US 9,542,585 B2Granted

Efficient machine-readable object detection and tracking

AssigneeApple Inc.

InventorsGeorge Williams, Benjamin Olson, Sebastien Beysserie, Ethan Tira-Thompson, Jianping Zhou, Claus Molgaard, Todd Sachs, Rudolph van der Merwe, Marco Zuliani

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A method to improve the efficiency of the detection and tracking of machine-readable objects is disclosed. The properties of image frames may be pre-evaluated to determine whether a machine-readable object, even if present in the image frames, would be likely to be detected. After it is determined that one or more image frames have properties that may enable the detection of a machine-readable object, image data may be evaluated to detect the machine-readable object. When a machine-readable object is detected, the location of the machine-readable object in a subsequent frame may be determined based on a translation metric between the image frame in which the object was identified and the subsequent frame rather than a detection of the object in the subsequent frame. The translation metric may be identified based on an evaluation of image data and/or motion sensor data associated with the image frames.

Claims19

Dependent claims

A non-transitory program storage device, readable by a processor and comprising computer-readable instructions stored thereon, which when executed by one or more processors, cause the one or more processors to:

receive a set of image frames;
analyze a first subset of image frames of the set of image frames to determine that at least one of the first subset of image frames satisfies one or more criteria;
analyze image data in at least one second image frame of a second set of image frames to detect a location of a machine-readable object in the at least one second image frame in response to determining that at least one of the first subset of image frames satisfies the one or more criteria, wherein the machine-readable object corresponds to either a one-dimensional or a two-dimensional spatial structure, and wherein the second set of image frames is received after the first set of image frames;
identify a location of the machine-readable object in at least one third image frame in a third set of successively received image frames, the identification based, at least in part, on the-detected location of the machine-readable object in the at least one second image frame and on a translation metric between the at least one second image frame and the third set of image frames;
determine a signature based, at least in part, on image data in the at least one third image frame that corresponds to the location of the machine-readable object in the at least one second image frame;
align the signature with one or more models;
and
identify one of the one or more models that is best aligned with the signature.

5 more elements

A method, comprising:

receiving, using one or more processing devices, a set of image frames;
analyzing, using the one or more processing devices, a first subset of image frames in the set of image frames to determine that at least one of the first subset of image frames satisfies one or more criteria;
analyzing, using the one or more processing devices, image data in at least one second image frame of a second set of image frames in response to determining that the at least one of the first subset of image frames satisfy the one or more criteria, wherein the machine-readable object corresponds to either a one-dimensional or a two-dimensional spatial structure, and wherein the second set of image frames is received after the first subset of image frames;
detecting, using the one or more processing devices, a location of the machine-readable object in the at least one second image frame of the second set of image frames in response to analyzing the image data in the at least one second image frame of the second set of image frames;
and
tracking, after the detection of the location of the machine-readable object in the at least one second image frame and using the one or more processing devices, the location of the machine-readable object in a third set of successively captured image frames captured after the second set of image frames based, at least in part on one or more frame-to-frame translation metrics;
determining a signature based, at least in part, on image data for a third image frame of the third set of image frames that corresponds to the detected location of the machine-readable object in the at least one second image frame;
aligning the signature with one or more models;
identifying one of the one or more models that is best aligned with the signature.

6 more elements

A system, comprising:

an image capture component;
a memory;
and
one or more processors operatively coupled to the memory and the image capture component and configured to execute program code stored in the memory to cause the one or more processors to:
receive a set of image frames captured by the image capture component;
analyze a first subset of image frames in the set of image frames;
determine that at least one of the first subset of image frames satisfies one or more criteria;
analyze, in response to the determination, image data in at least one second image frame in a second set of image frames to detect a machine-readable object that corresponds to either a one-dimensional or a two-dimensional spatial structure, wherein the second set of image frames is captured after the first set of image frames;
monitor, coincident to the detecting, the second set of image frames for a change in the one or more criteria;
and
identify a location of the machine-readable object in at least one third image frame in a third set of successively captured image frames based, at least in part, on a detected location of the machine-readable object in at least one second image frame and on a translation metric between the at least one second image frame and the third set of image frame;
determine a signature based, at least in part, on image data for the at least one third image frame;
align the signature with one or more models;
align one of the one or more models that is aligned with the signature.

11 more elements

Dependencies are inferred from the claim text.

Facts

Application: 13/911,983Filed 6 Jun 2013
Published: US 2014/0363044 A111 Dec 2014
Granted: 10 Jan 2017
Term ends: Not estimatedThe source records don’t support an estimate.

Classification10 codes

G06K 7/1443
Including a method step for retrieval of the optical code: locating of the code in an image
G06K 7/10722
Fixed beam scanning: photodetector array or CCD scanning
G06V 10/25
Image preprocessing: determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/7515
Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching: shifting the…