27 June 2017 Urban new construction land parcel detection with normalized difference vegetation index and PanTex information
Author Affiliations +
Abstract
An urban new construction land parcel detection method based on normalized difference vegetation index (NDVI) and built-up area presence index is proposed for high-resolution remote sensing images. The method consists of three main steps: construction land detection using NDVI and PanTex, false change removal, and new construction land parcel extraction. More specifically, a change proportion index is raised to convert the pixel-based change detection map to parcels in combination with a segmentation process. From experimental results validated using two cases of high-resolution optical satellite images, the proposed method is demonstrated to be efficient and achieves a per-object overall accuracy rate beyond 95%, significantly superior to the traditional postclassification change detection method. Furthermore, the proposed method avoids errors resulting from classification in the method of postclassification comparison.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Qingqing Huang, Qingqing Huang, Chengyi Wang, Chengyi Wang, Yu Meng, Yu Meng, Anzhi Yue, Anzhi Yue, Jingbo Chen, Jingbo Chen, Yuan Yuan, Yuan Yuan, } "Urban new construction land parcel detection with normalized difference vegetation index and PanTex information," Journal of Applied Remote Sensing 11(2), 026039 (27 June 2017). https://doi.org/10.1117/1.JRS.11.026039 . Submission: Received: 31 January 2017; Accepted: 1 June 2017
Received: 31 January 2017; Accepted: 1 June 2017; Published: 27 June 2017
JOURNAL ARTICLE
12 PAGES


SHARE
Back to Top