# US 2021/0279523 A1 · Apparatus for clarifying object based on deep learning and method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279523 A1
- Document ID: US20210279523A1
- Status: Published application
- Kind: A1
- Application number: 17/014,135
- Filed: 2020-09-08
- Published: 2021-09-09
- Earliest claimed: 2020-03-03
- Assignees: Hyundai Motor Company; Kia Motors Corporation
- Applicants: Hyundai Motor Company; Kia Motors Corporation
- Inventors: So Jin JANG
- Web page: https://patentgrep.com/patent/US20210279523A1

## CPC

- G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06F 18/2148: {characterised by the process organisation or structure, e.g. boosting cascade}
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/23: Clustering techniques
- G06F 18/2431: Multiple classes
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 10/764: using classification, e.g. of video objects
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An apparatus for classifying an object based on deep learning includes: a first deep learning device that performs deep learning for objects of a first class; a second deep learning device that performs deep learning for objects of a second class; and a controller that classifies objects on a road into the first class or the second class, classifies the objects classified into the first class for each type based on a learning result of the first deep learning device, and classifies objects classified into the second class based on a learning result of the second deep learning device.

## Claims

### Claim 1

An apparatus for classifying an object based on deep learning, the apparatus comprising:
a first deep learning device configured to perform deep learning for objects of a first class;
a second deep learning device configured to perform deep learning for objects of a second class; and
a controller configured to:
classify objects on a road into the first class or the second class,
classify the objects classified into the first class for each type based on a learning result of the first deep learning device, and
classify the objects classified into the second class based on a learning result of the second deep learning device.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the controller classifies the objects on the road into the first class or the second class based on a ratio of width to length of each of the objects.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the controller classifies objects, each of which has a ratio of width to length greater than a reference value, into the first class, and classifies objects, each of which has a ratio of width to length less than or equal to the reference value, into the second class.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the controller classifies each of the objects into one of a car, a goods vehicle, a two-wheeled vehicle, or a pedestrian.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein each of the objects has a square pillar shape in which Light Detection And Ranging (LiDAR) points are clustered.

### Claim 6

A method for classifying an object based on deep learning, the method comprising:
performing, by a first deep learning device, deep learning for objects of a first class;
performing, by a second deep learning device, deep learning for objects of a second class;
classifying, by a controller, objects on a road into the first class or the second class;
classifying, by the controller, the objects classified into the first class for each type based on a learning result of the first deep learning device; and
classifying, by the controller, the objects classified into the second class for each type based on a learning result of the second deep learning device.

### Claim 7 (depends on 6)

The method of claim 6, wherein the classifying objects on a road into the first class or the second class includes classifying the objects based on a ratio of width to length of each of the objects.

### Claim 8 (depends on 6)

The method of claim 6, wherein the classifying objects on a road into the first class or the second class includes:
classifying objects, each of which has the ratio of width to length greater than a reference value, into the first class; and
classifying objects, each of which has the ratio of width to length less than or equal to the reference value, into the second class.

### Claim 9 (depends on 6)

The method of claim 6, wherein the objects on the road include at least one of a car, a goods vehicle, a two-wheeled vehicle, or a pedestrian.

### Claim 10 (depends on 6)

The method of claim 6, wherein each of the objects on the road has a square pillar shape in which Light Detection And Ranging (LiDAR) points are clustered.

### Claim 11

An apparatus for classifying an object based on deep learning, the apparatus comprising:
a first deep learning device configured to perform deep learning for objects, each of which has a ratio of width to length greater than a reference value;
a second deep learning device configured to perform deep learning for objects, each of which has a ratio of width to length less than or equal to the reference value; and
a controller configured to:
calculate a ratio of width to length of each of objects located on a road,
classify the objects based on a learning result of the first deep learning device when the calculated ratio of width to length is greater than the reference value, and
classify the objects based on a learning result of the second deep learning device when the calculated ratio of width to length is less than or equal to the reference value.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the controller classifies each of the objects as one of a car, a goods vehicle, a two-wheeled vehicle, or a pedestrian.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein each of the objects has a square pillar shape in which Light Detection And Ranging (LiDAR) points are clustered.
