We propose an incremental learning scheme for learning a class hierarchy for objects typically occurring multiple in images. Given one example of an object that appears several times in the image, e.g. is part of a repetitive structure, we propose a method for identifying prototypes using an unsupervised clustering procedure. These prototypes are used for building a hierarchical appearance base...

...................................................................................................................... iii ACKNOWLEDGEMENTS ............................................................................................... iv DEDICATION .................................................................................................................... v INTRODUCTION...................

traditional persian architects used to employ the facade ornaments to illustrate cultural values and heritage. moreover, their approach for the adaptation of decorations to structural constructional requirements of buildings, called tectonics, could be considered as a cultural-artistic character itself. although these features were omitted when modernism and its independent facade principle pre...

The paper addresses the problem of feature selection during classification of image regions within the context of interpreting images showing highly structured objects such as buildings. We present a feature selection scheme that is connected with the classification framework Adaboost, cf. (Schapire and Singer, 1999). We constricted our weak learners on threshold classification on a single feat...

As part of an architectural modeling project, this paper investigates the problem of understanding and manipulating images of buildings. Our primary motivation is to automatically detect and seamlessly remove unwanted foreground elements from urban scenes. Without explicit handling, these objects will appear pasted as artifacts on the model. Recovering the building facade in a video sequence is...

In existing research about 3D city map, geometrical information of buildings’ facade is derived from video image. In order to improve quality of the geometrical information, range image is used in our research. At first range image of existing buildings is acquired using laser scanners mounted on data acquisition vehicle which runs in the street. After removing obstacles from original range ima...

We propose a novel three-layered approach for semantic segmentation of building facades. In the first layer, starting from an oversegmentation of a facade, we employ the recently introduced machine learning technique Recursive Neural Networks (RNN) to obtain a probabilistic interpretation of each segment. In the second layer, initial labeling is augmented with the information coming from specia...