We present an application of hierarchical Bayesian estimation to robot map building. The revisiting problem occurs when a robot has to decide whether it is seeing a previously-built portion of a map, or is exploring new territory. This is a difficult decision problem, requiring the probability of being outside of the current known map. To estimate this probability, we model the structure of a ”...

Multi-robot map merging is an essential task for cooperative robots navigation. Each robot is building its own local map with different reference. To merge these maps to global one, the transformation between the local maps must be computed so that we have one reference. Data association and inter robot observations are two alignment methods which are used to compute the transformation paramete...

In this paper, we propose an improved mechanism for saliency detection. Firstly,based on a neoteric background prior selecting four corners of an image as background,we use color and spatial contrast with each superpixel to obtain a salinecy map(CBP). Inspired by reverse-measurement methods to improve the accuracy of measurement in Engineering,we employ the Objectness labels as foreground prior...

This paper regards images with captions as a cross-media parallel corpus, and presents a corpus-based relevance feedback approach to combine the results of visual and textual runs. Experimental results show that this approach performs well. Comparing with the mean average precision (MAP) of the initial visual retrieval, the MAP is increased from 8.29% to 34.25% after relevance feedback from cro...

This paper presents an approach for building corporate knowledge, defined as the total knowledge acquired by an enterprise in its business dealings, through integration of its existing ontologies. We propose to represent corporate knowledge as the final merged ontology, defined under our formalism, in which a canon, or common ontology, is used as the standard under which all other ontologies ar...

This paper presents a quantitative comparison of several multi-view stereo reconstruction algorithms. In this paper, we propose a depth-map merging based hybrid method for large-scale scenes which takes both accuracy and efficiency is used into account. Different from typical multiview stereo methods, our approach is not only imposes the photo consistency constraint, but also associates explici...

We present an application of hierarchical Bayesian estimation to robot map building. The revisiting problem occurs when a robot has to decide whether it is seeing a previouslybuilt portion of a map, or is exploring new territory. This is a difficult decision problem, requiring the probability of being outside of the current known map. To estimate this probability, we model the structure of a "t...