Image capture-based Visual Map database construction method and indoor positioning method using database
An image acquisition and indoor positioning technology, applied in the field of indoor positioning and navigation, can solve the problem of low WLAN positioning accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0071] The specific embodiment one, based on the Visual Map database establishment method of image collection, it comprises the following steps:
[0072] Step 1: Select the appropriate coordinate origin P according to the indoor environment that needs to be positioned 0 (X 0 ,Y 0 ), establish a two-dimensional Cartesian coordinate system;
[0073] Step 2: Starting from the coordinate origin, establish a reference point every 1 meter along the x-axis, and every 0.5 m along the y-axis, and collect 4 images for each reference point, respectively according to 0°, 90°, 180°, 270° Or 45°, 135°, 225°, 315° for image acquisition at uniform intervals, such as image 3 shown. And calculate the rotation matrix R of the camera when the reference point captures the image r ;
[0074] Step 3: Use the 128-point SURF algorithm to extract feature points from the images collected from 4 angles of each reference point, and correspond to the coordinates of the reference point in the coordin...
specific Embodiment approach 2
[0075] Specific embodiment two, utilize the indoor positioning method of the Visual Map database described in specific embodiment one, it is realized by the following steps:
[0076] Step A, in the online phase, use the 128-point SURF algorithm on the mobile phone to extract the feature point information of the image provided by the location service user, and transmit the feature point to the server;
[0077] Step B. Use the KNN algorithm for the feature points of the image, retrieve the feature points of k images that best match the provided feature points in the server, and record the corresponding position coordinates P(X, Y) and rotation of the k feature points Matrix R r ;
[0078] Step C, using the RANSAC algorithm to eliminate mismatching points between the matched image and the image provided by the user, and improve the positioning accuracy. The algorithm flow chart is shown in FIG. 4 . Where t represents the threshold of the preset Euclidean distance, n represents ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
