Pii: S0262-8856(00)00052-4

Automatic 3D face authentication

This paper presents automatic face authentication from facial surface analysis. This geometrical approach was motivated by diiculties encountered when considering frontal face recognition. Apart from being less sensitive to viewpoint and lighting conditions, the method exploits information which is complementary to grey level based approaches, enabling the fusion with those techniques. A 3D acq...

Pii: S0262-8856(00)00060-3

Knowledge of the position and orientation of 3D planes that exist in a scene is very important for many machine vision-based tasks, such as navigation, self-localization and docking. In this paper we propose two iterative methods for robustly computing the plane parameters out of given image sequences. Both methods include the (limited) ability to determine unknown parameters of the 3D-camera m...

Navigation in birds and other animals

This paper describes how different animals cope with the challenges of orienting in very diverse environments. First, a broad general overview is given. Then, as a case story, bird migration is treated in more detail. The aim of the paper is to encourage designers of mobile robots to consider the natural solutions already used by animals when developing navigation systems for their robots. q 20...

A probabilistic model for appearance-based robot localization

Guaranteeing the probability of success using repeated runs of genetic algorithm

norm RGA P P = Q 2. Eqn (14) in pg. 558 should read 140019 728) 150)(100)(5 (4 1116141818) 95. 0 (= + = Q 3. Eqn (16) in the same page should read 9958 46655) 19429 (25) 5. 0 (4 1116141818) 95. 0 (= + = Q 4. In eqn (6), the correct names in statistics for and est P α are the lower confidence bound and the confidence level (see E.L. Lehmann, Testing statistical hypotheses, 2 nd Ed. Wiley (1986) ...