Cue Fusion using Information Theoretic Learning
نویسندگان
چکیده
In order to segment independently moving objects (IMO) in a visual scene, neurons in the higher processing stages of the visual cortex are able to fuse visual attributes (cue fusion). The modeling of cue fusion is the objective of the predoctoral project and will be developed in the context of Information Theoretic Learning.
منابع مشابه
Self-supervised learning: When is fusion of the primary and secondary sensor cue useful?
Self-supervised learning (SSL) is a reliable learning mechanism in which a robot enhances its perceptual capabilities. Typically, in SSL a trusted, primary sensor cue provides supervised training data to a secondary sensor cue. In this article, a theoretical analysis is performed on the fusion of the primary and secondary cue in a minimal model of SSL. A proof is provided that determines the sp...
متن کاملAn information theoretic approach to joint probabilistic face detection and tracking
A joint probabilistic face detection and tracking algorithm for combining a likelihood estimation and a prior probability is proposed in this paper. Face tracking is achieved by a Bayesian framework. The likelihood estimation scheme is based on statistical training of sets of automatically generated feature points, while the prior probability estimation is based on the fusion of an information ...
متن کاملFusing Color and Shape for Bag-of-Words Based Object Recognition
In this article we provide an analysis of existing methods for the incorporation of color in bag-of-words based image representations. We propose a list of desired properties on which bases fusing methods can be compared. We discuss existing methods and indicate shortcomings of the two well-known fusing methods, namely early and late fusion. Several recent works have addressed these shortcoming...
متن کاملDynamic Multi-Cue Information Fusion for Robust Detection of Traffic Infrastructure
-Visual object detection using single cue information has been successfully applied in various tasks, in particular for near range recognition. While robust classification and probabilistic representation enhance 2D pattern recognition performance, they are 'per se' restricted due to the limited information content of single cues. The contribution of this work is to demonstrate performance impr...
متن کاملBayesian Decision Fusion for Dynamic Multi-Cue Object Detection
Visual object detection using single cue information has been successfully applied in various tasks, in particular for near range recognition. While robust classification and probabilistic representation enhance 2D pattern recognition performance, they are ’per se’ restricted due to the limited information content of single cues. The contribution of this work is to demonstrate performance impro...
متن کامل