Image-based object location system and process

• US 10,127,667 B2
• Filed: 08/03/2015
• Issued: 11/13/2018
• Est. Priority Date: 08/01/2014
• Status: Active Grant

• Current Assignee: ABL IP Holding LLC (Acuity Brands, Inc.)
• Original Assignee: Locuslabs Inc. (Acuity Brands, Inc.)
• Inventors: Kennedy, Campbell O., McMinn, Jason D.
• Primary Examiner(s): Gilliard, Delomia L
• Application Number:
  US14/817,026
• Publication Number:
  US 20160035094A1
• Time in Patent Office: 1,198 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/73 using feature-based methods

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.

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.

3. The system of claim 1, wherein processing the image, position and orientation information and floor plan into the real-world objects in the map further comprises using ray-tracing to determine a location of at least one of the real world objects in the map.

4. The system of claim 1, wherein generating the graphical representation of real-world objects within the floor plan is further based on range data associated with the image.

5. The system of claim 4, wherein the position and orientation identifier is further configured to determine the range data based on the image.

6. The system of claim 4, wherein the system further comprises at least one sensor, wherein the at least one sensor is configured to obtain the range data.

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.

7. The process of claim 2, generating the graphical representation of real-world objects within the floor plan further comprises using ray-tracing to determine a location of the real world objects in the map.

8. The process of claim 2, wherein generating the graphical representation of real-world objects within the floor plan is further based on range data associated with the image.

9. The process of claim 8, wherein the position and orientation identifier is further configured to determine the range data based on the image.

10. The process of claim 8, wherein the system further comprises at least one sensor, wherein the at least one sensor is configured to obtain the range data.

11. The process of claim 2, wherein the associating is performed automatically based on image pattern recognition.