Research Papers

Mapping paddy rice agriculture in a highly fragmented area using a geographic information system object-based post classification process

[+] Author Affiliations
Yi-Shiang Shiu

National Taiwan University, Department of Geography, No. 1, Sec. 4, Roosevelt Road, Taipei 10617 Taiwan

Meng-Lung Lin

Aletheia University, Department of Tourism, No. 32, Chen-Li St., Danshui District, New Taipei City 25103 Taiwan

Chao-Hsiung Huang

National Taiwan University, Spatial Information Research Center, No. 1, Sec. 4, Roosevelt Road, Taipei 10617 Taiwan

Tzu-How Chu

National Taiwan University, Department of Geography, No. 1, Sec. 4, Roosevelt Road, Taipei 10617 Taiwan

National Taiwan University, Spatial Information Research Center, No. 1, Sec. 4, Roosevelt Road, Taipei 10617 Taiwan

J. Appl. Remote Sens. 6(1), 063526 (May 21, 2012). doi:10.1117/1.JRS.6.063526
History: Received April 11, 2011; Revised February 10, 2012; Accepted March 5, 2012
Text Size: A A A

Abstract.  Most paddy rice fields in Asia are comprised of small parcels of land, and the weather conditions during the growing season are usually cloudy. This study develops a geographic information system (GIS) object-based post classification (GOBPC) that combines low-cost remotely sensed and GIS data to precisely map paddy rice fields in the intensively cultivated but fragmented growing areas which are characteristic of Asia. FORMOSAT-2 multispectral images have an 8-meter resolution and a one-day recurrence, making them ideal for mapping such areas. Multitemporal images are examined to distinguish the different growth characteristics between paddy rice and other types of ground cover. The pixel-based hybrid classification technique is used with both the unsupervised and supervised approach to distinguish the paddy rice fields from their surroundings. In addition to the pixel-based approach, we also use GOBPC to deal with over-fragmented parcels of land and to reduce the incidence of misclassification caused by speckle or mixed pixels (mixels) in the images. A comparison is made with the pixel-based technique. The Kappa index of agreement obtained with the GOBPC reaches 0.095 to 0.291, and there is a statistically significant improvement in the user and producer accuracy for all the classes (z>1.96) with McNemar’s test in the four study areas. The proposed GOBPC approach is shown to be useful in highly fragmented rice growing areas and may have the potential for other agricultural applications.

Figures in this Article
© 2012 Society of Photo-Optical Instrumentation Engineers

Citation

Yi-Shiang Shiu ; Meng-Lung Lin ; Chao-Hsiung Huang and Tzu-How Chu
"Mapping paddy rice agriculture in a highly fragmented area using a geographic information system object-based post classification process", J. Appl. Remote Sens. 6(1), 063526 (May 21, 2012). ; http://dx.doi.org/10.1117/1.JRS.6.063526


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

PubMed Articles
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.