Object boundary detection for automotive radar imaging

• US 10,185,030 B2
• Filed: 08/31/2015
• Issued: 01/22/2019
• Est. Priority Date: 09/05/2014
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Stainvas Olshansky, Inna, Bilik, Igal, Bialer, Oded
• Primary Examiner(s): Windrich, Marcus E
• Application Number:
  US14/840,917
• Publication Number:
  US 20160124087A1
• Time in Patent Office: 1,240 Days
• Field of Search: 342 70- 72
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• CPC Class Codes: G01S 13/58 Velocity or trajectory determination systems; Sense-of-movement determination systems
• CPC Class Codes: G01S 13/60 wherein the transmitter and receiver are mounted on the moving object, e.g. for determining ground speed, drift angle, ground track G01S13/64 takes precedence
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 2013/9318 Controlling the steering
• CPC Class Codes: G01S 2013/93185 Controlling the brakes
• CPC Class Codes: G01S 2013/9319 Controlling the accelerator
• CPC Class Codes: G01S 7/411 Identification of targets based on measurements of radar reflectivity G01S7/415 takes precedence

Abstract

An automotive radar system includes a radar camera that captures a sequence of frames of radar images of a field of view of the radar. A boundary detector receives the radar data from the radar camera and detects object boundary data in the radar data. An image processor receives the radar data and the object boundary data and performs image analysis including image deblurring and generating response control signals based at least in part on the radar data and the object boundary data. Response equipment implements one or more response actions based on the response control signals. Object boundary detection includes performing pixel-level Doppler analysis to associate pixel velocities to pixels of the radar data and identifying discontinuities in the pixel velocities. Response equipment may include, for example, one or more of a navigation display, collision avoidance warning, automatic cruise control, automatic braking, and automatic steering.

Claims

1. A vehicle having a radar system comprising:

a radar configured to capture radar data comprising a sequence of frames of Doppler and image data and to form a sequence of radar images of a field of view of the radar from the image data, wherein the radar images include pixels having associated pixel velocities obtained from the Doppler data;

a boundary detector configured to receive the radar images from the radar, detect object boundary data in the radar images, wherein an object boundary in an image includes a pixel having a discontinuity indicated by a gradient of pixel velocities, and identify the discontinuity in the pixel velocity by computing a norm of a gradient of the pixel velocity;

an image processor configured to receive the radar images and the object boundary data, deblur the radar images by applying a filter to the radar images that imposes a sharpness constraint on the image that allows greater sharpness in areas of large norm and smaller sharpness in areas of small norm, and generate a response control signal based at least in part on the deblurred radar images; and

response equipment operative for implementing one or more response actions based on the response control signals.

2. The vehicle of claim 1, wherein the boundary detector is further configured to perform pixel-level Doppler analysis to associate pixel velocities to pixels of the radar image.

3. The vehicle of claim 1, wherein the boundary detector is further configured to detect object boundary data by identifying boundary continuities over sequences of frames of the radar data.

4. The vehicle of claim 1, wherein the boundary detector is further configured to receive vehicle velocity information and to utilize the vehicle velocity in detecting the object boundary data.

5. The vehicle of claim 1, wherein the image processor is further configured to utilize the object boundary data as an adaptive parameter in an image deblurring transfer function.

6. The vehicle of claim 5, wherein the image deblurring transfer function is in the form:

7. The vehicle of claim 1, wherein the radar camera is configured to operate in the frequency range of 77 GHz to 81 GHz.

8. The vehicle of claim 1, wherein:

the response equipment includes one or more of a navigation display, a collision avoidance warning, an automatic cruise control adjustment system, an automatic braking system, and an automatic steering system; and

the boundary detector determines the object boundary data and the image processor utilizes the object boundary data for image deblurring in real time to support effective response actions to objects identified in the radar data.

9. A radar system for a moving vehicle, comprising:

a radar configured to capture radar data comprising a sequence of frames of Doppler and image data and to form a sequence of radar images of a field of view of the radar from the image data, wherein the radar images include pixels having associated pixel velocities obtained from the Doppler data;

a boundary detector configured to receive the radar images from the radar, detect object boundary data in the radar images, wherein an object boundary in an image includes a pixel having a discontinuity indicated by a gradient of pixel velocities, and identify the discontinuity in the pixel velocity by computing a norm of a gradient of the pixel velocity; and

an image processor operative configured to receive the radar image and the object boundary data, deblur the radar image by applying a filter to the radar images that imposes a sharpness constraint on the image that allows greater sharpness in areas of large norm and smaller sharpness in areas of small norm, and generate a response control signal based at least in part on the deblurred radar images.

10. The radar system of claim 9, wherein the boundary detector is further configured to perform pixel-level Doppler analysis to associate pixel velocities to pixels of the radar data.

11. The radar system of claim 10, wherein the boundary detector is further configured to detect object boundary data by identifying discontinuities in the pixel velocities.

12. The radar system of claim 11, wherein the boundary detector is further configured to identify discontinuities in the pixel velocities by computing a gradient of the pixel velocities.

13. The radar system of claim 12, wherein the boundary detector is further configured to detect object boundary data by identifying boundary continuities over sequences of frames of the radar data.

14. The radar system of claim 9, wherein the image processor is further configured to utilize the object boundary data as an adaptive parameter in an image deblurring transfer function.

15. A method for controlling a vehicle, comprising:

capturing radar data comprising a sequence of frames of Doppler and image data and to form a sequence of radar images from the image data, wherein the radar images include pixels having associated pixel velocities obtained from the Doppler data;

detecting object boundary data in the radar images, the object boundary data including a pixel having a discontinuity in a gradient of the pixel velocities, by identifying the discontinuity in the pixel velocity by computing a norm of a gradient of the pixel velocity;

deblurring the radar images by applying a filter to the image that relaxes a smoothness property on the images at pixels representing the object boundary;

generating a response control signal based at least in part on the deblurred radar images; and

implementing one or more response actions at the vehicle based on the response control signal to control the vehicle.

16. The method of claim 15, wherein detecting object boundary data further comprises identifying boundary continuities over sequences of frames of the radar data.

17. The method of claim 15, further comprising implementing one or more response actions based on the response control signals including one or more of displaying radar images on a navigation display, activating a collision avoidance warning, activating an automatic cruise control adjustment system, activating an automatic braking system, and activating an automatic steering system.