IP Library Granted Patent US 12705699
Granted Patent B2
US 12705699 · App. 18/663,422 · Granted Aug 11, 2026

Generating top view of vehicle with image harmonization based on camera orientation

Inventors: Mark Patrick Griffin (Troy, MI); David James Moylan (Troy, MI); Satya Syamala Rao Giddi (Troy, MI)
Assignee: Connaught Electronics Ltd.
G06T5/50G06T5/70H04N5/2624G06T2207/10024G06T2207/20021G06T2207/20212G06T2207/30252
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 12705699
App. No.
18/663,422
Granted
Aug 11, 2026
Kind
B2
Abstract

Methods and systems for generating a top view of an area surrounding the vehicle. Images are received from a plurality of vehicle cameras configured to view respective regions of ground outside of the vehicle. Portions of at least some of the regions overlap with portions of another of the regions, defining overlapping portions. Each image is segmented into a respective plurality of segments, wherein the overlapping portions include some of the segments of one image and some of the segments of another image to define overlapping segments. A first harmonization model harmonizes the images based on brightness or color values within the overlapping segments. When an angular orientation of at least one of the plurality of vehicle cameras relative to the ground exceeds a threshold, a second harmonization model is executed in order to account for occlusions or lack of image data when the camera is angled.

Claims (50)

1 . A method for generating a top view of an area surrounding a vehicle, the method comprising:

receiving images from a plurality of vehicle cameras, wherein each vehicle camera is configured to view a respective area of ground outside of the vehicle;

projecting the images into corresponding projected image areas, each projected image area representing a top view of a portion of a respective one of the images, wherein each projected image area has a plurality of regions, and wherein at least one of the regions of one of the projected image areas overlaps with another of the regions of another of the projected image areas to define overlapping portions;

segmenting each projected image area into a respective plurality of segments, wherein the overlapping portions include some of the segments of one projected image area and some of the segments of another projected image area to define overlapping segments;

executing a first harmonization model to harmonize the projected image areas based on brightness values or color values within the overlapping segments;

determining an angular orientation of at least one of the plurality of vehicle cameras relative to the ground; and

executing a second harmonization model to harmonize the projected image areas based on the brightness values or color values within the overlapping segments, wherein the executing of the second harmonization model is performed in response to a determination that the angular orientation of the at least one of the plurality of vehicles cameras exceeds a threshold.

2 . The method of claim 1 , wherein the executing of the second harmonization model includes:

selecting a group of the overlapping segments;

adjusting the brightness values or color values of the selected group of overlapping segments; and

harmonizing the projected image areas with the adjusted brightness values or color values.

3 . The method of claim 2 , wherein the adjusting the brightness values or color values of the selected group of overlapping segments causes the brightness values or color values of the selected overlapping segments to be identical to the brightness values or color values of another of the segments.

4 . The method of claim 3 , wherein the another of the segments is one of the overlapping segments not in the selected group.

5 . The method of claim 2 , wherein the adjusting the brightness values or color values of the selected overlapping segments includes removing the brightness values or color values of the selected overlapping segments.

6 . The method of claim 1 , wherein the determining the angular orientation is based on vehicle calibration data.

7 . The method of claim 1 , further comprising:

generating, for display, the top view based on the executing of the second harmonization model.

8 . A method for generating a top view of an area surrounding a vehicle, the method comprising:

receiving images from a plurality of vehicle cameras, wherein each vehicle camera is configured to view a respective area of ground outside of the vehicle;

projecting the images into corresponding projected image areas, each projected image area representing a top view of a portion of a respective one of the images, wherein each projected image area has a plurality of regions, and wherein at least one of the regions of one of the projected image areas overlaps with another of the regions of another of the projected image areas to define overlapping portions;

segmenting each projected image area into a respective plurality of segments, wherein the overlapping portions include some of the segments of one projected image area and some of the segments of another projected image area to define overlapping segments;

determining an angular orientation of at least one of the plurality of vehicle cameras relative to the ground; and

harmonizing the projected image areas by altering brightness values or color values within the overlapping segments to generate the top view of the area surrounding the vehicle, wherein the harmonizing is performed based on the determined angular orientation.

9 . The method of claim 8 , wherein the harmonizing includes:

altering the brightness values or color values within the overlapping segments according to a first harmonization model when the determined angular orientation is of a first angle, and

altering the brightness values or color values within the overlapping segments according to a second harmonization model when the determined angular orientation is of a second angle.

10 . The method of claim 9 , wherein the first angle is perpendicular with the ground, and wherein the second angle is not perpendicular with the ground.

11 . The method of claim 10 , wherein the second angle is greater than five degrees relative to a perpendicular direction to the ground.

12 . The method of claim 8 , wherein the harmonizing includes:

selecting a group of the overlapping segments; and

adjusting the brightness values or color values of the group of overlapping segments to be identical to the brightness values or color values of another of the segments.

13 . The method of claim 12 , wherein the another of the segments is one of the overlapping segments not in the selected group of overlapping segments.

14 . The method of claim 12 , wherein the adjusting includes removing the brightness values or color values of the group of overlapping segments.

15 . The method of claim 8 , wherein the determining the angular orientation is based on vehicle calibration data.

16 . A vehicle camera system for generating a top view of an area surrounding a vehicle, the system comprising:

a plurality of vehicle cameras, each vehicle camera configured to view a respective region of ground outside of the vehicle, wherein portions of at least some of the regions overlap with portions of another of the regions to define overlapping portions;

at least one processor coupled to the vehicle cameras and programmed to:

receive images generated by the vehicle cameras,

project the images into corresponding projected image areas, each projected image area representing a top view of a portion of a respective one of the images, wherein each projected image area has a plurality of regions, and wherein at least one of the regions of one of the projected image areas overlaps with another of the regions of another of the projected image areas to define overlapping portions,

segment each projected image area into a respective plurality of segments, wherein the overlapping portions include some of the segments of one projected image area and some of the segments of another projected image area to define overlapping segments,

execute a first harmonization model to harmonize the projected image areas based on brightness values or color values within the overlapping segments,

receive an angular orientation of at least one of the plurality of vehicle cameras relative to the ground, and

execute a second harmonization model to harmonize the projected image areas based on the brightness values or color values within the overlapping segments, wherein the execution of the second harmonization model is performed in response to a determination that the angular orientation of the at least one of the plurality of vehicles cameras exceeds a threshold.

17 . The system of claim 16 , wherein the at least one processor is further programmed to, during the execution of the second harmonization model:

select a group of the overlapping segments;

adjust the brightness values or color values of the selected overlapping segments; and

harmonize the images with the adjusted brightness values or color values.

18 . The system of claim 17 , wherein the adjusting of the brightness values or color values of the selected group of overlapping segments causes the brightness values or color values of the selected overlapping segments to be identical to the brightness values or color values of another of the segments.

19 . The system of claim 18 , wherein the another of the segments is one of the overlapping segments not in the selected group.

20 . The system of claim 16 , wherein the angular orientation of at least one of the plurality of vehicle cameras relative to the ground is received from vehicle calibration data.