A method for scale parameter selection and segments refinement for multi-resolution image segmentation

Hui Li; Yunwei Tang; Qingjie Liu; Haifeng Ding; Yu Chen; Linhai Jing

doi:10.1117/12.2069020

18 November 2014 A method for scale parameter selection and segments refinement for multi-resolution image segmentation

Hui Li, Yunwei Tang, Qingjie Liu, Haifeng Ding, Yu Chen, Linhai Jing

Proceedings Volume 9263, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications V; 926307 (2014) https://doi.org/10.1117/12.2069020
Event: SPIE Asia-Pacific Remote Sensing, 2014, Beijing, China

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.

Citation Download Citation

Hui Li, Yunwei Tang, Qingjie Liu, Haifeng Ding, Yu Chen, and Linhai Jing "A method for scale parameter selection and segments refinement for multi-resolution image segmentation", Proc. SPIE 9263, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications V, 926307 (18 November 2014); https://doi.org/10.1117/12.2069020

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