Share Email Print
cover

Proceedings Paper

A method for scale parameter selection and segments refinement for multi-resolution image segmentation
Author(s): Hui Li; Yunwei Tang; Qingjie Liu; Haifeng Ding; Yu Chen; Linhai Jing
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Image segmentation is the basis of object-based information extraction from remote sensing imagery. Image segmentation based on multiple features, multi-scale, and spatial context is one current research focus. The scale parameters selected in the segmentation severely impact on the average size of segments obtained by multi-scale segmentation method, such as the Fractal Network Evolution Approach (FNEA) employed in the eCognition software. It is important for the FNEA method to select an appropriate scale parameter that causes no neither over- nor undersegmentation. A method for scale parameter selection and segments refinement is proposed in this paper by modifying a method proposed by Johnson. In a test on two images, the segmentation maps obtained using the proposed method contain less under-segmentation and over-segmentation than that generated by the Johnson’s method. It was demonstrated that the proposed method is effective in scale parameter selection and segment refinement for multi-scale segmentation algorithms, such as the FNEA method.

Paper Details

Date Published: 18 November 2014
PDF: 10 pages
Proc. SPIE 9263, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications V, 926307 (18 November 2014); doi: 10.1117/12.2069020
Show Author Affiliations
Hui Li, Institute of Remote Sensing and Digital Earth (China)
Yunwei Tang, Institute of Remote Sensing and Digital Earth (China)
Qingjie Liu, Institute of Remote Sensing and Digital Earth (China)
Haifeng Ding, Institute of Remote Sensing and Digital Earth (China)
Yu Chen, Institute of Remote Sensing and Digital Earth (China)
Linhai Jing, Institute of Remote Sensing and Digital Earth (China)


Published in SPIE Proceedings Vol. 9263:
Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications V
Allen M. Larar; Makoto Suzuki; Jianyu Wang, Editor(s)

© SPIE. Terms of Use
Back to Top