Change Detection in Hyperdimensional Images Using Untrained Models

Deep transfer-learning-based change detection methods are dependent on the availability of sensor-specific pretrained feature extractors. Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images. Moreover mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sudipan Saha, Lukas Kondmann, Qian Song, Xiao Xiang Zhu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Change detection (CD) deep image prior deep learning hyperdimensional images hyperspectral images Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/53146cd45cf044e3b2d63aa125ce9297
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:53146cd45cf044e3b2d63aa125ce9297
record_format	dspace
spelling	oai:doaj.org-article:53146cd45cf044e3b2d63aa125ce92972021-11-18T00:00:17ZChange Detection in Hyperdimensional Images Using Untrained Models2151-153510.1109/JSTARS.2021.3121556https://doaj.org/article/53146cd45cf044e3b2d63aa125ce92972021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9582825/https://doaj.org/toc/2151-1535Deep transfer-learning-based change detection methods are dependent on the availability of sensor-specific pretrained feature extractors. Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images. Moreover models trained on easily available multispectral (RGB/RGB-NIR) images cannot be reused on such hyperdimensional images due to their irregular number of bands. While hyperdimensional images show large number of spectral bands, they generally show much less spatial complexity, thus reducing the requirement of large receptive fields of convolution filters. Recent works in the computer vision have shown that even untrained deep models can yield remarkable result in some tasks like super-resolution and surface reconstruction. This motivates us to make a bold proposition that untrained lightweight deep model, initialized with some weight initialization strategy, can be used to extract useful semantic features from bi-temporal hyperdimensional images. Based on this proposition, we design a novel change detection framework for hyperdimensional images by extracting bitemporal features using an untrained model and further comparing the extracted features using deep change vector analysis to distinguish changed pixels from the unchanged ones. We further use the deep change hypervectors to cluster the changed pixels into different semantic groups. We conduct experiments on four change detection datasets: three hyperspectral datasets and a hyperdimensional polarimetric synthetic aperture radar dataset. The results clearly demonstrate that the proposed method is suitable for change detection in hyperdimensional remote sensing data.Sudipan SahaLukas KondmannQian SongXiao Xiang ZhuIEEEarticleChange detection (CD)deep image priordeep learninghyperdimensional imageshyperspectral imagesOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11029-11041 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Change detection (CD) deep image prior deep learning hyperdimensional images hyperspectral images Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Change detection (CD) deep image prior deep learning hyperdimensional images hyperspectral images Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Sudipan Saha Lukas Kondmann Qian Song Xiao Xiang Zhu Change Detection in Hyperdimensional Images Using Untrained Models
description	Deep transfer-learning-based change detection methods are dependent on the availability of sensor-specific pretrained feature extractors. Such feature extractors are not always available due to lack of training data, especially for hyperspectral sensors and other hyperdimensional images. Moreover models trained on easily available multispectral (RGB/RGB-NIR) images cannot be reused on such hyperdimensional images due to their irregular number of bands. While hyperdimensional images show large number of spectral bands, they generally show much less spatial complexity, thus reducing the requirement of large receptive fields of convolution filters. Recent works in the computer vision have shown that even untrained deep models can yield remarkable result in some tasks like super-resolution and surface reconstruction. This motivates us to make a bold proposition that untrained lightweight deep model, initialized with some weight initialization strategy, can be used to extract useful semantic features from bi-temporal hyperdimensional images. Based on this proposition, we design a novel change detection framework for hyperdimensional images by extracting bitemporal features using an untrained model and further comparing the extracted features using deep change vector analysis to distinguish changed pixels from the unchanged ones. We further use the deep change hypervectors to cluster the changed pixels into different semantic groups. We conduct experiments on four change detection datasets: three hyperspectral datasets and a hyperdimensional polarimetric synthetic aperture radar dataset. The results clearly demonstrate that the proposed method is suitable for change detection in hyperdimensional remote sensing data.
format	article
author	Sudipan Saha Lukas Kondmann Qian Song Xiao Xiang Zhu
author_facet	Sudipan Saha Lukas Kondmann Qian Song Xiao Xiang Zhu
author_sort	Sudipan Saha
title	Change Detection in Hyperdimensional Images Using Untrained Models
title_short	Change Detection in Hyperdimensional Images Using Untrained Models
title_full	Change Detection in Hyperdimensional Images Using Untrained Models
title_fullStr	Change Detection in Hyperdimensional Images Using Untrained Models
title_full_unstemmed	Change Detection in Hyperdimensional Images Using Untrained Models
title_sort	change detection in hyperdimensional images using untrained models
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/53146cd45cf044e3b2d63aa125ce9297
work_keys_str_mv	AT sudipansaha changedetectioninhyperdimensionalimagesusinguntrainedmodels AT lukaskondmann changedetectioninhyperdimensionalimagesusinguntrainedmodels AT qiansong changedetectioninhyperdimensionalimagesusinguntrainedmodels AT xiaoxiangzhu changedetectioninhyperdimensionalimagesusinguntrainedmodels
_version_	1718425224779661312

Change Detection in Hyperdimensional Images Using Untrained Models

Ejemplares similares