Paper
14 November 2007 Research on the classification algorithm of aerial image based on the weighted mean-shift
Qiang Guo, Hanyu Hong, Yichao Chen
Author Affiliations +
Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67903K (2007) https://doi.org/10.1117/12.751667
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Abstract
The main problem of aerial image classification is how to classify with robust and high precision at present. Therefore, a new approach of the aerial image classification based on the weighted Mean Shift is proposed in this paper. The kernel density function's local maximum is found by the weighted Mean Shift filter of pixels in feature space using resamplying strategy, and the neighborhood data points are shifted to the local maximum of the region, in which the same course is implemented repeatedly to all the pixels in image. Then the classification image is got by fusing each cluster region.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qiang Guo, Hanyu Hong, and Yichao Chen "Research on the classification algorithm of aerial image based on the weighted mean-shift", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67903K (14 November 2007); https://doi.org/10.1117/12.751667
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image classification

RGB color model

Edge detection

Image filtering

Image processing

Statistical analysis

Detection and tracking algorithms

RELATED CONTENT

Precise horizontal location of license plate image
Proceedings of SPIE (October 30 2009)
Using SPOT images for urban area classification
Proceedings of SPIE (December 04 1998)

Back to Top