Granted Patent B2

US 12,475,723 · App. 18/098,245 · Granted Nov 18, 2025

Inventors: Xuebing Zhang (Wuppertal, DE); Klaus Friedrichs (Dortmund, DE); Markus Buehren (Erkrath, DE)

Assignee: APTIV TECHNOLOGIES AG

G06V20/593G06T7/55G06T2207/10028G06T2207/30268

Abstract

Claims (36)

1 . Computer implemented method for detecting an occupancy of a seat;

the method comprising:

capturing, by means of an imaging device, a first image of a seat, the image comprising depth data;

determining, by means of a processing device, a first height profile along a first line in the first image from the depth data;

comparing, by means of the processing device, the first height profile in the first image with a first reference height profile taken along the same first line to determine whether the seat is occupied;

determining, by means of the processing device, a second height profile along a second line in the first image from the depth data; and

comparing, by means of the processing device, the second height profile in the first image with a second reference height profile taken along the same second line to determine whether the seat is occupied.

2 . Computer implemented method according to claim 1 , the method further comprising:

capturing, by means of an imaging device, a second image of the seat, the image comprising depth data;

determining, by means of the processing device, a first height profile along a first line in the second image from the depth data; and

comparing, by means of the processing device, the first height profile in the second image with the first height profile in the first image and/or the first reference height profile to determine whether the seat is occupied.

3 . Computer implemented method according to the previous claim 2 , the method further comprising:

averaging the first height profile along the first line in the first image with the first height profile along the first line in the second image to obtain a first average height profile; and

comparing the first average height profile with the first reference height profile to determine whether the seat is occupied.

4 . Computer implemented method according to claim 2 , the method further comprising:

determining, by means of the processing device, a second height profile along a second line in the second image from the depth data; and

comparing, by means of the processing device, the second height profile in the second image with the second height profile in the first image and/or the second reference height profile to determine whether the seat is occupied.

5 . Computer implemented method according to the previous claim 4 , the method further comprising:

averaging the second height profile along the second line in the first image with the second height profile along the second line in the second image to obtain a second average height profile; and

comparing the second average height profile with the second reference height profile to determine whether the seat is occupied.

6 . Computer implemented method according to claim 1 , wherein comparing the first height profile in the first image with a first reference height profile comprises comparing at least a first characteristic point along the first line in the first reference height profile with the same position along the first line in the first image to determine whether the seat is occupied.

7 . Computer implemented method according to the previous claim 6 , wherein comparing the first height profile in the first image with a first reference height profile further comprises comparing at least a second characteristic point along the first line in the first reference height profile with the same position along the first line in the first image to determine whether the seat is occupied.

8 . Computer implemented method according to claim 1 , wherein comparing the second height profile in the first image with a second reference height profile comprises comparing at least a first characteristic point along the second line in the second reference height profile with the same position along the second line in the first image to determine whether the seat is occupied.

9 . Computer implemented method according to the previous claim 8 , wherein comparing the second height profile in the first image with a second reference height profile further comprises comparing at least a second characteristic point along the second line in the second reference height profile with the same position along the second line in the first image to determine whether the seat is occupied.

10 . Computer implemented method according to claim 1 , wherein the comparing is performed by using a machine-learning algorithm.

11 . Computer implemented method according to claim 1 , the method further comprising:

classifying a type of an object occupying the seat based on the comparison.

12 . Computer system, the computer system being configured to carry out the computer implemented method of claim 1 .

13 . Non-transitory computer readable medium comprising instructions for carrying out the computer implemented method of claim 1 .

14 . Computer implemented method for detecting an occupancy of a seat; the method comprising:

capturing, by means of an imaging device, a first image of a seat, the image comprising depth data;

determining, by means of a processing device, a first height profile along a first line in the first image from the depth data;

comparing, by means of the processing device, the first height profile in the first image with a first reference height profile taken along the same first line to determine whether the seat is occupied;

capturing, by means of an imaging device, a second image of the seat, the image comprising depth data;

determining, by means of the processing device, a first height profile along a first line in the second image from the depth data; and

comparing, by means of the processing device, the first height profile in the second image with the first height profile in the first image and/or the first reference height profile to determine whether the seat is occupied.

Assignments (4)

Priority Claims (1)

Continuity (1)

References Cited (16)