As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This manuscript proposes a novel cloud-based localization infrastructure system for various mobile objects. All sorts of mobile objects, such as a robot, a smartphone, a card tag hanging around people neck, a drug cart in a hospital, and a vehicle in a warehouse, can be localized as a client of this system. The client only has to take a picture and send it to the server of this system. The server manages a 3D map and localizes the picture sent from the client in the map. This map, which is constructed beforehand, is coordinated with a real world so that the localization result is given as a 6-dimensional coordination including position and posture. Such a system includes several unsolved problems: what is a better map representation, how to localize a picture in the 3D map, how accurate does this system provide a result, how long to get the result? We have tackled these problems and solved them partly by developing a 3D-wireframe map and a similarity-based localization algorithm. We explain our solutions including map representation and localization algorithm with recent results.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.