2026-04-17T01:26:43Zhttps://recercat.cat/oai/request

oai:recercat.cat:10256/22982024-05-22T09:46:56Zcom_2072_452955com_2072_2054col_2072_452957

00925njm 22002777a 4500 dc Nicosevici, Tudor author García Campos, Rafael author 2008 This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential structure from motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene http://hdl.handle.net/10256/2298 Imatges -- Processament Visió per ordinador Visualització tridimensional (Informàtica) Computer graphics Image processing Three-dimensional display systems Online Robust 3D Mapping Using Structure from Motion Cues