US 10,853,662 B2Granted

Object recognition device that determines overlapping states for a plurality of objects

AssigneeToshiba Tec Kabushiki Kaisha

InventorMasaaki Yasunaga

Life of this patent

Estimating the term…

Loading patent…

Abstract

An object recognition device according to an embodiment includes a camera that captures an image of an imaging area. A storage device stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object. A processor receives the captured image from the camera, and determines an object area in the captured image. The processor extracts feature information from the object area, and, based on the extracted feature information compared to the dictionary feature information, identifies each object included in the object area. The processor also extracts boundary information corresponding to each identified object included in the object area, and, based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determines an overlap state of each identified object in the object area.

Claims20

Dependent claims

An object recognition device comprising:

a table having a surface on which an object to be recognized is placed;
a camera configured to capture an image of an imaging area including an object position area, the camera being located at a position facing the surface of the table;
a memory that stores, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object;
and
a processor configured to:
receive the captured image from the camera,
determine an object area in the captured image,
extract feature information from the object area,
based on the extracted feature information compared to the dictionary feature information, identify each object included in the object area, and extract boundary information corresponding to each identified object included in the object area,
based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determine an overlap state of each identified object relative to additional objects in the object area, and
based on the determined overlap state of each identified object, determine whether two or more identified objects in the object area are portions of the same object.

8 more elements

An object recognition method comprising the steps of:

storing in a memory, for each of a plurality of registered objects, dictionary feature information for identifying the corresponding object and dictionary boundary information for identifying an actual boundary area of the corresponding object;
capturing, by a camera facing a table having a surface on which an object to be recognized is placed, an image of an imaging area including an object position area;
receiving the captured image from the camera;
determining an object area in the captured image,
extracting feature information from the object area;
based on the extracted feature information compared to the dictionary feature information, identifying each object included in the object area, and extracting boundary information corresponding to each identified object included in the object area;
based on the extracted boundary information compared to the dictionary boundary information with respect to each identified object, determining an overlap state of each identified object relative to additional objects in the object area, and
based on the determined overlap state of each identified object, determining whether two or more identified objects in the object area are portions of the same object.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/739,800Filed 10 Jan 2020 · continuation
Priority: JP 2016-22895125 Nov 2016
Published: US 2020/0151463 A114 May 2020
Granted: 1 Dec 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification21 codes

G06V 20/52
Context or environment of the image: surveillance or monitoring of activities, e.g. for recognising suspicious objects
G06Q 20/203
Point-of-sale [POS] network systems: inventory monitoring
G06Q 20/208
Point-of-sale [POS] network systems: input by product or record sensing, e.g. weighing or scanner processing
G06T 7/11
Segmentation; Edge detection: region-based segmentation

Family

Application15/816,579Parent of this continuation · filed 17 Nov 2017
US 2020/0151463 A1Pre-grant publication · published 14 May 2020
US 10,552,686 B2Parent of this continuation
US 2018/0150699 A1Published application
US 10,853,662 B2This patent

From the US filing history. Foreign family members aren’t listed.