Depthwise Separable Convolutional Autoencoders for Hyperspectral Image Change Detection
- 30 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Abstract
Hyperspectral image change detection (HSI-CD) has recently become a research hotspot. Current methods rely heavily on a huge amount of training samples to perform the change detection tasks. While acquiring data from the same region of bi-temporal HSIs is extraordinarily time-consuming and laborious. Therefore, this letter proposes an unsupervised method based on three dimensional (3D) depthwise separable convolutional autoencoders (DSConvAE). First, the dual-branch symmetrical 3D DSConvAE is pre-trained with limited samples to obtain the optimal weights, which facilitates extracting discriminative spatial and spectral features subsequently. Second, we adopt the temporal-specific feature concatenation strategy to acquire comprehensive characteristics from bi-temporal HSIs. Third, the general autoencoders are employed at the end of the model to further explore the high-level and abstract feature vectors. Finally, we compare the mean square loss calculated from the spatial-spectral branches and apply threshold judgement to generate the ultimate detection maps. Experimental results on three public HSI datasets demonstrate that the proposed framework outperforms other comparative methods by significant improvements.Keywords
Funding Information
- National Natural Science Foundation of China (62071168)
- National Natural Science Foundation of China (42241109)
- National Natural Science Foundation of China (42271350)
- Natural Science Foundation of Jiangsu (BK20211201)
- China Postdoctoral Science Foundation (2021M690885)
This publication has 14 references indexed in Scilit:
- Change Detection in Hyperdimensional Images Using Untrained ModelsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- A Multiscale Dual-Branch Feature Fusion and Attention Network for Hyperspectral Images ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- A Spectral–Spatial Change Detection Method Based on Simplified 3-D Convolutional Autoencoder for Multitemporal Hyperspectral ImagesIEEE Geoscience and Remote Sensing Letters, 2021
- Three-Order Tucker Decomposition and Reconstruction Detector for Unsupervised Hyperspectral Change DetectionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- Hyperspectral Anomaly Change Detection Based on AutoencoderIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2018
- An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral UnmixingIEEE Transactions on Image Processing, 2018
- A k-Nearest Neighbor approach to improve change detection from remote sensing: Application to optical aerial images2015
- Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classificationInternational Journal of Remote Sensing, 2014
- Change Vector Analysis in Posterior Probability Space: A New Method for Land Cover Change DetectionIEEE Geoscience and Remote Sensing Letters, 2010