A competitive pixel‐object approach for land cover classification
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.
Document Type: Research Article
Affiliations: 1: Computer Science and Engineering Department, The University of Connecticut, 371 Fairfield Road, Unit 1155, Storrs, CT 06269‐1155 2: Center for Land Use Education and Research, Department of Natural Resources Management and Engineering, The University of Connecticut, U‐4087, 1376 Storrs Road, Storrs, CT 06269‐4087
Publication date: November 20, 2005