Stories
Slash Boxes
Comments

In+ersec+ion for Spatial People

Landmark Based Navigation Developed by Nokia

posted by Satri on Wednesday April 23, @04:56PM   Printer-friendly   Email story  Permalink  Trackback URI  Slashdotthis  Diggthis  Del.icio.us
from the see-where-you-go dept.
Last week, All Points Blog linked to an article on Nokia developing a navigating system based on image recognition. From the article: "With landmark-based navigation you won’t even need to know your address or cross streets to get directions. You just take a picture of a nearby landmark, like the Golden Gate Bridge, with the camera in your mobile phone. Then, Nokia will match your photo with other landmark photos in its mapping database, and tell you where you are. Instructions to your destination are given by red arrows added to pictures, text or voice." Related stories below include GPS phones used to identify landmarks and the Open Landmark directory.

Related Stories

Technology: Identifying Landmarks Using GPS Phones 1 comment [+]
The Geospatial Semantic Web Blog describes iPointer, a device to identify landmarks using GPS phones. From the blog: "Once the user information is arrived at the remote server, the server uses various algorithms to approximate the exact physical thing that the user is interested. There is a predefined database of physical things that the server has knowledge about." This service sounds very similar to this previous story.
Industry: Recreating Cities Using Online Photos [+]
SlashDot is currently running a discussion on another technology along the likes of Photosynth by Microsoft. To help you differentiate between the two, a co-author of the new tech wrote in one of his comments on SlashDot : "I also worked on the Photo Tourism project (which is related to Photosynth). There's a big difference between Photosynth and this new 3D reconstruction work, in that Photosynth takes a photo collection and reconstructs camera positions and a sparse point cloud (a set of disconnected 3D points floating in space), while in this new work we build *dense* 3D models of scenes (in the form of polygon meshes). Dense models are usually much better for use in applications like computer graphics, since they can be used to render scenes with much more photo-realism."

Here is SlashDot's summary : "The billion of images available from a site like Flickr has stimulated the imagination of many researchers. After designing tools using Flickr to edit your photos, another team at the University of Washington (UW) is using our vacation photos to create 3D models of world landmarks. But recreating original scenes is challenging because all the photos we put on Flickr and similar sites don't exhibit the same quality. With such a large number of pictures available, the researchers have been able to reconstruct with great accuracy virtual 3D model of landmarks, including Notre Dame Cathedral in Paris and the Statue of Liberty in New York City."
Nokia's Maps 2.0 now in Beta [+]
BBC News writes about Nokia's Maps 2.0 beta release. Some exerpts from the article:
* "Nokia is taking navigation services out of the car so it can always be with you," said Olli-Pekka Kallasvuo, president and CEO of the firm.
* "Nokia's announcement underlines its belief that GPS chips will become as ubiquitous in mobile phones as cameras. It has already made a $6bn (£3bn) investment in mapping company NavTeq to show that it is putting its money where its mouth is." * Mr Kallasvuo said: "Navigation is one of the foundations of the context-aware mobile phone. We believe it will be as important as voice capability was 20 years ago."
Open Landmark Directory in Beta [+]
Very Spatial links to the Open Landmark project. From the website: "What is Open Landmark? Open Landmark is a free, collaborative, landmark directory maintained by volunteers around the world. What's in a Landmark? Street address, latitude, longitude, distance away from where you are, photographs, name of the place, tags, description, phone number, URL, ratings, and comments." First question that came to my mind is how this community-driven project relates to other projects such the successful OpenStreetMap and if the objectives and features of OpenLandmark could simply be integrated into other existing projects. Their FAQ is informative: "The system tracks who has discovered landmarks and bookmarked photos to the landmarks. It will assign points to each discovery and credit the users for top photos and votes. In the near future, we will be putting ads on the pages. When we do so, we will announce a revenue sharing plan." See also some related stories below.
Display Options Threshold:
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.