Improving Data Association in Vision-based SLAM

This paper presents an approach to vision-based simultaneous localization and mapping (SLAM). Our approach uses the scale invariant feature transform (SIFT) as features and applies a rejection technique to concentrate on a reduced set of distinguishable, stable features. We track detected SIFT features over consecutive frames obtained by a stereo camera and select only those features that appear to be stable from different views. Whenever a feature is selected, we compute a representative feature given the previous observations. This approach is applied within a Rao-Blackwellized particle filter to make the data association easier and furthermore to reduce the number of landmarks that need to be maintained in the map. Our system has been implemented and tested on data gathered with a mobile robot in a typical office environment. Experiments presented in this paper demonstrate that our method improves the data association and in this way leads to more accurate maps

Authors

• Arturo Gil
• Óscar Reinoso
• Óscar Martínez Mozos
• Cyrill Stachniss
• Wolfram Burgard

Keywords

• Simultaneous localization and mapping
• Cameras
• Intelligent robots
• Euclidean distance
• Mobile robots
• Robot kinematics
• Robot vision systems
• Particle filters
• Gas insulated transmission lines
• Intelligent systems
• Scale-invariant
• Consecutive Frames
• Particle Filter
• Scale-invariant Feature Transform
• Stereo Camera
• Number Of Landmarks
• Covariance Matrix
• Viewing Angle
• Mahalanobis Distance
• Extended Kalman Filter
• Squared Euclidean Distance
• Illumination Changes
• Image Gradient
• Landmark Localization
• Feature Tracking
• Environment Map
• Laser Ranging
• Stereo Images
• Robot Movement
• Left Camera
• Visual Landmarks
• Robot Pose
• Robot Path
• Global Reference Frame