Change detection of urban buildings considering geometric features

Mengyi Wang; Li Pan

doi:10.1117/12.2063859

14 May 2014 Change detection of urban buildings considering geometric features

Mengyi Wang, Li Pan

Proceedings Volume 9158, Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China; 91580S (2014) https://doi.org/10.1117/12.2063859
Event: Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China, 2012, Wuhan, China

Abstract

In recent years, high resolution remote sensing imagery has been widely utilized in change detection, especially in urban residential areas. The quality of image features has great influence on detection results, and each kind of feature has its own unique advantage in the process of change detection. It is hard to obtain satisfying results if we only use one kind of feature. This paper extracts image gray scale feature, edge feature and geometric feature for change detection. Firstly, according to the image gray scale feature of the house, K-means classification and binarization are utilized to extract house areas roughly. After that, Hough transformation is used to detect the straight lines and obtain the difference map. To improve the accuracy, minor changes, such as spot-like and linear changes are eliminated by using the geometric shape and size of the objects. At last, we conducted accuracy assessment for the final result. Experiments show that geometric feature plays an important role in extracting target objects and improving the final result, and has obvious advantages and feasibility.

Citation Download Citation

Mengyi Wang and Li Pan "Change detection of urban buildings considering geometric features", Proc. SPIE 9158, Remote Sensing of the Environment: 18th National Symposium on Remote Sensing of China, 91580S (14 May 2014); https://doi.org/10.1117/12.2063859

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