Image change detection based on an improved rough fuzzy c-means clustering algorithm
- PDF / 626,497 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 52 Downloads / 239 Views
ORIGINAL ARTICLE
Image change detection based on an improved rough fuzzy c-means clustering algorithm Wenping Ma • Licheng Jiao • Maoguo Gong • Congling Li
Received: 28 January 2013 / Accepted: 8 May 2013 Ó Springer-Verlag Berlin Heidelberg 2013
Abstract An unsupervised change detection method based on an improved rough fuzzy c-means clustering method (SRFPCM) for synthetic aperture radar and optical remote sensing images is proposed. SRFPCM incorporates the local spatial information and gray level information in a novel fuzzy way, aiming at guaranteeing noise insensitiveness and image detail preservation. Inspired by the idea of a robust fuzzy local information c-means clustering algorithm, this new algorithm can overcome the disadvantages of rough fuzzy c-means clustering algorithm and enhance the clustering performance at the same time. SRFPCM is employed to cluster the difference image into two clusters (changed and unchanged regions) and get the change map. Experimental results confirm the effectiveness of the proposed algorithm. Keywords Change detection Rough set Fuzzy cluster algorithm Remote sensing image
1 Introduction Image change detection is an important application of remote sensing image, which is a process aimed at identifying the earth’s surface changes by analyzing images acquired on the same geographical area at different time [1, 2]. In the last decades, it has attracted widespread interests due to a large number of applications in diverse fields such as remote sensing [3–11], medical diagnosis [12, 13], and
W. Ma (&) L. Jiao M. Gong C. Li Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, No. 2 South Taibai Road, Shaanxi 710071 Xi’an, China e-mail: [email protected]
video surveillance [14, 15].With the development of remote sensing technology, change detection in remote sensing image becomes more and more important. Optical remote sensing has been used for addressing change detection applications for many years [16]. Unlike optical sensors, synthetic aperture radar (SAR) has been less attention than optical sensors in the context of change detection. This is due to the fact that SAR images processing is intrinsically complex, with the presence of the speckle noise, it is difficult to render their analysis for SAR images. Even so, the use of SAR sensors in change detection is potentially attractive from the operational viewpoint. These active SAR sensors have the advantage that they are able to acquire data in all weather conditions and not affected by the presence of cloud cover or different sunlight conditions. As mentioned in the literatures, unsupervised change detection in SAR and optical remote sensing images can be divided into three steps: (1) image preprocessing, (2) producing difference image (DI) between the multi-temporal images, and (3) analysis of the DI. The tasks of the first step mainly include co-registration, geometric corrections, and noise reduction. In the second step, two co-registered images are co
Data Loading...
