A Spectral-Spatial Change Detection Method Based on Simplified 3-D Convolutional Autoencoder for Multitemporal Hyperspectral Images

Change detection for multitemporal hyperspectral images (HSIs) has always been a research hotspot of remote sensing. However, most current detection methods only use spectral information or spatial information separately, and there are many false detection areas in the detection results. Besides, th...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE geoscience and remote sensing letters Ročník 19; s. 1 - 5
Hlavní autori: Zhao, Chunhui, Cheng, Hao, Feng, Shou
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
3-D convolutional autoencoder (3DCAE)
Change detection
Classifiers
Convolution
Data analysis
Data mining
Data processing
Decoding
Detection
Feature extraction
hyperspectral images (HSIs)
Hyperspectral imaging
Kernel
Methods
Neural networks
Redundancy
Remote sensing
Spatial data
spatial–spectral information
Spectra
Training
ISSN:1545-598X, 1558-0571
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Change detection for multitemporal hyperspectral images (HSIs) has always been a research hotspot of remote sensing. However, most current detection methods only use spectral information or spatial information separately, and there are many false detection areas in the detection results. Besides, the feature extraction method based on neural networks needs a huge amount of training samples, but collecting labeled training samples for change detection tasks is difficult. Therefore, this letter proposes a hyperspectral change detection method based on a simplified 3-D convolutional autoencoder (S3DCAECD). First, the framework is based on deep unsupervised autoencoder (AE), which can extract deep spectral-spatial features from bitemporal images without the need for prior information. Second, by adding a 3-D convolution kernel and eliminating the pooling layer, the structure of 3-D convolutional AE is simplified, which can reduce spectral redundancy and improve data processing speed. Finally, a softmax classifier with a 2-D convolutional layer added is used to obtain the detection result, and only a few label samples are needed to train the classifier. Three HSIs' experimental results indicate that the accuracy of the S3DCAECD is more than 95% on three experimental datasets and it has better detection results than several commonly used methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2021.3096526