Abstract
Navigation and localization are important capabilities of mobile systems allowing definition of mission goals. Only the knowledge about the absolute and relative position in an indoor or outdoor environment allows a free definition of mission goals and path planning in areas not previously traversed by the system. A typical concurrent goal is the reconstruction of coherent 3D geometric representations of arbitrary indoor or outdoor environments from a configurable set of sensors. This representation is typically used as a reference for localization. The sensor configuration is thereby defined by the required accuracy and system costs. We investigate monocular and binocular cameras, laser range finders, and inertial systems as input sources for this task. The minimal hardware configuration of such a system is a monocular camera that can be supported by additional sensors to enhance the quality of the reconstructed models. The goal is to replace expensive inertial systems with a set of low-cost sensors, like video cameras available on most current computer systems. The necessary accuracy is achieved through fusion of information over a sequence of images. The idea is to replace expensive hardware with appropriate algorithmic techniques to compensate for the imperfections of the low-cost sensors. An important milestone towards a high accuracy reconstruction of the environment is an exact localization in an unknown or partially known environment. The reference model for localization needs often to be extracted in parallel to the actual localization task. This process is known in the literature as Simultaneous Localization and Mapping (SLAM). The localization is necessary to fuse the sensor readings from different positions to a consistent and complete 3D model. In this chapter, we will focus on the localization task from a video camera. We assume a video camera mounted on a mobile system. The localization implicates several challenges. The first challenge is an accurate estimation of the 3D pose pa-
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
