Combining spectral matching and anomalous change detection for target rediscovery in hyperspectral images

Introductory view of anomalous change detection in hyperspectral images within a theoretical gaussian framework

IEEE Aerospace and Electronic Systems Magazine ◽

10.1109/maes.2017.160155 ◽

2017 ◽

Vol 32 (7) ◽

pp. 2-27 ◽

Cited By ~ 6

Author(s):

Nicola Acito ◽

Marco Diani ◽

Giovanni Corsini ◽

Salvatore Resta

Keyword(s):

Change Detection ◽

Hyperspectral Images ◽

Anomalous Change

Download Full-text

A theoretical Gaussian framework for anomalous change detection in hyperspectral images

Image and Signal Processing for Remote Sensing XXIII ◽

10.1117/12.2278225 ◽

2017 ◽

Author(s):

Nicola Acito ◽

Marco Diani ◽

Giovanni Corsini

Keyword(s):

Change Detection ◽

Hyperspectral Images ◽

Anomalous Change

Download Full-text

A novel change detection method for multitemporal hyperspectral images based on a discrete representation of the change information

2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) ◽

10.1109/igarss.2017.8126919 ◽

2017 ◽

Cited By ~ 2

Author(s):

Daniele Marinelli ◽

Francesca Bovolo ◽

Lorenzo Bruzzone

Keyword(s):

Change Detection ◽

Detection Method ◽

Hyperspectral Images ◽

Discrete Representation

Download Full-text

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

Remote Sensing ◽

10.3390/rs10111827 ◽

2018 ◽

Vol 10 (11) ◽

pp. 1827 ◽

Cited By ~ 24

Author(s):

Ahram Song ◽

Jaewan Choi ◽

Youkyung Han ◽

Yongil Kim

Keyword(s):

Deep Learning ◽

Change Detection ◽

Spatial Information ◽

Short Term Memory ◽

Hyperspectral Images ◽

Convolutional Network ◽

Ground Truth Data ◽

Fully Convolutional Network ◽

Training Samples ◽

Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

Download Full-text