Remote sensing image segmentation using local sparse structure constrained latent low rank representation

Shu Tian; Ye Zhang; Yimin Yan; Nan Su; Junping Zhang

doi:10.1117/12.2237726

19 September 2016 Remote sensing image segmentation using local sparse structure constrained latent low rank representation

Shu Tian, Ye Zhang, Yimin Yan, Nan Su, Junping Zhang

Author Affiliations +

Proceedings Volume 9976, Imaging Spectrometry XXI; 99760T (2016) https://doi.org/10.1117/12.2237726
Event: SPIE Optical Engineering + Applications, 2016, San Diego, California, United States

Abstract

Latent low-rank representation (LatLRR) has been attached considerable attention in the field of remote sensing image segmentation, due to its effectiveness in exploring the multiple subspace structures of data. However, the increasingly heterogeneous texture information in the high spatial resolution remote sensing images, leads to more severe interference of pixels in local neighborhood, and the LatLRR fails to capture the local complex structure information. Therefore, we present a local sparse structure constrainted latent low-rank representation (LSSLatLRR) segmentation method, which explicitly imposes the local sparse structure constraint on LatLRR to capture the intrinsic local structure in manifold structure feature subspaces. The whole segmentation framework can be viewed as two stages in cascade. In the first stage, we use the local histogram transform to extract the texture local histogram features (LHOG) at each pixel, which can efficiently capture the complex and micro-texture pattern. In the second stage, a local sparse structure (LSS) formulation is established on LHOG, which aims to preserve the local intrinsic structure and enhance the relationship between pixels having similar local characteristics. Meanwhile, by integrating the LSS and the LatLRR, we can efficiently capture the local sparse and low-rank structure in the mixture of feature subspace, and we adopt the subspace segmentation method to improve the segmentation accuracy. Experimental results on the remote sensing images with different spatial resolution show that, compared with three state-of-the-art image segmentation methods, the proposed method achieves more accurate segmentation results.

Conference Presentation

Citation Download Citation

Shu Tian, Ye Zhang, Yimin Yan, Nan Su, and Junping Zhang "Remote sensing image segmentation using local sparse structure constrained latent low rank representation", Proc. SPIE 9976, Imaging Spectrometry XXI, 99760T (19 September 2016); https://doi.org/10.1117/12.2237726

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available