Perceptual Grouping of 3-D Features in Aerial Image Using Decision Tree Classifier

We address a new perceptual grouping algorithmfor aerial images, which employs a decision tree classifier and hierarchical multilevel grouping strategy an a bottom-up fashion. In our approach, grouping is performed perceptually on 9-Dfeatures extracted from 2D images, in which the Gestalt principles including collinearity, parallelism and L-typed convergence are encoded by the decision tree learning technique. The decision tree is constructed using training samples obtained from the given 9-D reference model. Then, each pair of the extracted 9-D line features of an input image is classified into one of the learned Gestalt primitives. On the other hand, an multilevel grouping procedure, grouping of collated features are performed from lower to higher level, yielding the structured target model. In order to evaluate the proposed algorithm, experiments are carried out on RADIUS model board images. The results show that grouping is performed effectivelyto extract man-made structures an ae...

• Type: Conference
• Year: 1999
• Where: ICIP
• Authors: In Kyu Park, Kyoung Mu Lee, Sang Uk Lee
• Keywords: Decision Tree Classifier, Hierarchical Multilevel Grouping, ICIP 1999, Image Processing, Multilevel Grouping Procedure