Coupling high-resolution satellite imagery with ALS-based canopy height model and digital elevation model in object-based boreal forest habitat type classification |
| |
| Institution: | 1. R&D Division, Marua Suisan Co., Ltd., 4472 Iwagi, Kamijima, Ehime 794-2410, Japan;2. The United Graduate School of Agricultural Sciences, Ehime University, 3-5-7 Tarumi, Matsuyama, Ehime 790-5866, Japan;3. Nippon Total Science, Inc., 456-2 Minomi cho, Fukuyama, Hiroshima 720-0832, Japan;4. South Ehime Fisheries Research Center, Tarumi Branch, Ehime University, 3-5-7 Tarumi, Matsuyama, Ehime 790-8566, Japan;1. Canada Centre for Remote Sensing, Natural Resources Canada, 560 Rochester Street, Ottawa, Ontario K1A 0E4, Canada;2. Institut National de la Recherche Agronomique, Université d''Avignon et des Pays du Vaucluse (INRA-UAPV), 228 Route de l''Aérodrome, 84914 Avignon, France;3. Agriculture and Agri-Food Canada, 960 Carling Ave, Ottawa, Ontario K1A 0C6, Canada;4. CARTEL, Université de Sherbrooke, 2500 boul. de l''Université, Sherbrooke, Québec J1K 2R1, Canada |
| |
| Abstract: | We developed a classification workflow for boreal forest habitat type mapping. In object-based image analysis framework, Fractal Net Evolution Approach segmentation was combined with random forest classification. High-resolution WorldView-2 imagery was coupled with ALS based canopy height model and digital terrain model. We calculated several features (e.g. spectral, textural and topographic) per image object from the used datasets. We tested different feature set alternatives; a classification accuracy of 78.0% was obtained when all features were used. The highest classification accuracy (79.1%) was obtained when the amount of features was reduced from the initial 328 to the 100 most important using Boruta feature selection algorithm and when ancillary soil and land-use GIS-datasets were used. Although Boruta could rank the importance of features, it could not separate unimportant features from the important ones. Classification accuracy was bit lower (78.7%) when the classification was performed separately on two areas: the areas above and below 1 m vertical distance from the nearest stream. The data split, however, improved the classification accuracy of mire habitat types and streamside habitats, probably because their proportion in the below 1 m data was higher than in the other datasets. It was found that several types of data are needed to get the highest classification accuracy whereas omitting some feature groups reduced the classification accuracy. A major habitat type in the study area was mesic forests in different successional stages. It was found that the inner heterogeneity of different mesic forest age groups was large and other habitat types were often inside this heterogeneity. |
| |
| Keywords: | Habitat type mapping Multispectral imagery ALS Object-based image analysis Random forest classifier Feature selection |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
