Technique based on 3D LIDAR scanning and MPEG7 Visual Search Solution

This paper describes a location algorithm for mobile phones based on image recognition. The use of image recognition based (IRB) positioning in mobile applications is characterized by the availability of a single camera; under this constraint, to estimate the camera position and orientation a prior knowledge of 3D environment is needed, acquired for instance with a LiDAR (Light Detection And Ranging) survey, in the form of a database of images with associated spatial information The procedure to locate the camera can be divided in two steps, a first step is the selection of the (reference) image from the database as most similar to the (query) image used to locate the camera and a second one for estimation of the position and orientation of the camera based on available 3D information on the reference image. In designing those steps of the proposed location procedure, we propose to reuse as much as possible the solutions adopted in MPEG7 standard for Visual Search: for processing time optimization we have introduced also in position estimation procedure, with an approach similar to the one of retrieval procedure defined by MPEG7, the geometric check for a preliminary coarse outliers rejections in paired descriptors belonging to the couple (query and reference) of images. We present the position and orientation accuracy results of the location methodology, for indoor and outdoor environment, that reaches few decimeters precision in large percentage of case in both selected environments.