Journal ArticleDOI
Joint Dictionary Learning for Multispectral Change Detection
Reads0
Chats0
TLDR
An improved sparse coding method for change detection that minimizes the reconstruction errors of the changed pixels without the prior assumption of the spectral signature, which can adapt to different data due to the characteristic of joint dictionary learning.Abstract:
Change detection is one of the most important applications of remote sensing technology. It is a challenging task due to the obvious variations in the radiometric value of spectral signature and the limited capability of utilizing spectral information. In this paper, an improved sparse coding method for change detection is proposed. The intuition of the proposed method is that unchanged pixels in different images can be well reconstructed by the joint dictionary, which corresponds to knowledge of unchanged pixels, while changed pixels cannot. First, a query image pair is projected onto the joint dictionary to constitute the knowledge of unchanged pixels. Then reconstruction error is obtained to discriminate between the changed and unchanged pixels in the different images. To select the proper thresholds for determining changed regions, an automatic threshold selection strategy is presented by minimizing the reconstruction errors of the changed pixels. Adequate experiments on multispectral data have been tested, and the experimental results compared with the state-of-the-art methods prove the superiority of the proposed method. Contributions of the proposed method can be summarized as follows: 1) joint dictionary learning is proposed to explore the intrinsic information of different images for change detection. In this case, change detection can be transformed as a sparse representation problem. To the authors’ knowledge, few publications utilize joint learning dictionary in change detection; 2) an automatic threshold selection strategy is presented, which minimizes the reconstruction errors of the changed pixels without the prior assumption of the spectral signature. As a result, the threshold value provided by the proposed method can adapt to different data due to the characteristic of joint dictionary learning; and 3) the proposed method makes no prior assumption of the modeling and the handling of the spectral signature, which can be adapted to different data.read more
Citations
More filters
Journal ArticleDOI
When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs
TL;DR: This paper proposes a simple but effective method to learn discriminative CNNs (D-CNNs) to boost the performance of remote sensing image scene classification and comprehensively evaluates the proposed method on three publicly available benchmark data sets using three off-the-shelf CNN models.
Journal ArticleDOI
Video Salient Object Detection via Fully Convolutional Networks
TL;DR: Wang et al. as discussed by the authors proposed a deep video saliency network consisting of two modules, for capturing the spatial and temporal saliency information, respectively, which can directly produce spatio-temporal saliency inference without time-consuming optical flow computation.
Journal ArticleDOI
ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data
TL;DR: In this article, a novel deep learning architecture, ResUNet-a, is proposed for the task of semantic segmentation of monotemporal very high-resolution aerial images.
Journal ArticleDOI
Remote Sensing Scene Classification by Unsupervised Representation Learning
TL;DR: An unsupervised representation learning method is proposed to investigate deconvolution networks for remote sensing scene classification and outperform most state of the arts results, which demonstrates the effectiveness of this method.
Journal ArticleDOI
Semantic labeling in very high resolution images via a self-cascaded convolutional neural network
TL;DR: A novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet), for confusing manmade objects and fine-structured objects, ScasNet improves the labeling coherence with sequential global- to-local contexts aggregation.
References
More filters
Journal ArticleDOI
A Semisupervised Context-Sensitive Change Detection Technique via Gaussian Process
TL;DR: A semisupervised context-sensitive technique for change detection in high-resolution multitemporal remote sensing images by analyzing the posterior probability of probabilistic Gaussian process classifier within a Markov random field (MRF) model.
Proceedings ArticleDOI
Block-wise constrained sparse graph for face image representation
TL;DR: A novel approach to construct a Sparse Graph with Block-wise constraint for face representation with extensive results on Extended YaleB, ORL and kinship dataset Family101 demonstrate that the method consistently outperforms several state-of-the-art graphs.
Journal ArticleDOI
Lip segmentation under MAP-MRF framework with automatic selection of local observation scale and number of segments.
TL;DR: Experimental results show that the proposed method is robust to the segment number that changes with a speaker's appearance, and can enhance the segmentation accuracy by taking advantage of the local optimal observation scale information.
Proceedings ArticleDOI
Unsupervised change detection in the feature space using kernels
TL;DR: An unsupervised approach to change detection by computing the difference image directly in the feature spaces using a combination of kernels computed on the coregistered and radiometrically matched input images to train a nonlinear partitioning algorithm.