Generation of 3D Mirror World via 3D RGB-D SLAM
This is a preliminary result on building an object-oriented 3D RGB-Depth map for a large indoor space with high visual quality.
The result is different from kinect based 3D RGB-Depth SLAM in two points that
- It uses of 3D RGB-Depth sensor of which range is far larger (30m) than Kinect and can be of useful even in outdoor. Also, this sensor provides 360 deg full view as well as 180 deg depth coverage of which redeems the difficulty coming out of simultaneity (such as SLAM and SfM).
- Its aim is not just RGB-Depth but implement that map in an object-oriented manner. In other words, the proposed technique automatically segments object and structure, so that each RGB-D map can be composed of object by object. This will enable the object-based semantic mapping which will make human interaction in this mirror world to be feasible.
|과제명||동적 실내환경의 RGB-D SLAM 기반 실시간 삼차원 공간 모델링 기술|