東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Deep Learning Based Remote Sensing I...

Sun, Huiming,

Linked to FindBook

Google Book

Amazon

博客來

Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios // Huiming Sun.
Author:	Sun, Huiming,
Description:	1 electronic resource (124 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
Contained By:	Dissertations Abstracts International86-01B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31480122
ISBN:	9798382833705

Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios /
Sun, Huiming,

Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios /Huiming Sun. - 1 electronic resource (124 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

With the rapid development of satellite and remote sensing technology, the huge remote sensing data is being accumulated, which has been widely used in many fields, such as land resource monitoring, Unmanned Aerial Vehicle (UAV) traffic surveillance, change detection and so on. Deep learning methods have achieved great success in the field of computer vision, such as image classification, object detection and so on. Deep learning methods can help remote sensing image analysis in many ways, for example, representative feature extraction, accuracy improvement compared to traditional machine learning methods, large-scale parallel image data processing and computation, etc. However, there are still some challenges for deep learning-based remote sensing image analysis under some complex situations, such as thin cloud, thick cloud, adversarial attack and defense, and camouflaging adversarial attack and so on. Directly and simply applying the existing deep learning models on these complex scenarios might fail to some extent.Therefore, this dissertation focuses on the deep learning based remote sensing image analysis under complex scenarios. Specifically, four remote sensing related research problems are systematically studied in this dissertation. For problem 1, we explored the effect of thin clouds on the remote sensing scene classification. For problem 2, we studied the occlusions by thick clouds on the tasks of remote sensing scene classification, cross-view geolocation, and semantic segmentation. For problem 3, we studied the adversarial cloud based hacking attack and defense methods on remote sensing datasets. For problem 4, we investigated camouflaging adversarial attack methods against deep learning based UAV object detection models in real world.Experimental results on the publicized and synthesized remote sensing datasets show the effectiveness and accuracy of the proposed deep learning methods for remote sensing image analysis under complex scenarios.

English

ISBN: 9798382833705Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep learning

Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios /
LDR:03472nmm a22004453i 4500 001 2430649
005 20250527055723.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382833705
035 $a (MiAaPQD)AAI31480122
035 $a AAI31480122
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Sun, Huiming, $e author. $3 3819074
245 1 0 $a Deep Learning Based Remote Sensing Image Analysis Under Complex Scenarios / $c Huiming Sun.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (124 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
500 $a Advisors: Yu, Hongkai Committee members: Chi, Zicheng; Zhang, Tianyun; Lu, Subrina; Rahmati, Mehdi.
502 $b PEG $c Cleveland State University $d 2024.
520 $a With the rapid development of satellite and remote sensing technology, the huge remote sensing data is being accumulated, which has been widely used in many fields, such as land resource monitoring, Unmanned Aerial Vehicle (UAV) traffic surveillance, change detection and so on. Deep learning methods have achieved great success in the field of computer vision, such as image classification, object detection and so on. Deep learning methods can help remote sensing image analysis in many ways, for example, representative feature extraction, accuracy improvement compared to traditional machine learning methods, large-scale parallel image data processing and computation, etc. However, there are still some challenges for deep learning-based remote sensing image analysis under some complex situations, such as thin cloud, thick cloud, adversarial attack and defense, and camouflaging adversarial attack and so on. Directly and simply applying the existing deep learning models on these complex scenarios might fail to some extent.Therefore, this dissertation focuses on the deep learning based remote sensing image analysis under complex scenarios. Specifically, four remote sensing related research problems are systematically studied in this dissertation. For problem 1, we explored the effect of thin clouds on the remote sensing scene classification. For problem 2, we studied the occlusions by thick clouds on the tasks of remote sensing scene classification, cross-view geolocation, and semantic segmentation. For problem 3, we studied the adversarial cloud based hacking attack and defense methods on remote sensing datasets. For problem 4, we investigated camouflaging adversarial attack methods against deep learning based UAV object detection models in real world.Experimental results on the publicized and synthesized remote sensing datasets show the effectiveness and accuracy of the proposed deep learning methods for remote sensing image analysis under complex scenarios.
546 $a English
590 $a School code: 0466
650 4 $a Computer science. $3 523869
650 4 $a Remote sensing. $3 535394
650 4 $a Information technology. $3 532993
653 $a Deep learning
653 $a Unmanned Aerial Vehicle
653 $a Remote sensing image analysis
653 $a Adversarial attacks
653 $a Cloudy environments
690 $a 0984
690 $a 0489
690 $a 0800
690 $a 0799
710 2 $a Cleveland State University. $b Washkewicz College of Engineering. $e degree granting institution. $3 3819075
720 1 $a Yu, Hongkai $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 0466
791 $a PEG
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31480122