Data driven dynamically reconfigured disparity map

Patent metadata

Field	Value
Publication number	US-11790665-B2
Application number	US-202117243617-A
Country	US
Kind code	B2
Filing date	Apr 29, 2021
Priority date	Apr 29, 2021
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

In some examples, a system may receive, from at least one camera of a vehicle, at least one image including a road. The system may further receive vehicle location information including an indication of a location of the vehicle. In addition, the system may receive at least one of historical information from a historical database, or road anomaly information, where the road anomaly information is determined from at least one of a road anomaly database or real-time road anomaly detection. Based on the at least one image, the indication of the location of the vehicle, and the at least one of the historical information or the road anomaly information, the system may generate at least one of a disparity map or a disparity image.

First claim

What is claimed:

1. A system comprising:
one or more processors configured by executable instructions to perform operations comprising:
receiving, by the one or more processors, from at least one camera of a vehicle, at least one image including a road;
receiving, by the one or more processors, vehicle location information including an indication of a location of the vehicle;
receiving, by the one or more processors, at least one of:
historical information from a historical database, or
road anomaly information, wherein the road anomaly information is determined from at least one of a road anomaly database or detected road anomaly information;

selecting, in the at least one image, at least one higher priority area and at least one lower priority area based at least in part on the at least one of the historical information or the road anomaly information;
at least one of:
making a bit depth for the at least one higher priority area higher than a bit depth for the at least one lower priority area; or
compressing the at least one lower priority area with a higher compression rate than the at least one higher priority area; and

generating, by the one or more processors, at least one of a disparity map or disparity image based on the at least one image, the indication of the location of the vehicle, and further based on the at least one higher priority area and the at least one lower priority area selected based at least in part on the at least one of the historical information or the road anomaly information.

2. The system as recited in claim 1 , the operations further comprising:
segmenting a prior image of a frame received prior to the at least one image into at least one higher priority area and a least one lower priority area based at least in part on:
at least one of a disparity map from the prior image or a disparity image from the prior image, and
an edge map of the prior image;

determining a histogram for the at least one higher priority area and the at least one lower priority area; and
determining a search range for searching the at least one image based at least in part on the histogram.

3. The system as recited in claim 1 , the operations further comprising:
determining disparity information for the at least one image by applying a first disparity resolution to the at least one higher priority area and a second, different disparity resolution to the at least one lower priority area.

4. The system as recited in claim 1 , the operations further comprising:
determining an adaptive window to use for block matching for determining disparity information for the at least one image,
wherein determining the adaptive window is based at least in part on comparing at least one of grayscale values or color values of pixels within the adaptive window with at the least one of grayscale values or color values, respectively, of neighboring pixels.

5. The system as recited in claim 1 , the operations further comprising:
performing recognition of one of more features in the at least one of the disparity map or disparity image to determine recognition information; and
sending at least one control signal based on the recognition information, the at least one control signal including at least one of:
an instruction for controlling a vehicle to cause the vehicle to accelerate or decelerate;
an instruction for controlling the vehicle to cause the vehicle to steer a wheel of the vehicle; or
an instruction to cause an alert to be presented.

6. A method comprising:
receiving, by one or more processors, from at least one camera of a vehicle, at least one image including a road;
receiving, by the one or more processors, vehicle location information including an indication of a location of the vehicle;
receiving, by the one or more processors, at least one of:
historical information from a historical database, or
road anomaly information, wherein the road anomaly information is determined from at least one of a road anomaly database or detected road anomaly information;

selecting, in the at least one image, at least one higher priority area and at least one lower priority area based at least in part on the at least one of the historical information or the road anomaly information;
at least one of:
making a bit depth for the at least one higher priority area higher than a bit depth for the at least one lower priority area; or
compressing the at least one lower priority area with a higher compression rate than the at least one higher priority area; and

generating, by the one or more processors, at least one of a disparity map or disparity image based on the at least one image, the indication of the location of the vehicle, and further based on the at least one higher priority area and the at least one lower priority area selected based at least in part on the at least one of the historical information or the road anomaly information.

7. The method as recited in claim 6 , further comprising:
segmenting a prior image of a frame received prior to the at least one image into at least one higher priority area and a least one lower priority area based at least in part on:
at least one of a disparity map from the prior image or a disparity image from the prior image, and
an edge map of the prior image;
determining a histogram for the at least one higher priority area and the at least one lower priority area; and
determining a search range for searching the at least one image based at least in part on the histogram.

8. The method as recited in claim 6 , further comprising:
determining disparity information for the at least one image by applying a first disparity resolution to the at least one higher priority area and a second, different disparity resolution to the at least one lower priority area.

9. The method as recited in claim 6 , further comprising:
determining an adaptive window to use for block matching for determining disparity information for the at least one image,
wherein determining the adaptive window is based at least in part on comparing at least one of grayscale values or color values of pixels within the adaptive window with at the least one of grayscale values or color values, respectively, of neighboring pixels.

10. The method as recited in claim 6 , wherein the historical information includes at least one of: current sensed operator monitoring information, past operator monitoring information, current vehicle lights activity, past vehicle lights activity, past steering wheel position information, current steering wheel position information, past traffic information, or current traffic information.

11. The method as recited in claim 6 , wherein the historical information includes at least one of: current sensed operator monitoring information, past operator monitoring information, current vehicle lights activity, past vehicle lights activity, past steering wheel position information, current steering wheel position information, past traffic information, or current traffic information.

12. The method as recited in claim 6 , further comprising:
performing recognition of one of more features in the at least one of the disparity map or disparity image to determine recognition information; and
sending at least one control signal based on the recognition information, the at least one control signal including at least one of:
an instruction for controlling a vehicle to cause the vehicle to accelerate or decelerate;
an instruction for controlling the vehicle to cause the vehicle to steer a wheel of the vehicle; or
an instruction to cause an alert to be presented.

13. One or more non-transitory comput

Assignees

• Hitachi Astemo Ltd

Inventors

• BANGALORE RAMAIAH Naveen Kumar
• Kundu Subrata Kumar

Classifications

• G06V20/584 Primary

  of vehicle lights or traffic lights · CPC title

• G05D1/0246

  using a video camera in combination with image processing means · CPC title

• G06F18/213

  Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title