|
|
Scalable Multisensor 3D Reconstruction Framework
Šolony, Marek ; Kneip, Laurent (oponent) ; Sojka, Eduard (oponent) ; Zemčík, Pavel (vedoucí práce)
Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection, robotic navigation and map building, to the movie industry, in particular, scene survey and special effects integration to scenes. It is common practice to capture the scene with multiple different types of sensors such as monocular, stereoscopic or spherical cameras or 360-degree laser scanners to achieve large coverage of the scene. The advantage of the laser scanners and spherical cameras is that they capture the full surrounding scene as a consistent seamless image. Using easy to operate and manipulate hand-held conventional cameras, the details of the scene obstructed areas are easily covered. The 3D reconstruction consists of three steps--data acquisition, data processing and registration, and refinement of the reconstruction. The contribution of this thesis is a careful analysis of the image registration from several types of cameras~(planar and spherical), as well as 3D laser measurements to obtain an initial estimation of the sensor position and the 3D structure. They are further refined by a unified representation system capable of integrating multisensor measurements and obtain an accurate 3D reconstruction of the environment. The evaluation of the multisensor 3D reconstruction is performed on multiple synthetic, and real-world datasets. The accuracy comparison with commercial multisensor 3D reconstruction software shows that our proposed solution achieves more accurate results. While the commercial solutions are limited to specific type of sensors, our framework can integrate any types of measurements and constraints.
|
|
|
Scalable Multisensor 3D Reconstruction Framework
Šolony, Marek ; Kneip, Laurent (oponent) ; Sojka, Eduard (oponent) ; Zemčík, Pavel (vedoucí práce)
Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection, robotic navigation and map building, to the movie industry, in particular, scene survey and special effects integration to scenes. It is common practice to capture the scene with multiple different types of sensors such as monocular, stereoscopic or spherical cameras or 360-degree laser scanners to achieve large coverage of the scene. The advantage of the laser scanners and spherical cameras is that they capture the full surrounding scene as a consistent seamless image. Using easy to operate and manipulate hand-held conventional cameras, the details of the scene obstructed areas are easily covered. The 3D reconstruction consists of three steps--data acquisition, data processing and registration, and refinement of the reconstruction. The contribution of this thesis is a careful analysis of the image registration from several types of cameras~(planar and spherical), as well as 3D laser measurements to obtain an initial estimation of the sensor position and the 3D structure. They are further refined by a unified representation system capable of integrating multisensor measurements and obtain an accurate 3D reconstruction of the environment. The evaluation of the multisensor 3D reconstruction is performed on multiple synthetic, and real-world datasets. The accuracy comparison with commercial multisensor 3D reconstruction software shows that our proposed solution achieves more accurate results. While the commercial solutions are limited to specific type of sensors, our framework can integrate any types of measurements and constraints.
|
host ::
RSS.