MonoSLAM: Real-Time Single Camera SLAM
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vision-Based SLAM in Real-Time
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Active matching for visual tracking
Robotics and Autonomous Systems
Covariance recovery from a square root information matrix for data association
Robotics and Autonomous Systems
Automatically and efficiently inferring the hierarchical structure of visual maps
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
On optimal dynamic sequential search for matching in real- time machine vision
IEEE Transactions on Image Processing
Combining geometric and appearance priors for robust homography estimation
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Temporal accumulation of oriented visual features
Journal of Visual Communication and Image Representation
Robotics and Autonomous Systems
Scene reconstruction and visualization from internet photo collections
Scene reconstruction and visualization from internet photo collections
Editors Choice Article: Visual SLAM: Why filter?
Image and Vision Computing
Information-theoretic compression of pose graphs for laser-based SLAM
International Journal of Robotics Research
Jointly compatible pair linking for visual tracking with probabilistic priors
ACSC '11 Proceedings of the Thirty-Fourth Australasian Computer Science Conference - Volume 113
Hi-index | 0.00 |
In most cases when information is to be extracted from an image, there are priors available on the state of the world and therefore on the detailed measurements which will be obtained. While such priors are commonly combined with the actual measurements via Bayes驴 rule to calculate posterior probability distributions on model parameters, their additional value in guiding efficient image processing has almost always been overlooked. Priors tell us where to look for information in an image, how much computational effort we can expect to expend to extract it, and of how much utility to the task in hand it is likely to be. Such considerations are of importance in all practical real-time vision systems, where the processing resources available at each frame in a sequence are strictly limited 驴 and it is exactly in high frame-rate real-time systems such as trackers where strong priors are most likely to be available. In this paper, we use Shannon information theory to analyse the fundamental value of measurements using mutual information scores in absolute units of bits, specifically looking at the overwhelming case where uncertainty can be characterised by Gaussian probability distributions. We then compare these measurement values with the computational cost of the image processing required to obtain them. This theory puts on a firm footing for the first time principles of 驴active search驴 for efficient guided image processing, in which candidate features of possibly different types can be compared and selected automatically for measurement.