IP Library › Granted Patent US 11,846,725
Granted Patent B2
US 11,846,725 · App. 17/208,056 · Granted Dec 19, 2023

Radar apparatus and method for classifying object

Inventor: Jae Eun Lee (Seoul, KR)
Assignee: BITSENSING INC.
G01S7/417G01S13/867G01S13/931G05D1/0088G06F18/251G06V10/762G06V10/764G06V10/774G06V10/803G06V20/58G01S2013/93271
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 11,846,725
App. No.
17/208,056
Granted
Dec 19, 2023
Kind
B2
Abstract

A radar apparatus installed in a vehicle includes a transceiver that transmits a radar signal to an outside of the vehicle and receives a radar signal reflected from an object; a signal processing unit that processes the reflected radar signal to detect the object; a fusion data generation unit that generates fusion data based on radar data and camera data; and a classification unit that classifies the detected object using an artificial intelligence module trained based on the generated fusion data.

Claims (43)

1. A radar apparatus installed in a vehicle, comprising:

a transceiver that transmits a radar signal to an outside of the vehicle and receives a radar signal reflected from an object;

a signal processing unit that processes the reflected radar signal to detect the object;

a fusion data generation unit that projects camera data to a radar coordinate system and matches the camera data projected to the radar coordinate system and radar data to generate fusion data; and

a classification unit that classifies the detected object using an artificial intelligence module trained based on the generated fusion data,

wherein the radar data include data derived from the reflected radar signal, and

wherein the camera data include data derived from image data generated by a camera.

2. The radar apparatus of claim 1 ,

wherein the signal processing unit is further configured to:

perform a signal processing to the reflected radar signal to detect the object, and

recognize the object based on a detection result value of the object.

3. The radar apparatus of claim 2 ,

wherein the radar data include at least one of a fast Fourier transform value of the reflected radar signal, the detection result value of the object and a recognition result value of the object, and

the camera data include a detection result value of another object included in image data generated by the camera and a classification result value of said another object.

4. The radar apparatus of claim 3 ,

wherein the fusion data generation unit is further configured to match the camera data and

the radar data for each target to generate the fusion data.

5. The radar apparatus of claim 4 , further comprising:

a training unit that:

inputs the radar data into an artificial intelligence radar module of the radar apparatus to train the artificial intelligence radar module, and

inputs the image data into an artificial intelligence camera module of the camera to train the artificial intelligence camera module,

wherein the camera data are derived through the artificial intelligence camera module.

6. The radar apparatus of claim 5 ,

wherein the training unit is further configured to additionally input the fusion data into the artificial intelligence radar module and the artificial intelligence camera module to additionally train the artificial intelligence radar module and the artificial intelligence camera module.

7. The radar apparatus of claim 6 ,

wherein when a performance evaluation value of the artificial intelligence radar module exceeds a predetermined threshold value, the fusion data generation unit is further configured to generate the fusion data further based on a classification result value of the object derived through the artificial intelligence radar module.

8. The radar apparatus of claim 6 ,

wherein the classification unit is further configured to classify the detected object through the additionally trained artificial intelligence radar module.

9. The radar apparatus of claim 3 ,

wherein the radar signal is received while the vehicle is driving, and

the image data are generated while the vehicle equipped with the camera is driving.

10. The radar apparatus of claim 9 ,

wherein the fusion data generation unit is further configured to generate the fusion data by analyzing driving condition of the vehicle while the vehicle is driving and giving weightings to the camera data and the radar data based on the analyzed driving condition.

11. /The radar apparatus of claim 1 , further comprising:

an autonomous driving unit that performs autonomous driving of the vehicle based on a classification result value of the object.

12. A method for classifying an object by a radar apparatus installed in a vehicle, the method comprising:

transmitting a radar signal to an outside of the vehicle;

receiving a radar signal reflected from an object;

processing the reflected radar signal to detect the object;

matching the camera data projected to the radar coordinate system and radar data to generate fusion data based on the radar data and the camera data; and

classifying the detected object using an artificial intelligence module trained based on the generated fusion data,

wherein the radar data include data derived from the reflected radar signal, and

wherein the camera data include data derived from image data generated by a camera.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 22, 2021
From: LEE, JAE EUN
To: BITSENSING INC.
Reel/Frame 055667/0345 →
Priority Claims (2)
KR 10-2020-0038964 · Mar 31, 2020 · national
KR 10-2021-0035112 · Mar 18, 2021 · national
Continuity (1)
Related Publication 20210302564A1 · Sep 30, 2021