Image and Signal Processing Methods

Integrated approach using data mining-based decision tree and object-based image analysis for high-resolution urban mapping of WorldView-2 satellite sensor data

[+] Author Affiliations
Alireza Hamedianfar

Universiti Putra Malaysia (UPM), Department of Civil Engineering, Faculty of Engineering, 43400 Serdang, Selangor, Malaysia

Islamic Azad University, Department of Surveying Engineering, Estahban Branch, Estahban, Fars, Iran

Islamic Azad University, Young Researchers and Elite Club, Estahban Branch, Estahban, Fars, Iran

Helmi Zulhaidi Mohd Shafri

Universiti Putra Malaysia (UPM), Department of Civil Engineering, Faculty of Engineering, 43400 Serdang, Selangor, Malaysia

Universiti Putra Malaysia (UPM), Geospatial Information Science Research Centre (GISRC), Faculty of Engineering, 43400 Serdang, Selangor, Malaysia

J. Appl. Remote Sens. 10(2), 025001 (Apr 07, 2016). doi:10.1117/1.JRS.10.025001
History: Received December 8, 2015; Accepted March 11, 2016
Text Size: A A A

Abstract.  This paper integrates decision tree–based data mining (DM) and object-based image analysis (OBIA) to provide a transferable model for the detailed characterization of urban land-cover classes using WorldView-2 (WV-2) satellite images. Many articles have been published on OBIA in recent years based on DM for different applications. However, less attention has been paid to the generation of a transferable model for characterizing detailed urban land cover features. Three subsets of WV-2 images were used in this paper to generate transferable OBIA rule-sets. Many features were explored by using a DM algorithm, which created the classification rules as a decision tree (DT) structure from the first study area. The developed DT algorithm was applied to object-based classifications in the first study area. After this process, we validated the capability and transferability of the classification rules into second and third subsets. Detailed ground truth samples were collected to assess the classification results. The first, second, and third study areas achieved 88%, 85%, and 85% overall accuracies, respectively. Results from the investigation indicate that DM was an efficient method to provide the optimal and transferable classification rules for OBIA, which accelerates the rule-sets creation stage in the OBIA classification domain.

Figures in this Article
© 2016 Society of Photo-Optical Instrumentation Engineers

Citation

Alireza Hamedianfar and Helmi Zulhaidi Mohd Shafri
"Integrated approach using data mining-based decision tree and object-based image analysis for high-resolution urban mapping of WorldView-2 satellite sensor data", J. Appl. Remote Sens. 10(2), 025001 (Apr 07, 2016). ; http://dx.doi.org/10.1117/1.JRS.10.025001


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.