Christopher O. Jaynes

TL;DR: A new method for extracting planar polygonal rooftops in monocular aerial imagery with top-down feature verification used so that features, and links between the features, are verified with local information in the image and weighed in a graph.

TL;DR: The Ascender system acquires, extends, and refines 3D geometric site models from calibrated aerial imagery to add previously unseen buildings and to improve the geometric accuracy of the existing 3D building models.

TL;DR: A system has been developed to acquire, extend and refine 3D geometric site models from aerial imagery that hypothesizes potential building roofs in an image, automatically locates supporting geometric evidence in other images, and determines the precise shape and position of the new buildings via multiimage triangulation.

TL;DR: It is suggested that a promising direction for achieving automatic robust reconstruction of both natural and cultural features under a variety of conditions and variable sensor data lies in the construction of systems containing context sensitive control strategies for synchronizing the application of image understanding modules (algorithms) whose individual domain of expertise is limited.

TL;DR: Under theAPGD program, this work is constructing a knowledge-based site reconstruction system that automatically selects the correct algorithm according to thecur-rent context, appliesliesittoafo cusedsubsetofthedata, and constrains the interpretation of the result through the explicit use of knowledge.