IP Library Granted Patent US 9,087,258
Granted Patent B2
US 9,087,258 · App. 13/816,304 · Granted Jul 21, 2015

Method for counting objects and apparatus using a plurality of sensors

Inventors: Jaeshin Yu (Uiwang, KR); Sungjin Kim (Anyang, KR)
Assignee: LG ELECTRONICS INC.
G06K9/3241G06K9/00201G06K9/00778G06T7/0083H04N7/181G06T2207/10028G06T2207/30242
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 9,087,258
App. No.
13/816,304
Granted
Jul 21, 2015
Kind
B2
Abstract

According to one embodiment of the present invention, a method for counting objects involves using an image sensor and a depth sensor, and comprises the steps of: acquiring an image from the image sensor and acquiring a depth map from the depth sensor, the depth map indicating depth information on the subject in the image; acquiring boundary information on objects in the image; applying the boundary information to the depth map to generate a corrected depth map; identifying the depth pattern of the objects from the corrected depth map; and counting the identified objects.

Claims (29)

1. A method for counting objects using an image sensor and a depth sensor, the method comprising:

acquiring an image by the image sensor, and acquiring a depth map from the depth sensor, the depth map indicating depth information on the subject in the image;

acquiring edge information of objects of interest in the image;

generating a corrected depth map by applying the edge information to the depth map;

extracting depth patterns of the objects of interest from the corrected depth map;

identifying at least one valid object among the objects of interest by comparing the extracted depth patterns and reference depth patterns stored in a database; and

counting the identified valid object,

wherein the step of extracting depth patterns of the objects of interest comprises:

selecting one of the objects of interest; and

extracting a depth pattern, based on projection information on virtual planes crossing the selected object, while moving toward a lower side of the selected object.

2. The method of claim 1 , wherein in the step of identifying at least one valid object, the reference depth patterns of a reference object stored in the database, is compared with the depth patterns of the corrected depth map.

3. The method of claim 1 , further comprising tracking movement of the identified valid object.

4. A camera apparatus, comprising:

an image sensor configured to generate an image captured with respect to objects of interest;

a depth sensor configured to generate a depth map indicating depth information on the subject in the image; and

a controller configured to acquire edge information of the objects of interest in the image, configured to generate a corrected depth map by applying the edge information to the depth map, configured to extract depth patterns of the objects of interest from the corrected depth map, configured to identify at least one valid object among the objects of interest by comparing the extracted depth patterns and reference depth patterns stored in a database, and configured to count the identified valid object,

wherein the controller is further configured to

select one of the objects of interest, and

extract a depth pattern, based on projection information on virtual planes crossing the selected object, while moving toward a lower side of the selected object.

5. The camera apparatus of claim 4 , further comprising a memory configured to store therein the database for storing reference depth patterns of a reference object at different angles,

wherein the controller identifies the valid object among the objects of interest, using the reference depth patterns of the reference object at different angles, from the corrected depth map.

6. An apparatus for counting objects, comprising:

a transceiver configured to receive an image captured with respect to objects of interest, and a depth map indicating depth information on the subject in the image; and

a controller configured to acquire edge information of the objects of interest in the image, configured to generate a corrected depth map by applying the edge information to the depth map, configured to extract depth patterns of the objects of interest from the corrected depth map, configured to identify at least one valid object among the objects of interest by comparing the extracted depth patterns and reference depth patterns stored in a database, and configured to count the identified valid object,

wherein the controller is further configured to

select one of the objects of interest, and

extract a depth pattern, based on projection information on virtual planes crossing the selected object, while moving toward a lower side of the selected object.

7. The apparatus of claim 6 , further comprising a memory configured to store therein the database for storing the reference depth patterns of a reference object at different angles,

wherein the controller identifies the valid object, using the reference depth patterns of the reference object at different angles, from the corrected depth map.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 11, 2013
From: YU, JAESHIN; KIM, SUNGJIN
To: LG ELECTRONICS INC.
Reel/Frame 029788/0345 →
Continuity (1)
Related Publication 20130136307A1 · May 30, 2013