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 language | English |
|---|---|
| Pages | 159-161 |
| Number of pages | 3 |
| Publication status | Published - 2000 |
| Externally published | Yes |
| Event | 2000 Interantional Geoscience and Remote Sensing Symposium (IGARSS 2000) - Honolulu, HI, USA Duration: Jul 24 2000 → Jul 28 2000 |
Other
| Other | 2000 Interantional Geoscience and Remote Sensing Symposium (IGARSS 2000) |
|---|---|
| City | Honolulu, HI, USA |
| Period | 7/24/00 → 7/28/00 |
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Earth and Planetary Sciences(all)