14 December 2015 Combining low level features and visual attributes for VHR remote sensing image classification
Author Affiliations +
Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 98150C (2015) https://doi.org/10.1117/12.2205566
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
Semantic classification of very high resolution (VHR) remote sensing images is of great importance for land use or land cover investigation. A large number of approaches exploiting different kinds of low level feature have been proposed in the literature. Engineers are often frustrated by their conclusions and a systematic assessment of various low level features for VHR remote sensing image classification is needed. In this work, we firstly perform an extensive evaluation of eight features including HOG, dense SIFT, SSIM, GIST, Geo color, LBP, Texton and Tiny images for classification of three public available datasets. Secondly, we propose to transfer ground level scene attributes to remote sensing images. Thirdly, we combine both low-level features and mid-level visual attributes to further improve the classification performance. Experimental results demonstrate that i) Dene SIFT and HOG features are more robust than other features for VHR scene image description. ii) Visual attribute competes with a combination of low level features. iii) Multiple feature combination achieves the best performance under different settings.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fumin Zhao, Hao Sun, Shuai Liu, Shilin Zhou, "Combining low level features and visual attributes for VHR remote sensing image classification", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 98150C (14 December 2015); doi: 10.1117/12.2205566; https://doi.org/10.1117/12.2205566
PROCEEDINGS
8 PAGES


SHARE
Back to Top