Multitemporal SAR images change detection based on joint sparse representation of pair dictionaries

Li, Wei; Chen, Jiayu; Yang, Pei

doi:10.1109/igarss.2012.6352664

Cited by 9 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the reference maps for bitemporal SAR images are usually not available, and it is challenging to detect the changes from bitemporal SAR images without any guidance. Recently, sparse learning has been employed in many tasks on SAR images' interpretation and understanding, including target classification [54][55][56], image segmentation [57,58], and change detection [19,23]. The spirit of sparse learning is that learning a dictionary exploits the fundamental structures from a given dataset and encodes each sample into a robust feature vector.…”

Section: Change Detection By Sparse Learningmentioning

confidence: 99%

“…Gong et al proposed a fuzzy clustering method with a Markov random field (MRF) [18] to exploit the spatial context in the DI. Li et al proposed an object-based change detection method [19] in which joint sparse representation learning is developed for each pair of regions and the learned features and pairwise dictionaries are obtained by the bitemporal SAR images. The robust ratio and the difference of bitemporal SAR images are obtained from the learned sparse features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

How Can Despeckling and Structural Features Benefit to Change Detection on Bitemporal SAR Images?

et al. 2019

View full text Add to dashboard Cite

Change detection on bitemporal synthetic aperture radar (SAR) images is a key branch of SAR image interpretation. However, it is challenging due to speckle and unavoidable registration errors within bitemporal SAR images. A key issue is whether and how despeckling and structural features can improve accuracy. In this paper, we investigate how despeckling and structural features can benefit change detection for SAR images. Several change detection methods were performed on both input images and the corresponding despeckled images, where despeckling was achieved by different methods. The comparisons demonstrate that despeckling methods that preserve the structures can suppress noise in difference images and can improve the accuracy of change detection. We also developed a sparse model to exploit structural features from the difference images while reducing the influence of misalignment between bitemporal SAR images. The comparisons were performed on five datasets of bitemporal SAR images, and the experimental results show that our proposed sparse model outperforms other traditional methods, demonstrating the advantages of change detection.

show abstract

Section: Change Detection By Sparse Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

How Can Despeckling and Structural Features Benefit to Change Detection on Bitemporal SAR Images?

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Zhang et al [4] proposed a graph-cut method to extract the change regions on the log-ratio difference image through the statistical distributions on the changed and unchanged regions. Li et al [5] proposed a joint sparse learning model to obtain robust features from difference images.…”

Section: Introductionmentioning

confidence: 99%

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

et al. 2020

View full text Add to dashboard Cite

In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP) network to exploit the changed information from the noisy difference image. Being different from the traditional convolutional network with only mono-scale pooling kernels, in the proposed method, multi-scale pooling kernels are equipped in a convolutional network to exploit the spatial context information on changed regions from the difference image. Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset. We compare the proposed method with other state-of-arts and the comparisons are performed on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that our proposed method obtain comparable results with S-PCA-Net on YR-A and YR-B dataset and outperforms other state-of-art methods, especially on the Sendai-A and Sendai-B datasets with more complex scenes. More important, MSSP-Net is more efficient than S-PCA-Net and convolutional neural networks (CNN) with less executing time in both training and testing phases.

show abstract

“…There have been a number of change detection studies using thresholding [5,6,7,8], extreme learning machine [9,10], Markov random fields [11,12] and combinations of feature learning and clustering algorithms [13,14,15,16,17,18,19]. Optical flow fields can be used to distinguish between objects that have actually moved between frames and those that are in the same location but are slightly misregistered.…”

Section: Introductionmentioning

confidence: 99%

Improving the Accuracy of Two-Color Multiview (2CMV) Advanced Geospatial Information (AGI) Products Using Unsupervised Feature Learning and Optical Flow

Kanberoglu

2019

Sensors

View full text Add to dashboard Cite

In two-color multiview (2CMV) advanced geospatial information (AGI) products, temporal changes in synthetic aperture radar (SAR) images acquired at different times are detected, colorized, and overlaid on an initial image such that new features are represented in cyan, and features that have disappeared are represented in red. Accurate detection of temporal changes in 2CMV AGI products can be challenging because of ’speckle noise’ susceptibility and false positives that result from small orientation differences between objects imaged at different times. Accordingly, 2CMV products are often dominated by colored pixels when changes are detected via simple pixel-wise cross-correlation. The state-of-the-art in SAR image processing demonstrates that generating efficient 2CMV products, while accounting for the aforementioned problem cases, has not been well addressed. We propose a methodology to address the aforementioned two problem cases. Before detecting temporal changes, speckle and smoothing filters mitigate the effects of speckle noise. To detect temporal changes, we propose using unsupervised feature learning algorithms in conjunction with optical flow algorithms that track the motion of objects across time in small regions of interest. The proposed framework for distinguishing between actual motion and misregistration can lead to more accurate and meaningful change detection and improve object extraction from an SAR AGI product.

show abstract

Multitemporal SAR images change detection based on joint sparse representation of pair dictionaries

Cited by 9 publications

References 6 publications

How Can Despeckling and Structural Features Benefit to Change Detection on Bitemporal SAR Images?

How Can Despeckling and Structural Features Benefit to Change Detection on Bitemporal SAR Images?

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

Improving the Accuracy of Two-Color Multiview (2CMV) Advanced Geospatial Information (AGI) Products Using Unsupervised Feature Learning and Optical Flow

Contact Info

Product

Resources

About