A NEW FRAMEWORK FOR OBJECT-BASED IMAGE ANALYSIS BASED ON SEGMENTATION SCALE SPACE AND RANDOM FOREST CLASSIFIER
In this paper a new object-based framework is developed for automate scale selection in image segmentation. The quality of image objects have an important impact on further analyses. Due to the strong dependency of segmentation results to the scale parameter, choosing the best value for this paramet...
Main Authors: | A. Hadavand, M. Saadatseresht, S. Homayouni |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2015-12-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-1-W5/263/2015/isprsarchives-XL-1-W5-263-2015.pdf |
Similar Items
-
Using pixel-based and object-based methods to classify urban hyperspectral features
by: Ahmad Hadavand, et al.
Published: (2016-09-01) -
A NEW OBJECT-BASED FRAMEWORK TO DETECT SHODOWS IN HIGH-RESOLUTION SATELLITE IMAGERY OVER URBAN AREAS
by: N. Tatar, et al.
Published: (2015-12-01) -
A random forest approach to segmenting and classifying gestures
by: Joshi, Ajjen Das
Published: (2016) -
Object-based classification of hyperspectral data using Random Forest algorithm
by: Saeid Amini, et al.
Published: (2018-04-01) -
Image segmentation using IHS space and object-based analysis
by: Carlos Frederico de Sá Volotão
Published: (2013)