MonoSLAM: Real-Time Single Camera SLAM

Abstract

Abstract-We present a real-time algorithm which can recover the 3D trajectory of a monocular camera, moving rapidly through a previously unknown scene. Our system, which we dub MonoSLAM, is the first successful application of the SLAM methodology from mobile robotics to the "pure vision" domain of a single uncontrolled camera, achieving real time but drift-free performance inaccessible to Structure from Motion approaches. The core of the approach is the online creation of a sparse but persistent map of natural landmarks within a probabilistic framework. Our key novel contributions include an active approach to mapping and measurement, the use of a general motion model for smooth camera movement, and solutions for monocular feature initialization and feature orientation estimation. Together, these add up to an extremely efficient and robust algorithm which runs at 30 Hz with standard PC and camera hardware. This work extends the range of robotic systems in which SLAM can be usefully applied, but also opens up new areas. We present applications of MonoSLAM to real-time 3D localization and mapping for a high-performance full-size humanoid robot and live augmented reality with a hand-held camera.

Developing monocular visual pose estimation for arctic environments

“…Common methods range from locating simple image corners (Cheng, Maimone, & Matthies, 2005;Nister et al, 2004) to using descriptive feature detectors such as scale invariant feature transform (SIFT) (Schleicher et al, 2007;Se, Lowe, & Little, 2001) or maximally stable extremal regions (MSER) (Matas, Chum, Urban, & Pajdla, 2004). Methods for matching features are equally as diverse in the literature, with some relying on feature patch template matching methods (Davison, Reid, Molton, & Stasse, 2007), correlation peaks (Cheng et al, 2005), or feature descriptor key matching (Se et al, 2001).…”

“…At the heart of visual SLAM systems is an incremental state estimation filter, generally implemented as either an extended Kalman filter (EKF) (Davison et al, 2007) or particle filter (PF) (Eade & Drummond, 2006;Pupilli & Calway, 2006). In the EKF MonoSLAM approach (Davison et al, 2007), the EFK models the motion of the camera using a standard acceleration model.…”

Benchmarking urban six‐degree‐of‐freedom simultaneous localization and mapping

“…Among the category of feature-based 6D SLAM are the visual SLAM methods, that is, the MonoSLAM system of Davison et al (Davison, Reid, Molton, & Stasse, 2007).…”

Vision-based loop closing for delayed state robot mapping

“…Simple correlation-based features, such as Harris corners [3] or Shi and Tomasi features [4], are of common use in vision-based SFM and SLAM; from the early uses of Harris himself to the popular work of Davison [5]. This kind of features can be robustly tracked when camera displacement is small and are tailored to real-time applications.…”