Change Detection in Hyperdimensional Images Using Untrained Models
Open Access
- 20 October 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 14 (19391404) , 11029-11041
Abstract
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.Keywords
Funding Information
- Helmholtz Association (W2-W3-100, ZT-I-PF-5-01)
- Bundesministerium fr Bildung und Forschung (01DD20001)
- H2020 European Research Council (ERC-2016-StG-714087)
This publication has 45 references indexed in Scilit:
- Unsupervised change detection analysis to multi-channel scenario based on morphological contextual analysis2016
- Robust Change Vector Analysis (RCVA) for multi-sensor very high resolution optical satellite dataInternational Journal of Applied Earth Observation and Geoinformation, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Rayleigh-Rice Mixture Parameter Estimation via EM Algorithm for Change Detection in Multispectral ImagesIEEE Transactions on Image Processing, 2015
- Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means ClusteringIEEE Geoscience and Remote Sensing Letters, 2009
- Survey over image thresholding techniques and quantitative performance evaluationJournal of Electronic Imaging, 2004
- Automatic analysis of the difference image for unsupervised change detectionIEEE Transactions on Geoscience and Remote Sensing, 2000
- A review of target decomposition theorems in radar polarimetryIEEE Transactions on Geoscience and Remote Sensing, 1996
- Minimum cross entropy thresholdingPattern Recognition, 1993
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979