الفهرس 
Chapter 1 IntroductionOnly 14 pages are availabe for public view
 |  | from | 293 |  |  |
| | | from | 293 | | |
Abstract
Recently, explosive growth of research in computer vision, graphics, and robotics have been witnessed and brought by the evolution of depth cameras. The emerging active depth cameras, such as Velodyne HDL lidars, Microsoft kinects, TOF cameras, and ASUS Xtion Pro, can produce high quality range information in real time with an affordable cost. Hence, they are used for widespread applications such as augmented reality, interactive free-viewpoint video, semantic scene analysis, and human pose recognition. With depth information, computers will have a better understanding of the physical world for solving many fundamental computer vision problems. However, modern 3D scanning devices, such as TOF (Time Of Flight) cameras and Microsoft Kinect sensors, provide a huge unbalance between the resolution of the intensity image and its corresponding depth map. In addition, the quality of the depth images captured by current low-cost depth sensing devices is often poor and noisy. In this thesis, the efforts that have been made in utilizing that potentially noisy, holed and low-resolution depth map for getting an enhanced HR depth map using different sparse representations, that are one of the most active research areas, are described.