Indoor surface model estimation and visualization using monocular camera | |
| Author | Zask, Ran |
| Call Number | AIT Thesis no.CS-08-16 |
| Subject(s) | Vision, Monocular Visualization |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | In recent years, mobile robot implementations have been based more on sophisticated computer vision techniques rather than "pure" electronics. Nowadays, robots can clean the swimming pool, mow the grass and even clean the carpets at home. In many mobile robot applications involving exploration of unknown environments, it would be extremely useful be able to obtain an accurate surface model as well as to provide human operators with a real-time 3D visualization of the environment the robot is exploring. Although a great deal of progress has been made in the separate fields of photorealistic structure from motion and real-time vision-based robot localization and mapping (SLAM), the ultimate goal of real-time 3D visualization of the robot's environment has yet to be realized. This thesis aims to improve the robot's "understanding" of the environment and to provide the human operator, with the means for acquiring and maintaining situation awareness as easy and quickly as possible. I propose a simple and efficient incremental algorithm for 3D modeling amenable to real-time implementation. The algorithm creates a polygonal mesh model of the environment from a monocular video feed or sequence of images. The key to the algorithms simplicity and efficiency is the use of the isosurface of a coarse 3D occupancy grid that is incrementally updated as new images arrive. The isosurface-based scene reconstruction provides low metric accuracy but helps to filter measurement noise and allows rapid construction of a 3D visualization. I demonstrate the practicality and effectiveness of the algorithm by visualizing wire frame models and generating an OpenGL model of a real indoor environment. |
| Year | 2008 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Honda, Kiyoshi ;Guha, Sumanta; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2008 |