Spatial discrimination based on the ground truth with mixed categories

Ryuei Nishii, Shojiro Tanaka

Research output: Contribution to conferencePaper

Abstract

We examined discriminant analysis of land-cover categories based on multivariate Gaussian fields. A parameter-estimation method by the ground-truth data consisting of pure and mixed cells with known category-proportions was discussed, and test data were discriminated by a penalized likelihood. With actual Landsat data, our procedure showed an excellent performance with respect to the linear discriminant function and Switzer's method. Further, the use of mixels in the ground-truth data improved the discrimination results significantly.

Original languageEnglish
Pages159-161
Number of pages3
Publication statusPublished - Dec 1 2000
Event2000 Interantional Geoscience and Remote Sensing Symposium (IGARSS 2000) - Honolulu, HI, USA
Duration: Jul 24 2000Jul 28 2000

Other

Other2000 Interantional Geoscience and Remote Sensing Symposium (IGARSS 2000)
CityHonolulu, HI, USA
Period7/24/007/28/00

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Fingerprint Dive into the research topics of 'Spatial discrimination based on the ground truth with mixed categories'. Together they form a unique fingerprint.

  • Cite this

    Nishii, R., & Tanaka, S. (2000). Spatial discrimination based on the ground truth with mixed categories. 159-161. Paper presented at 2000 Interantional Geoscience and Remote Sensing Symposium (IGARSS 2000), Honolulu, HI, USA, .