IP Library Granted Patent US 9,613,274
Granted Patent B2
US 9,613,274 · App. 14/284,564 · Granted Apr 4, 2017

Identifying an obstacle in a route

Inventors: Mark B. Stevens (Austin, TX); John D. Wilson (Houston, TX)
Assignee: International Business Machines Corporation
G06K9/00664G01C21/00G06K9/00G06K9/46G06K9/6202G09B21/00G09B21/001G09B21/008H04N7/181G06K9/00805
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,613,274
App. No.
14/284,564
Granted
Apr 4, 2017
Kind
B2
Abstract

A system and computer implemented method for identifying an object in a route is disclosed. The method may include capturing a first set of images during a first traversal of a first route. The method may also include capturing a second set of images during a second traversal of the first route. The method may also include identifying, by comparing the first set of images with the second set of images, an object in the second set of images meeting an obstruction criteria. The method may also include providing a notification of the object which was identified as meeting the obstruction criteria.

Claims (19)

1. A computer implemented method for identifying an object in a route, the method comprising:

capturing, by an image capture device, a first set of images during a first traversal of a first route;

capturing, by the image capture device, a second set of images during a second traversal of the first route;

identifying, by an image analysis module configured to compare the first set of images with the second set of images, an object in the second set of images meeting an obstruction criteria; and

providing a notification of the object which was identified as meeting the obstruction criteria;

wherein capturing the first set of images during the first traversal of the first route includes:

collecting route frequency data for a set of routes traversed by a user;

determining, for a specific route of the set of routes traversed by the user, that a frequency value is greater than a frequency threshold value;

selecting, in response to determining that the specific route has the frequency value greater than the frequency threshold value, the route as the first route.

2. The method of claim 1 , wherein the obstruction criteria includes a displacement threshold and an object size threshold.

3. The method of claim 1 , wherein capturing the first set of images during the first traversal of the first route includes:

creating, in response to receiving a route traversal initiation command, a starting point of the first route;

collecting, in response to receiving the route traversal initiation command, image data and distance data for a path traversed by a user; and

creating, in response to receiving a route traversal termination command, an ending point of the first route.

4. The method of claim 1 , wherein the first set of images and the second set of images are captured by a mobile device including but not limited to one or more selected from the group consisting of smart phones, tablets, smart watches, and wearable computing devices.

5. The method of claim 4 , further comprising determining, using a user interface provided on the mobile device, a set of route preferences and a set of obstruction criteria preferences.

6. The method of claim 1 , wherein the first route is a frequently traversed path by a user between a first location and a second location.

7. The method of claim 1 , wherein identifying the object in the second set of images meeting an obstruction criteria further comprises using a digital image processing algorithm configured to use Scale-Invariant Feature Transform (SIFT) techniques to detect one or more objects, and measure one or more dimensions of the one or more objects.

8. The method of claim 1 , wherein the first set of images and the second set of images are captured at a set of image capture locations selected from a group consisting of doorways, corners, hallway entrances, or configurable distance increments.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 22, 2014
From: STEVENS, MARK B; WILSON, JOHN D.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 032947/0453 →
Continuity (1)
Related Publication 20150339531A1 · Nov 26, 2015