Publications (6)0 Total impact
-
[show abstract]
[hide abstract]
ABSTRACT: Extracting cartographic objects from images is a difficult task because aerial images are inherently noisy, complex, and ambiguous.
Using models of the objects of interest to guide the search has proved to be an effective approach that yields good results.
In such an approach, the problem becomes one of fitting the models to the image data, which we phrase as an optimization problem.
The appropriate optimization technique to use depends on the exact nature of the model. In this paper, we review and contrast
some of the approaches we have developed for extracting cartographic objects and present the key aspects of their implementation.
Using these techniques, rough initial sketches of 2-D and 3-D objects can automatically be refined, resulting in accurate
models that can be guaranteed to be consistent with one another. We believe that such capabilities will prove indispensable
to automating the generation of complex object databases from imagery, such as the ones required for high-resolution mapping,
realistic simulations or intelligence analysis.
01/2008: pages 190-228;
-
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we show that, given video sequences of a moving person acquired with a multi-camera system, we can track joint locations during the movement and recover shape information. We outline techniques for fitting a simplified model to the noisy 3-D data extracted from the images and a new tracking process based on least squares matching is presented. The recovered shape and motion parameters can be used to either reconstruct the original sequence or to allow other animation models to mimic the subject's actions. Our ultimate goal is to automate the process of building complete and realistic animation models of humans, given a set of video sequences
-
pages 36-47;
-
-
