Image-based object location system and process
First Claim
Patent Images
1. An image-based object location system for generating a human readable map comprising:
- an image generator for producing a plurality of images containing information, wherein the images are of an original place to be mapped;
a position and orientation identifier for accessing the information associated with the plurality of images and generating position and orientation information of at least a portion of the plurality of images;
a floor plan generator for generating a floor plan based on the plurality images and position and orientation information;
a feature identifier for;
extracting feature-related data from the image, the position and orientation information and the floor plan;
generating a graphical representation of real-world objects within the floor plan to create a feature map based on the extracted feature-related data, the image information, the position and orientation information, and the floor plan; and
associating a name, a category, and at least two keyword attributes to each of the real-world objects based on the image, the position and orientation information, and the floor plan; and
,a database for storing the feature-related data and the name, category, and the at least two keyword attributes for one of the group of real-time retrieval and manual retrieval, wherein each of the name, category and at least two key words attributes is individually searchable to identify and locate the real-world object in the map.
3 Assignments
0 Petitions
Accused Products
Abstract
A camera image, associated pose, and range data are applied as inputs to a floor plan generation process, which outputs a venue floor plan. The camera image, associated pose, and venue floor plan are input to a data extraction process, which outputs feature geo-location and metadata information to a data storage mechanism.
-
Citations
11 Claims
-
1. An image-based object location system for generating a human readable map comprising:
-
an image generator for producing a plurality of images containing information, wherein the images are of an original place to be mapped; a position and orientation identifier for accessing the information associated with the plurality of images and generating position and orientation information of at least a portion of the plurality of images; a floor plan generator for generating a floor plan based on the plurality images and position and orientation information; a feature identifier for; extracting feature-related data from the image, the position and orientation information and the floor plan; generating a graphical representation of real-world objects within the floor plan to create a feature map based on the extracted feature-related data, the image information, the position and orientation information, and the floor plan; and associating a name, a category, and at least two keyword attributes to each of the real-world objects based on the image, the position and orientation information, and the floor plan; and
,a database for storing the feature-related data and the name, category, and the at least two keyword attributes for one of the group of real-time retrieval and manual retrieval, wherein each of the name, category and at least two key words attributes is individually searchable to identify and locate the real-world object in the map. - View Dependent Claims (3, 4, 5, 6)
-
-
2. An image-based object location process for generating a human readable map comprising the steps of:
-
receiving information from an image, wherein the image is of an original place to be mapped; accessing the information associated with the image and generating position and orientation information for at least a portion of the image; generating a floor plan based on the image and the position and orientation information; extracting feature-related data from the image, the position and orientation information and the floor plan; processing the image, position and orientation information and floor plan into real-world objects in a map; associating a name, a category, and at least two keyword attributes to each of the real-world objects based on the image, the position and orientation information, and the floor plan; and
,storing the feature-related data and the name, category, and the at least two keyword attributes for one of the group of real-time retrieval and manual retrieval, wherein each of the name, category and at least two key words attributes is individually searchable to identify and locate the real-world object in the map. - View Dependent Claims (7, 8, 9, 10, 11)
-
Specification