M
Matthias O. Franz
Researcher at University of Western Ontario
Publications - 137
Citations - 3921
Matthias O. Franz is an academic researcher from University of Western Ontario. The author has contributed to research in topics: Equivariant cohomology & Cohomology. The author has an hindex of 27, co-authored 132 publications receiving 3632 citations. Previous affiliations of Matthias O. Franz include Daimler AG & Konstanz University of Applied Sciences.
Papers
More filters
Journal ArticleDOI
Biomimetic robot navigation
TL;DR: The review shows that biomimetic systems make significant contributions to two fields of research: first, they provide a real world test of models of biological navigation behaviour; second, they make new navigation mechanisms available for technical applications, most notably in the field of indoor robot navigation.
Journal ArticleDOI
Iterative kernel principal component analysis for image modeling
TL;DR: A new iterative method for performing KPCA is proposed, the kernel Hebbian algorithm, which iteratively estimates the kernel principal components with only linear order memory complexity.
Journal ArticleDOI
Where did I take that snapshot? Scene-based homing by image matching
TL;DR: This work shows that most existing approaches to scene-based homing implicitly assume an isotropic landmark distribution, and proposes a homing scheme that uses parameterized displacement fields that is obtained from an approximation that incorporates prior knowledge about perspective distortions of the visual environment.
Journal ArticleDOI
Center-surround patterns emerge as optimal predictors for human saccade targets.
TL;DR: It is shown that center-surround patterns emerge as the optimal solution for predicting saccade targets from their local image structure, and bottom-up visual saliency may not be computed cortically as has been thought previously.
Proceedings Article
A Nonparametric Approach to Bottom-Up Visual Saliency
TL;DR: The model is rather simplistic and essentially parameter-free, and contrasts recent developments in the field that usually aim at higher prediction rates at the cost of additional parameters and increasing model complexity, and in fact learns image features that resemble findings from several previous studies.