The selection of optimum scale in coast area classification of high-resolution remote sensing imagery

Jianyu Chen; Delu Pan; Zhihua Mao; Xiaoyu Zhang

doi:10.1117/12.627375

31 October 2005 The selection of optimum scale in coast area classification of high-resolution remote sensing imagery

Jianyu Chen, Delu Pan, Zhihua Mao, Xiaoyu Zhang

Proceedings Volume 5983, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology V; 59831Q (2005) https://doi.org/10.1117/12.627375
Event: SPIE Remote Sensing, 2005, Bruges, Belgium

Abstract

Spatial conception exists in remote sensing imagery as well as spectral information. It acts as more importance role in dominant landscape objects detection in high-resolution remote sensing imagery. Multiscale analysis is a new approach to meet the requirement of how to use spatial information in classification. Compared with traditional pixel based classification methods, multiscale analysis is composed of two fundamental components: the generation of a multiscale representation and information extraction. The paper focuses on one segmentation techniques- Fractal Net Evolution Approach (FNEA) and its usage in improvement in coastal remotely sensed image classification. FNEA is considered as one of effectual region-based segmentation and its threshold is a combination of size and homogeneity. We discuss two different segmental strategies which are speed-first and scale-first, and their impacts on image-objects. We can get the optimal segmental scale by analyzing the relationship between average size of each image-object and the different scale.

Citation Download Citation

Jianyu Chen, Delu Pan, Zhihua Mao, and Xiaoyu Zhang "The selection of optimum scale in coast area classification of high-resolution remote sensing imagery", Proc. SPIE 5983, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology V, 59831Q (31 October 2005); https://doi.org/10.1117/12.627375

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