A competitive pixel-object approach for land cover classification
- 20 November 2005
- journal article
- research article
- Published by Informa UK Limited in International Journal of Remote Sensing
- Vol. 26 (22), 4981-4997
- https://doi.org/10.1080/01431160500213912
Abstract
This paper describes a novel remote sensing land cover classification approach named competitive pixel-object classification, based on Bayesian neural networks and image segmentation. This approach makes use of both pixel spectral features and object features resulting from image segmentation through a competitive mechanism to resolve the problem of spectral confusion caused by reflectance similarity of some land cover types that traditional pixel-based classification cannot resolve. The competitive pixel-object method reduces the unreliability of object feature information produced by over- or under-segmentation of the image through a competitive mechanism. The experiment shows that the competitive pixel-object approach produces higher classification accuracy than either pixel-based classification or object-oriented classification.Keywords
This publication has 2 references indexed in Scilit:
- Artificial neural networks for land-cover classification and mappingInternational Journal of Geographical Information Science, 1993
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989