Using Models to Detect Man-Made Objects

A.L. Reno and D.M. Booth

Objects in aerial images are extracted by using a new method based on a two-dimensional viewer-centred model. Using this approach has advantages over existing methods because the models are easily created and it is efficient. Experiments illustrate the extraction and tracking of man-made objects in reconnaissance images. In later work we intend to extend the method to allow selection between different object types, or between different views of the same object.

Proceedings of the Second IEEE Workshop on Visual Surveillance
Copyright (c) 1998 Institute of Electrical and Electronics Engineers, Inc. All rights reserved.

---