Abstract
Change detection (CD) has found a wide range of applications in many fields. In this article, we propose a novel nonlocal low-rank (NLR) based method for multitemporal synthetic aperture radar image CD. This method jointly exploits the powerful NLR-based despeckling and the effective cascade clustering. First, the NLR model is used to generate the difference image (DI), which consists of a patch grouping process and a low-rank minimizing process. Especially, the NLR minimization model contains a data fidelity term, which is based on the statistical distribution of speckle noise, and a regularization term, which uses the weighted nuclear norm. Then, the alternating direction methods of multipliers is introduced to solve this minimization problem. Second, after DI is generated, the principal component analysis is employed to extract the feature and a two-level clustering method is used to generate the final change map, which separates the intermediate class by using the neighbor information with Gaussian weighted distance. Experiment results demonstrate the effectiveness of the proposed method by comparing with some state-of-the-art methods.
Highlights
C HANGE detection (CD) is a process of identifying changes of an object or phenomenon that have occurred in the same geographical area at different times
We apply six methods in comparison: principal component analysis (PCA) with k-means clustering (PCA-KM) [25], modified Markov random field with fuzzy c-means (FCM) (MRFFCM) [30], neighborhood-based ratio and extreme learning machine method (NR-ELM) [37], Gabor feature with two-level clustering (GaborTLC) [26], PCANet [38], and convolutional-wavelet neural network (CWNN) [39]
We present a new synthetic aperture radar (SAR) image CD method named as nonlocal low-rank (NLR)-PCATLC for short
Summary
C HANGE detection (CD) is a process of identifying changes of an object or phenomenon that have occurred in the same geographical area at different times. We introduce the NLR model to generate the DI, which can effectively utilize the characteristics of speckle noise, aiming to reduce the noise and provide better DI for CD. To obtain two independent denoising images, or applying NLR to the log-ratio DI directly, the proposed NLR model jointly uses the statistical distribution characteristics of the multitemporal images, which can avoid the loss of information in the subtraction process and lead to a better quantity of DI. We employ the PCA to extract the feature vectors and modify the two-level clustering scheme proposed in [26] to identify the changed and unchanged classes by implementing FCM with the nearest neighbor rule with Gaussian weighted distance. We modify the data fidelity term in the traditional NLR-based methods according to the noise characteristics of two original observed SAR images.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
