IP Library Granted Patent US 12,456,311
Granted Patent B2
US 12,456,311 · App. 18/334,609 · Granted Oct 28, 2025

Method for determining a current status of a window

Inventors: Kamil Lelowicz (Bogunice, PL); Pawel Markiewicz (Cracow, PL)
Assignee: APTIV TECHNOLOGIES AG
G06V20/59B60J1/20
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 12,456,311
App. No.
18/334,609
Granted
Oct 28, 2025
Kind
B2
Abstract

A method is provided for determining a current status of a window of a vehicle. The vehicle comprises an optical sensor system configured to acquire at least one image of an interior of a vehicle cabin, wherein at least a part of the window is visible in the at least one image. According to the method, at least one characteristic of a pane of the window is determined from the at least one image, and the current status of the window is determined based on the at least one characteristic of the pane.

Claims (64)

1 . A computer implemented method for determining a current status of a window of a vehicle, the vehicle comprising an optical sensor system configured to acquire at least one image of an interior of a vehicle cabin, at least a part of the window visible in the at least one image, the method comprising:

determining, via a processing unit, at least one characteristic of a pane of the window from the at least one image, and

determining, via the processing unit, a current status of the window based on the at least one characteristic of the pane,

wherein determining the current status of the window includes based on the at least one characteristic of the pane further comprises: applying a machine learning algorithm to the at least one image, and

wherein:

the optical sensor system is configured to capture an image in the visible spectral range and an infrared image,

the current status of the window is determined by applying the machine learning algorithm to the image in the visible spectral range and to the infrared image,

determining the at least one characteristic of the pane further comprises monitoring at least a predefined portion of an upper edge of the pane with respect to a frame of the window,

monitoring at least the predefined portion of the upper edge of the pane further comprises determining a position of the predefined portion of the upper edge of the pane relative to a position of at least one of an upper part or a lower part of the frame,

a first straight line is adapted to the predefined portion of upper edge of the pane,

a second straight line is adapted to at least one of the upper part or the lower part of the frame, and

the position of the upper edge of the pane is determined with respect to at least one of the upper part or the lower part of the frame based on a respective offset and a respective slope of the first and second straight lines.

2 . A computer implemented method for determining a current status of a window of a vehicle, the vehicle comprising an optical sensor system configured to acquire at least one image of an interior of a vehicle cabin, at least a part of the window visible in the at least one image, the method comprising:

determining, via a processing unit, at least one characteristic of a pane of the window from the at least one image, and

determining, via the processing unit, a current status of the window based on the at least one characteristic of the pane,

wherein determining the at least one characteristic of the pane further comprises:

monitoring at least a predefined portion of an upper edge of the pane with respect to a frame of the window,

wherein monitoring at least the predefined portion of the upper edge of the pane further comprises:

determining a position of the predefined portion of the upper edge of the pane relative to a position of at least one of an upper part or a lower part of the frame, and

wherein:

a first straight line is adapted to the predefined portion of upper edge of the pane,

a second straight line is adapted to at least one of the upper part or the lower part of the frame, and

the position of the upper edge of the pane is determined with respect to at least one of the upper part or the lower part of the frame based on a respective offset and a respective slope of the first and second straight lines.

3 . The method according to claim 2 , wherein determining the at least one characteristic of the pane further comprises:

monitoring at least a predefined portion of an upper edge of the pane with respect to a frame of the window.

4 . The method according to claim 3 , wherein the current status is indicative of at least one of a closed state, a partly open state, or a fully open state of the window.

5 . The method according to claim 3 , wherein:

the at least one characteristic of the pane of the window includes a damage indicator which is determined based on the at least one image, and

the current status further includes a damage degree of the window which is determined based on the damage indicator.

6 . The method according to claim 3 , wherein:

a free space between an upper edge of the pane and an upper part of a frame of the window is monitored regarding a presence of a foreign object, the free space being a part of a predefined work area of the pane,

the at least one characteristic includes the presence of the foreign object in the predefined work area,

the current status further includes a flag for a violation of the predefined work area, and

the flag is set if the foreign object is present in the predefined work area.

7 . The method according to claim 3 , wherein:

the current status is indicative of at least one of a closed state, a partly open state, or a fully open state of the window,

the at least one characteristic of the pane of the window includes a damage indicator which is determined based on the at least one image,

the current status further includes a damage degree of the window which is determined based on the damage indicator,

a free space between an upper edge of the pane and an upper part of a frame of the window is monitored regarding a presence of a foreign object, the free space being a part of a predefined work area of the pane,

the at least one characteristic includes the presence of the foreign object in the predefined work area,

the current status further includes a flag for a violation of the predefined work area, and

the flag is set if the foreign object is present in the predefined work area.

8 . The method according to claim 3 , wherein monitoring at least the predefined portion of the upper edge of the pane further comprises:

determining a position of the predefined portion of the upper edge of the pane relative to a position of at least one of an upper part or a lower part of the frame.

9 . The method according to claim 2 , wherein the current status is indicative of at least one of a closed state, a partly open state, or a fully open state of the window.

10 . The method according to claim 9 , wherein the current status is further indicative of an opening degree of the window.

11 . The method according to claim 2 , wherein:

the at least one characteristic of the pane of the window includes a damage indicator which is determined based on the at least one image, and

the current status further includes a damage degree of the window which is determined based on the damage indicator.

12 . The method according to claim 11 , wherein:

the damage indicator includes at least one of a predefined trace or a predefined pattern which is associated with a damage of the pane, and

the image provided by the optical sensor system is analyzed by the processing unit in order to recognize the predefined trace or predefined pattern.

13 . The method according to claim 2 , wherein:

a free space between an upper edge of the pane and an upper part of a frame of the window is monitored regarding a presence of a foreign object, the free space being a part of a predefined work area of the pane,

the at least one characteristic includes the presence of the foreign object in the predefined work area,

the current status further includes a flag for a violation of the predefined work area, and

the flag is set if the foreign object is present in the predefined work area.

14 . The method according to claim 2 ,

wherein the current status of the window is transferred to at least one of:

a further system of the vehicle, or

a display being visible for a driver of the vehicle,

in order to at least one of:

issue a warning message based on the current status of the window, or

initiate a safety measure based on the current status of the window.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 11, 2024
From: APTIV MANUFACTURING MANAGEMENT SERVICES S.À R.L.
To: APTIV TECHNOLOGIES AG
Reel/Frame 066551/0219 →
MERGER Recorded Feb 11, 2024
From: APTIV TECHNOLOGIES (2) S.À R.L.
To: APTIV MANUFACTURING MANAGEMENT SERVICES S.À R.L.
Reel/Frame 066566/0173 →
ENTITY CONVERSION Recorded Feb 11, 2024
From: APTIV TECHNOLOGIES LIMITED
To: APTIV TECHNOLOGIES (2) S.À R.L.
Reel/Frame 066746/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 14, 2023
From: LELOWICZ, KAMIL; MARKIEWICZ, PAWEL
To: APTIV TECHNOLOGIES LIMITED
Reel/Frame 063950/0932 →
Priority Claims (1)
EP 22182321 · Jun 30, 2022 · regional
Continuity (1)
Related Publication 20240005675A1 · Jan 4, 2024
References Cited (16)
US 3971065A · Bayer · 1976 [cited by applicant]
US 11763478B1 · Yang · 2023 [cited by examiner]
US 20050074142A1 · Ertl · 2005 [cited by examiner]
US 20120026318A1 · Huelsen · 2012 [cited by examiner]
US 20180187472A1 · Ikeda · 2018 [cited by examiner]
US 20200387723A1 · Mazuir et al. · 2020 [cited by applicant]
US 20220101507A1 · Tournier · 2022 [cited by examiner]
US 20230057766A1 · Salter · 2023 [cited by examiner]
US 20230384116A1 · Beaurepaire · 2023 [cited by examiner]
EP 2207700 · 2011 [cited by applicant]
JP 2007186915 · 2007 [cited by applicant]
“Extended European Search Report”, EP Application No. 22182321.4, Jan. 31, 2023, 9 pages. [cited by applicant]
Bochkovskiy, et al., “YOLOv4: Optimal Speed and Accuracy of Object Detection”, Apr. 23, 2020, 17 pages. [cited by applicant]
Niklaus, et al., “3D Ken Burns Effect from a Single Image”, Sep. 12, 2019, 15 pages. [cited by applicant]
Wang, et al., “FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection”, Sep. 24, 2021, 10 pages. [cited by applicant]
Yan, et al., “Windows Open Status Detection for Boxcar in Railway Transportation Based on Computer Vision”, Dec. 2, 2017, pp. 91-94. [cited by applicant]