Next-Generation Hyperspectral Image Analysis: Using Deep Learning Method
暫譯: 下一代高光譜影像分析：使用深度學習方法
M. Haut, Juan, E. Paoletti, Mercedes
- 出版商: Springer
- 出版日期: 2026-04-07
- 售價: $8,420
- 貴賓價: 9.5 折 $7,999
- 語言: 英文
- 頁數: 269
- 裝訂: Hardcover - also called cloth, retail trade, or trade
- ISBN: 9819520371
- ISBN-13: 9789819520374
-
相關分類:
DeepLearning
海外代購書籍(需單獨結帳)
商品描述
This book is a comprehensive guide that bridges the gap between foundational principles and cutting-edge advancements in hyperspectral imaging and deep learning. With contributions from leading international experts, this book covers a wide range of topics essential for researchers, engineers, and professionals in the field.
This book begins with an introduction to hyperspectral imaging and deep learning, setting the stage for more advanced discussions. Subsequent chapters delve into neural network architectures, graph-based methods, generative models, and the application of transformers in hyperspectral imaging. Each chapter not only presents theoretical insights but also practical applications, making complex concepts accessible and relevant.
Readers will discover methods to optimize deep learning models through techniques like quantization and pruning, ensuring efficiency without sacrificing performance. Additionally, this book addresses the practical challenges of managing and processing large volumes of hyperspectral data, offering strategies for data storage, management, and parallel processing.
Exclusive online resources, including example codes, tutorials, and hyperspectral datasets, complement the comprehensive content, enabling readers to apply what they learn in real-world scenarios. This book is an indispensable resource for anyone looking to harness the power of hyperspectral technology to drive innovation and solve complex problems.
商品描述(中文翻譯)
這本書是一本全面的指南，橋接了高光譜成像和深度學習的基礎原則與前沿進展之間的鴻溝。書中匯集了國際領先專家的貢獻，涵蓋了對於該領域的研究人員、工程師和專業人士至關重要的廣泛主題。
本書首先介紹高光譜成像和深度學習，為更深入的討論奠定基礎。隨後的章節深入探討神經網絡架構、基於圖的方法、生成模型以及變壓器在高光譜成像中的應用。每一章不僅提供理論見解，還包含實際應用，使複雜的概念變得易於理解且相關。
讀者將發現通過量化和剪枝等技術來優化深度學習模型的方法，確保效率而不犧牲性能。此外，本書還解決了管理和處理大量高光譜數據的實際挑戰，提供數據存儲、管理和並行處理的策略。
獨家的線上資源，包括範例代碼、教程和高光譜數據集，補充了全面的內容，使讀者能夠在現實場景中應用所學知識。這本書是任何希望利用高光譜技術推動創新和解決複雜問題的人的必備資源。
作者簡介
Juan Mario Haut is an associate professor in the Department of Computer and Communication Technology at the University of Extremadura. The topic of his research covers the efficient analysis of remotely sensed (RS) images collected from Earth's surface Observation platforms through the design and implementation of novel machine (ML) and deep learning (DL) processing methods. Dr. Haut delves into the application of Big Data and High-performance Computing (HPC) strategies, such as parallelization and distribution over GPU devices and Cloud Computing platforms, combined with deep neural networks for large and complex RS dataset analysis, such as hyperspectral and multispectral images. Dr. Haut is an author and a co-author of more than 120 scientific publications, including more than 70 contributions to JCR journals and more than 50 contributions to congresses, both national (17) and international (36) of relevance such as IEEE IGARSS, IEEE WHISPERS, or IEEE CBMS, and 1 book chapter.
M.E. Paoletti is a professor in the Department of Computer and Communication Technology at the University Centre of Merida, University of Extremadura, and a researcher at the Hyperspectral Computing Laboratory (HyperComp). Her research focuses on the efficient processing of remote sensed hyperspectral images through the development of deep learning techniques combined with graphical processing. Dr. Paoletti is author and co-author of 117 scientific publications, including 70 contributions to JCR journals, 49 contributions to congresses, both national (16) and international (33) of relevance such as IEEE IGARSS, IEEE WHISPERS, or IEEE CBMS, and 1 book chapter. Her JCR contributions stand out in the fields of computation (e.g., Journal of Supercomputing), neural networks (e.g., IEEE TNNLS and Neurocomputing), and remote sensing (e.g., IEEE TGRS, IEEE GRSL, or IEEE GRSM), having 8 highly cited articles with 2 research fronts (InCites Essential Science Indicators of Clarivate).
作者簡介(中文翻譯)
胡安·馬里奧·豪特（Juan Mario Haut）是埃斯特雷馬杜拉大學（University of Extremadura）計算機與通信技術系的副教授。他的研究主題涵蓋從地球表面觀測平台收集的遙感（RS）影像的高效分析，透過設計和實施新穎的機器學習（ML）和深度學習（DL）處理方法。豪特博士深入探討大數據（Big Data）和高效能計算（HPC）策略的應用，例如在GPU設備和雲計算平台上的平行化和分佈，結合深度神經網絡對大型和複雜的遙感數據集進行分析，如高光譜和多光譜影像。豪特博士是120多篇科學出版物的作者和合著者，其中包括70多篇對JCR期刊的貢獻，以及50多篇對國內（17篇）和國際（36篇）重要會議的貢獻，如IEEE IGARSS、IEEE WHISPERS或IEEE CBMS，並且有1章書籍。
梅·保萊提（M.E. Paoletti）是埃斯特雷馬杜拉大學梅里達大學中心（University Centre of Merida）計算機與通信技術系的教授，以及高光譜計算實驗室（Hyperspectral Computing Laboratory, HyperComp）的研究員。她的研究專注於通過開發結合圖形處理的深度學習技術來高效處理遙感高光譜影像。保萊提博士是117篇科學出版物的作者和合著者，其中包括70篇對JCR期刊的貢獻，49篇對國內（16篇）和國際（33篇）重要會議的貢獻，如IEEE IGARSS、IEEE WHISPERS或IEEE CBMS，並且有1章書籍。她在計算（例如，《超級計算期刊》）、神經網絡（例如，IEEE TNNLS和Neurocomputing）和遙感（例如，IEEE TGRS、IEEE GRSL或IEEE GRSM）領域的JCR貢獻尤為突出，擁有8篇高被引文章，並有2個研究前沿（根據Clarivate的InCites Essential Science Indicators）。
