Abstract | Applications for 3D models of objects and scenes are rapidly growing in number. Active sensors are the most commonly used means of acquiring geometric models. The current acquisition process of view planning, sensing, registration and integration requires a high level of intervention by imaging specialists with extensive training and experience. Automation would improve productivity, freeing humans for higher level tasks. While progress has been made, general purpose, automated model acquisition remains an open problem. View planning, the process of determining a suitable set of sensor viewpoints, is subject to numerous competing constraints. This paper presents a theoretical framework and concept for automated view planning. The goal is to automatically obtain geometric models of a single object with triangulation-based active range sensor. |
---|