Method and system for object detection

Patent metadata

Field	Value
Publication number	US-12372636-B2
Application number	US-202016911605-A
Country	US
Kind code	B2
Filing date	Jun 25, 2020
Priority date	Jul 17, 2019
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

A computer implemented method for detecting objects includes providing signal representation data comprising range information, velocity information and angular information; for each of a plurality of spatial scales, determining respective scaled data for the respective spatial scale based on the signal representation data, to obtain a plurality of scaled data; providing the plurality of scaled data to a plurality of detectors; and each detector carrying out object detection based on at least one of the plurality of scaled data.

First claim

We claim:

1. A computer implemented method for object detection, the method comprising:
receiving signal representation data comprising range information, velocity information, and angular information;
for each of a plurality of spatial scales, determining respective scaled data for the respective spatial scale, based on the signal representation data, to obtain a plurality of scaled data;
providing the plurality of scaled data to a plurality of detectors; and
carrying out, with each detector of the plurality of detectors, object detection based on at least one of the plurality of scaled data in a respective predetermined spatial region assigned to the respective detector;
wherein the respective predetermined spatial regions of the plurality of detectors overlap and have different sizes;
wherein each detector of the plurality of detectors is tuned to a respective particular region of space; and
wherein all of the detectors of the plurality of detectors share a common input and preprocessing chain.

2. The computer implemented method of claim 1 , wherein the signal representation data is based on at least one of radar signals or ultrasonic signals.

3. The computer implemented method of claim 1 , wherein the signal representation data comprises frequency-domain radar data.

4. The computer implemented method of claim 1 , wherein the signal representation data is based on signals received by an array of antennas.

5. The computer implemented method of claim 1 , wherein the signal representation data is determined as dense data based on sparse input data based on a transformation preserving a spatial order of the sparse input data.

6. The computer implemented method of claim 1 , wherein the plurality of spatial scales are provided in a hierarchy from fine spatial resolution to coarse spatial resolution.

7. The computer implemented method of claim 1 , wherein the plurality of spatial scales are related to the range information of the signal representation data.

8. The computer implemented method of claim 1 , wherein the respective pre-determined spatial regions of the plurality of detectors are provided across a predetermined range in polar angle coordinates.

9. The computer implemented method of claim 1 , wherein each detector of the plurality of detectors provides a respective confidence of the object detection.

10. The computer implemented method of claim 1 , wherein each detector of the plurality of detectors, upon detecting an object, predicts a property of the detected object.

11. The computer implemented method of claim 10 , wherein the property of the detected object comprises at least one of a location of the detected object, a size of the detected object, an orientation of the detected object, a velocity of the detected object, a shape of the detected objects, or a class of the detected object.

12. The computer implemented method of claim 1 , further comprising using a neural network that is trained based on labeled data comprising reference object information and data based on which reference signal representation data is obtainable.

13. A computer system comprising a plurality of computer hardware components configured to carry out the method of claim 1 .

14. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause the at least one processor to perform the computer implemented method of claim 1 .

Assignees

• Aptiv Technologies AG

Inventors

• Zhu Weimeng
• Su Yu
• Cremer Peet
• Maoz Ori
• Lessmann Stephanie
• Kossaczký Igor
• Dehkordi Saeid Khalili
• Labusch Sven

Classifications

• G01S13/589

  measuring the velocity vector · CPC title

• G01S13/4445

  amplitude comparisons monopulse, i.e. comparing the echo signals received by an antenna arrangement with overlapping squinted beams · CPC title

• G01S13/931

  of land vehicles · CPC title

• G01S13/64

  Velocity measuring systems using range gates · CPC title

• G01S13/584

  adapted for simultaneous range and velocity measurements · CPC title