US 12,437,561 B2
Method and system for detecting a type of seat occupancy
Klaus Friedrichs, Dortmund (DE); Monika Heift, Schwelm (DE); Thomas Kurbiel, Essen (DE); Xuebing Zhang, Wuppertal (DE); Amil George, Erkrath (DE); and Markus Buehren, Erkrath (DE)
Assigned to Aptiv Technologies AG, Schaffhausen (CH)
Filed by Aptiv Technologies AG, Schaffhausen (CH)
Filed on Jan. 11, 2023, as Appl. No. 18/095,694.
Claims priority of application No. 22152751 (EP), filed on Jan. 21, 2022.
Prior Publication US 2023/0237814 A1, Jul. 27, 2023
Int. Cl. G06V 20/59 (2022.01); G06V 10/25 (2022.01); G06V 10/34 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/593 (2022.01) [G06V 10/25 (2022.01); G06V 10/34 (2022.01); G06V 10/82 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A computer implemented method for detecting a type of seat occupancy, the method comprising:
capturing, by means of an imaging device, an image of a seat, the image comprising depth data and intensity data;
performing, by means of a processor device, a classifier algorithm on the captured image to determine a level of seat occupancy;
if the determination indicates that the level of seat occupancy is above a predetermined threshold: processing, by means of the processor device, only the depth data with a convolutional neural network, to determine a type of occupancy; and
if the determination indicates that the level of seat occupancy is below the predetermined threshold: processing, by means of the processor device, only the intensity data with a convolutional neural network to determine the type of occupancy.