PROJECT TITLE :

Building a 3-D Line-Based Map Using Stereo SLAM

ABSTRACT:

This paper presents a graph-primarily based visual simultaneous localization and mapping (SLAM) system using straight lines as features. Compared with point features, lines give so much richer data about the structure of the environment and make it possible to infer spatial semantics from the map. Employing a stereo rig as the only real sensor, our proposed system utilizes several advanced techniques, like motion estimation, pose optimization, and bundle adjustment. We have a tendency to use 2 totally different representations to parameterize 3-D lines during this paper: Plücker line coordinates for efficient initialization of newly observed line options and projection of three-D lines, and orthonormal representation for graph optimization. The proposed system is tested with indoor and outdoor sequences, and it exhibits higher reconstruction performance against a purpose-based mostly SLAM system in line-rich environments.