A New Approach to Stereo Vision SLAM Using a Hybrid Measurement Model
Date Issued
2007
Date
2007
Author(s)
Yuan, Wei-Chun
DOI
en-US
Abstract
In visual Simultaneous Localization and Mapping, many models are proposed to make use of various kinds of vision systems including monocular camera, stereo camera, and omni-directional camera. We propose a measurement model suitable for stereo systems having good properties of efficiency and simplicity. Our approach combines visual information with three dimensional point clouds as spatial contour to calculate the relative pose of the spots where the image pairs are taken by the stereo cameras. In our method, feature extraction is done before matching the point clouds, so our model is faster than others and is robust to measurement noise. Furthermore, the sequence of the camera poses yet offers the trajectory of the robot, which is usually unavailable in online SLAM implementation.
Subjects
同步定位與地圖建立
影像同步定位與地圖建立
立體視覺
機器人學
主動式相機
SLAM
vSLAM
Stereo Vision
Stereo vSLAM
Robotics
Active Camera
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-96-R94922052-1.pdf
Size
23.31 KB
Format
Adobe PDF
Checksum
(MD5):94e4328b7e50a04a673609053b72a105