Robust Real-Time SLAM Using Scale Prediction and Exemplar Based Feature Description

Our latest visual SLAM algorithm gives very robust performance, even in the presence of severe occlusion of features or camera shake. The key component is a novel utilisation of multi-resolution descriptors in a coherent top-down framework. Scale prediction is used to speed up feature recognition and exemplar based descriptors are used to improve wide angled matching. The resulting system provides superior performance over previous methods in terms of robustness to erratic motion, camera shake, and the ability to recover from measurement loss.

Video Example 1 Video Example 2

Real-Time SLAM Using Line-Segments and a Concurrently Built Model

This work develops a monocular real-time SLAM system that uses line segments extracted on the fly and that builds a wire-frame model of the scene to help tracking. The use of line segments provides viewpoint invariance and robustness to partial occlusion, whilst the model-based tracking is fast and efficient, reducing problems associated with feature matching and extraction.

Video Example

Real-Time Camera Tracking Using Known 3D Models and a Particle Filter

We present an algorithm which can track the 3D pose of a hand held camera in real-time using predefined models of objects in the scene. The technique utilises and extends recently developed techniques for 3D tracking with a particle filter. The novelty is in the use of edge information for 3D tracking which has not been achieved before within a real-time Bayesian sampling framework.

Video Example

Real-time Visual SLAM with Resilience to Erratic Motion

SLAM using a single camera becomes difficult when erratic motions violate predictive motion models. This problem needs to be addressed if visual SLAM algorithms are to be transferred from robots or mobile vehicles onto hand-held or wearable devices.

Video Example

Real-time Camera Tracking Using Particle Filtering

We have developed a real-time camera tracking system based on particle filtering. It gives robust tracking of a hand-held camera, even in the presence of severe camera shake and occlusion. Our system is the first to demonstrate real-time camera tracking of this form using a sequential Monte Carlo method.

Video Example