather condition of broilers is crucial for monitoring the animal welfare status and detecting the occurrence of feather pecking activities. Currently, the feather condition of individual broilers is manually scored by trained experts. To provide a more objective and efficient tool for feather condition scoring, a novel deep learning-based model, named Feather Condition Scoring Network (FCS-Net), was proposed based on RGB and thermal infrared images. The FCS-Net model combined the ResNet18 architecture with the proposed Dense Feature Fusion (DFF) module, which can effectively learn the feature mapping relationship between RGB and thermal infrared images. Before inputting the images into the network, an image registration process was conducted to align the RGB and thermal infrared images. The results showed that the FCS-Net model had a good performance for feather condition scoring, with the Accuracy of 97.02%, the Precision of 96.99%, the Recall of 97.04%, the F1 of 97.01%, and the Inference speed of 15.34 fps. Compared to the ResNet18_RGB model, which only utilise RGB images, the FCS-Net model showed notable improvements in Accuracy by 4.02%, Precision by 3.90%, Recall by 4.08%, and F1 by 4.01%. Moreover, it was observed that the FCS-Net model focused more on the back region of the broilers through heatmap visualization. Furthermore, the algorithm was compared with six typical image recognition algorithms including VGG16, ResNet18, SE-ResNet18, DenseNet121, Mobilenet_V2, and Shufflenet_V2_x1_0, as well as the state-of-the-art (SOTA) feather condition assessment methods. The results showed that the FCS-Net model achieved better performance than the six algorithms and the SOTA feather condition assessment methods. This study provided a valuable reference for automated monitoring of feather condition scoring of broilers in smart farming.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Biosystems Engineering
Biosystems Engineering 农林科学-农业工程
CiteScore
10.60
自引率
7.80%
发文量
239
审稿时长
53 days
期刊介绍: Biosystems Engineering publishes research in engineering and the physical sciences that represent advances in understanding or modelling of the performance of biological systems for sustainable developments in land use and the environment, agriculture and amenity, bioproduction processes and the food chain. The subject matter of the journal reflects the wide range and interdisciplinary nature of research in engineering for biological systems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信