Accurate noise models are important to perform reliable robust image analysis. Indeed, many vision problems can be seen as parameter estimation problems. In this paper, two noise m...
Sio-Song Ieng, Jean-Philippe Tarel, Pierre Charbon...
The traditional goal of computer vision, to reconstruct, or recover properties of, the scene has recently been challenged by advocates of a new purposive approach in which the vis...
Michael J. Black, Yiannis Aloimonos, Christopher M...
This paperdescribes initial work on a family of projectivereconstructiontechniques that extract projection matrices directly and linearly from matching tensors estimated from imag...
This paper describes the continuing development of a system for tracking multiple man made objects, (typically vehicles) moving in a natural open world scene, where the detected m...
We describe several established error of fit (EOF) functions for use in the least square fitting of ellipses, and introduce a further four new EOFs. Four measures are given for as...
We introduce a new class of panoramic images, called polycentric panoramic images, which is a generalization from more specific classes such as single-center, multiple-center, or ...