用于高光谱图像重建的渐进式 CNN 变压器交替重建网络--赤潮检测案例研究

IF 7.6 Q1 REMOTE SENSING
Ying Shen, Ping Zhong, Xiuxing Zhan, Xu Chen, Feng Huang
{"title":"用于高光谱图像重建的渐进式 CNN 变压器交替重建网络--赤潮检测案例研究","authors":"Ying Shen,&nbsp;Ping Zhong,&nbsp;Xiuxing Zhan,&nbsp;Xu Chen,&nbsp;Feng Huang","doi":"10.1016/j.jag.2024.104129","DOIUrl":null,"url":null,"abstract":"<div><p>Spectral reconstruction technology extracts rich detail information from limited spectral bands, thereby enhancing both of the image quality and the resolution capabilities. It finds application in non-destructive testing, elevating the precision and robustness of detection. Current studies primarily focus on improving the local information perception of convolutional neural networks or modeling long-distance dependencies with Transformer. However, such approaches fail to effectively integrate global–local modeling information, resulting in poor accuracy in image reconstruction. This paper introduces a Progressive CNN-Transformer Alternating Reconstruction Network (PCTARN) to alternately utilize robust convolutional attention and transpose Transformer self-attention. A Dual-Path CNN-Transformer Alternating Reconstruction Module (DPCTARM) is proposed to dynamically introduce global–local dynamic priors at various levels to facilitate extracting high- and low-frequency features. This enhancement effectively strengthens PCTARN’s capability to discern valuable signals. To verify the proposed method, a spectral dataset based on seven selected red tide algae is collected. And a peak signal-to-noise ratio (PSNR) metric of 34.58 dB is achieved, which is at least 0.44 dB higher than the methods such as MAUN and MST++. While the Params and FLOPS are reduced by over 41.9 % and 38.4 %, respectively. Since the performance of the proposed PCTARN depends not only on image quality but also on spectral fidelity, an application of spectral detection on red tide are conducted for this purpose. Four feature bands are selected from multispectral images and reconstructed into 20-band hyperspectral images by using PCTARN. Species identification and cell concentration detection are conducted based on the reconstructed images. The results demonstrate that PCTARN can enhance the spatial signal and spectral peak differences of red tide samples, achieving an identification accuracy of 94.21 % and a coefficient of determination (<em>R2</em>) of 0.9660 in species identification and cell concentration detection, which are respectively improved by 11.55 % and 11.59 % compared to those of 4-band multispectral detection.</p></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"134 ","pages":"Article 104129"},"PeriodicalIF":7.6000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1569843224004837/pdfft?md5=7f5f8d8f265f219c5e89890c6de11614&pid=1-s2.0-S1569843224004837-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Progressive CNN-transformer alternating reconstruction network for hyperspectral image reconstruction—A case study in red tide detection\",\"authors\":\"Ying Shen,&nbsp;Ping Zhong,&nbsp;Xiuxing Zhan,&nbsp;Xu Chen,&nbsp;Feng Huang\",\"doi\":\"10.1016/j.jag.2024.104129\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Spectral reconstruction technology extracts rich detail information from limited spectral bands, thereby enhancing both of the image quality and the resolution capabilities. It finds application in non-destructive testing, elevating the precision and robustness of detection. Current studies primarily focus on improving the local information perception of convolutional neural networks or modeling long-distance dependencies with Transformer. However, such approaches fail to effectively integrate global–local modeling information, resulting in poor accuracy in image reconstruction. This paper introduces a Progressive CNN-Transformer Alternating Reconstruction Network (PCTARN) to alternately utilize robust convolutional attention and transpose Transformer self-attention. A Dual-Path CNN-Transformer Alternating Reconstruction Module (DPCTARM) is proposed to dynamically introduce global–local dynamic priors at various levels to facilitate extracting high- and low-frequency features. This enhancement effectively strengthens PCTARN’s capability to discern valuable signals. To verify the proposed method, a spectral dataset based on seven selected red tide algae is collected. And a peak signal-to-noise ratio (PSNR) metric of 34.58 dB is achieved, which is at least 0.44 dB higher than the methods such as MAUN and MST++. While the Params and FLOPS are reduced by over 41.9 % and 38.4 %, respectively. Since the performance of the proposed PCTARN depends not only on image quality but also on spectral fidelity, an application of spectral detection on red tide are conducted for this purpose. Four feature bands are selected from multispectral images and reconstructed into 20-band hyperspectral images by using PCTARN. Species identification and cell concentration detection are conducted based on the reconstructed images. The results demonstrate that PCTARN can enhance the spatial signal and spectral peak differences of red tide samples, achieving an identification accuracy of 94.21 % and a coefficient of determination (<em>R2</em>) of 0.9660 in species identification and cell concentration detection, which are respectively improved by 11.55 % and 11.59 % compared to those of 4-band multispectral detection.</p></div>\",\"PeriodicalId\":73423,\"journal\":{\"name\":\"International journal of applied earth observation and geoinformation : ITC journal\",\"volume\":\"134 \",\"pages\":\"Article 104129\"},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2024-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1569843224004837/pdfft?md5=7f5f8d8f265f219c5e89890c6de11614&pid=1-s2.0-S1569843224004837-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International journal of applied earth observation and geoinformation : ITC journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1569843224004837\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"REMOTE SENSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of applied earth observation and geoinformation : ITC journal","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1569843224004837","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"REMOTE SENSING","Score":null,"Total":0}
引用次数: 0

摘要

光谱重建技术可从有限的光谱波段中提取丰富的细节信息,从而提高图像质量和分辨率。它可应用于无损检测,提高检测的精确度和鲁棒性。目前的研究主要集中在提高卷积神经网络的局部信息感知能力,或利用 Transformer 建立长距离依赖关系模型。然而,这些方法未能有效整合全局-局部建模信息,导致图像重建精度不高。本文介绍了一种渐进式 CNN-变换器交替重建网络(PCTARN),交替使用鲁棒卷积注意力和变换器自注意力。本文提出了一个双路径 CNN-变换器交替重构模块(DPCTARM),在不同层面动态引入全局-局部动态前验,以方便提取高频和低频特征。这一改进有效加强了 PCTARN 识别有价值信号的能力。为了验证所提出的方法,我们收集了基于七种选定赤潮藻类的光谱数据集。该方法的峰值信噪比(PSNR)指标达到了 34.58 dB,比 MAUN 和 MST++ 等方法至少高出 0.44 dB。而 Params 和 FLOPS 分别减少了 41.9% 和 38.4%。由于所提出的 PCTARN 的性能不仅取决于图像质量,还取决于光谱保真度,因此我们对赤潮进行了光谱检测应用。从多光谱图像中选取四个特征波段,利用 PCTARN 重构成 20 波段的高光谱图像。根据重建后的图像进行物种识别和细胞浓度检测。结果表明,PCTARN 能够增强赤潮样本的空间信号和光谱峰值差异,在物种识别和细胞浓度检测方面的识别准确率达到 94.21 %,判定系数 (R2) 为 0.9660,与 4 波段多光谱检测相比分别提高了 11.55 % 和 11.59 %。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Progressive CNN-transformer alternating reconstruction network for hyperspectral image reconstruction—A case study in red tide detection

Spectral reconstruction technology extracts rich detail information from limited spectral bands, thereby enhancing both of the image quality and the resolution capabilities. It finds application in non-destructive testing, elevating the precision and robustness of detection. Current studies primarily focus on improving the local information perception of convolutional neural networks or modeling long-distance dependencies with Transformer. However, such approaches fail to effectively integrate global–local modeling information, resulting in poor accuracy in image reconstruction. This paper introduces a Progressive CNN-Transformer Alternating Reconstruction Network (PCTARN) to alternately utilize robust convolutional attention and transpose Transformer self-attention. A Dual-Path CNN-Transformer Alternating Reconstruction Module (DPCTARM) is proposed to dynamically introduce global–local dynamic priors at various levels to facilitate extracting high- and low-frequency features. This enhancement effectively strengthens PCTARN’s capability to discern valuable signals. To verify the proposed method, a spectral dataset based on seven selected red tide algae is collected. And a peak signal-to-noise ratio (PSNR) metric of 34.58 dB is achieved, which is at least 0.44 dB higher than the methods such as MAUN and MST++. While the Params and FLOPS are reduced by over 41.9 % and 38.4 %, respectively. Since the performance of the proposed PCTARN depends not only on image quality but also on spectral fidelity, an application of spectral detection on red tide are conducted for this purpose. Four feature bands are selected from multispectral images and reconstructed into 20-band hyperspectral images by using PCTARN. Species identification and cell concentration detection are conducted based on the reconstructed images. The results demonstrate that PCTARN can enhance the spatial signal and spectral peak differences of red tide samples, achieving an identification accuracy of 94.21 % and a coefficient of determination (R2) of 0.9660 in species identification and cell concentration detection, which are respectively improved by 11.55 % and 11.59 % compared to those of 4-band multispectral detection.

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
International journal of applied earth observation and geoinformation : ITC journal
International journal of applied earth observation and geoinformation : ITC journal Global and Planetary Change, Management, Monitoring, Policy and Law, Earth-Surface Processes, Computers in Earth Sciences
CiteScore
12.00
自引率
0.00%
发文量
0
审稿时长
77 days
期刊介绍: The International Journal of Applied Earth Observation and Geoinformation publishes original papers that utilize earth observation data for natural resource and environmental inventory and management. These data primarily originate from remote sensing platforms, including satellites and aircraft, supplemented by surface and subsurface measurements. Addressing natural resources such as forests, agricultural land, soils, and water, as well as environmental concerns like biodiversity, land degradation, and hazards, the journal explores conceptual and data-driven approaches. It covers geoinformation themes like capturing, databasing, visualization, interpretation, data quality, and spatial uncertainty.
×
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