IP Library Granted Patent US 12674873
Granted Patent B2
US 12674873 · App. 18/336,072 · Granted Jul 7, 2026

Object recognition device, object recognition method, and non-transitory program recording medium

Inventors: Hidetaka Okushiro (Yokohama, JP); Tatsuki Ishikawa (Yokohama, JP); Kumi Nakada (Yokohama, JP); Chisato Suzuki (Yokohama, JP)
Assignee: JVCKENWOOD Corporation
G01S7/487G01S17/08
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 12674873
App. No.
18/336,072
Granted
Jul 7, 2026
Kind
B2
Abstract

An object recognition device includes: a point cloud measurement unit configured to measure the positions of point clouds included in an object and the distance to each of the point clouds; a noise adding unit configured to add a noise around the measured point clouds according to the distance to each of the point clouds; a noise count memory unit configured to store the total number and position of noises added by the noise adding unit; and a recognition unit configured to recognize the object based on the point clouds and the noises added to the point clouds.

Claims (26)

1 . An object recognition device for recognizing an object, comprising:

a point cloud measurement unit configured to measure the positions of point clouds included in the object and the distance to each of the point clouds;

a noise adding unit configured to add a noise around the measured point clouds according to the distance to each of the point clouds;

a noise count memory unit configured to store the number of noises added by the noise adding unit for each position of the added noises; and

a recognition unit configured to recognize the object based on the point clouds and the noises added to the point clouds.

2 . The object recognition device according to claim 1 , wherein the number of noises added around the measured point clouds increases as the distance to each of the cloud groups decreases.

3 . The object recognition device according to claim 1 , wherein the variation in the distribution range of noises added around the measured point clouds increases as the distance to each of the cloud groups decreases.

4 . The object recognition device according to claim 1 , wherein

the noise count memory unit is configured to store the number of noises added by the noise adding unit for each point of the point clouds measured by the point cloud measurement unit, and

the number of noises for each position of the added noises is stored for each point in the point clouds.

5 . The object recognition device according to claim 1 , wherein

the point cloud measurement unit is configured to further measure the luminance of point clouds included in the target, and

the noise adding unit is configured to add a noise around the measured point clouds according to the distance to and luminance of each of the point clouds.

6 . The object recognition device according to claim 1 , wherein

the point cloud measurement unit is configured to further measure the color of point clouds included in the target, and

the noise adding unit is configured to add a noise around the measured point clouds according to the distance to and color of each of the point clouds.

7 . An object recognition method for recognizing an object, comprising:

measuring the positions of point clouds included in the object and the distance to each of the point clouds;

adding a noise around the measured point clouds according to the distance to each of the point clouds;

storing the number and position of added noises; and

recognizing the object based on the point clouds and the noises added to the point clouds.

8 . A non-transitory program recording medium comprising an object recognition program for recognizing an object, comprising computer-implemented modules including:

a point cloud measurement module that measures the positions of point clouds included in the object and the distance to each of the point clouds;

a noise adding module that adds a noise around the measured point clouds according to the distance to each of the point clouds;

a noise count memory module that stores the number and position of added noises; and

a recognition module that recognizes the object based on the point clouds and the noises added to the point clouds.