CPC G06F 18/253 (2023.01) [G01S 7/417 (2013.01); G01S 13/867 (2013.01); G06F 18/211 (2023.01); G06N 20/00 (2019.01); G06V 20/593 (2022.01)] | 16 Claims |
1. A system for performing sensor fusion for efficient deep learning processing, comprising:
a computing device of a vehicle having a plurality of seating zones, programmed to
receive a camera image from an image sensor and a supplemental sensor data from one or more supplemental sensors, the camera image and the supplemental sensor data including imaging of a cabin of the vehicle;
determine regions of interest in the camera image based on one or more of the camera image or the supplemental sensor data, the regions of interest including areas of the camera image flagged for further image analysis, the determination including to utilize an unactivated region of interest locator to determine the regions of interest in the camera image according to the camera image, and to utilize an activated region of interest locator to determine the regions of interest in the camera image according to the supplemental sensor data;
utilize a machine-learning model to perform object detection on the regions of interest of the camera image to identify one or more objects in the camera image, including to perform feature extraction on the regions of interest determined using the unactivated region of interest locator and the activated region of interest locator; and
place the objects into the seating zones of the vehicle.
|