Interior location identification

• US 8,908,923 B2
• Filed: 05/13/2011
• Issued: 12/09/2014
• Est. Priority Date: 05/13/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Billingham, James, Bowyer, Helen, Brown, Kevin, Jellard, Edward, White, Graham
• Primary Examiner(s): Rush, Eric
• Application Number:
  US13/107,072
• Publication Number:
  US 20120288202A1
• Time in Patent Office: 1,306 Days
• Field of Search: 382/100, 382/103, 382/104, 382/153, 382/154, 382/181, 382/187, 382/209, 382/217, 382/218, 382/321, 382/325, 348/113, 348/116, 701/1, 701/2, 701/27, 701/28, 701/400, 701/408, 701/409, 701/450, 701/461, 701519-524, 701/526
• US Class Current: 382/104
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video

Abstract

A parse module calibrates an interior space by parsing objects and words out of an image of the scene and comparing each parsed object with a plurality of stored objects. The parse module further selects a parsed object that is differentiated from the stored objects as the first object and stores the first object with a location description. A search module can detect the same objects from the scene and use them to determine the location of the scene.

Claims

1. A computer program product for task context recovery, the computer program product comprising:

a tangible computer readable storage medium having computer readable program code executable by a processor embodied therein, the computer readable program code configured to;

parse at least one object from a first image of an interior space;

compare each parsed object with a plurality of stored objects;

select parsed objects as first objects by excluding parsed objects that are identified as potentially mobile, calculating a plurality of spatial difference scores for each of at least two parsed objects that corresponds to a same stored object as a sum of differences between each of the at least two parsed objects, and selecting the at least two parsed objects with a lowest spatial difference score as the first objects; and

index a location description of the interior space with the first objects in a location record.

2. The computer program product of claim 1, the computer readable program code further configured to:

scan the first image; and

append a secondary location indication to the location record.

3. The computer program product of claim 2, wherein the secondary location indication is selected from the group consisting of a wireless network identification and a cellular telephone network identification.

4. The computer program product of claim 1, the computer readable program code further configured to:

identify the first objects from a second image of the interior space; and

retrieve the location description in response to identifying the first objects.

5. The computer program product of claim 1, the computer readable program code further configured to:

scan a second image; and

narrow a scope for identifying the first objects using a secondary location indication.

6. The computer program product of claim 1, wherein the first object comprises text and an Optical Character Recognition (OCR) process parses the text.

7. The computer program product of claim 1, wherein the location description comprises at least one of a room number, an address, a navigation direction, a building map, and coordinates.

8. An apparatus comprising:

a tangible computer readable storage medium storing computer readable program code executable by a processor, the computer readable program code comprising;

a parse module parsing at least one object from a first image of an interior space, comparing each parsed object with a plurality of stored objects, selecting parsed objects as first objects by excluding parsed objects that are identified as potentially mobile, calculating a plurality of spatial difference scores for each of at least two parsed objects that corresponds to a same stored object as a sum of differences between each of the at least two parsed objects, selecting the at least two parsed objects with a lowest spatial difference score as the first objects, and indexing a location description of the interior space with the first objects in a location record.

9. The apparatus of claim 8, the parse module further scanning the first image and appending a secondary location indication to the location record.

10. The apparatus of claim 9, wherein the secondary location indication is selected from the group consisting of a wireless network identification and a cellular telephone network identification.

11. The apparatus of claim 8, the apparatus further comprising a search module identifying the first objects from a second image of the interior space and retrieving the location description in response to identifying the first objects.

12. The apparatus of claim 11, the search module further scanning the second image and narrowing a scope for identifying the first objects using a secondary location indication.