Method for managing driving and electronic device

A method for managing driving comprising:

• in response that a vehicle is in a driving state is detected, obtaining Red-Green-Blue (RGB) images of a scene in front of the vehicle;
• processing the RGB images based on a trained depth estimation model, and obtaining depth images corresponding to the RGB images;
• converting the depth images to three dimensional (3D) point cloud maps;
• determining 3D regions of interest of the vehicle from the 3D point cloud maps according to a size of the vehicle;
• converting the 3D regions of interest into two dimensional (2D) regions of interest according to internal parameters of a camera;
• determining whether the 2D regions of interest have obstacles;
• in response that the 2D regions of interest have obstacles, obtaining images of the 2D regions of interest, performing semantic segmentation processing on the images of the 2D regions of interest and obtaining a segmentation result, wherein the segmentation result includes object categories of the obstacles in the 2D regions of interest;
• determining whether the obstacles are target objects according to the segmentation result;
• in response that the segmentation result indicates that the obstacles are the target objects, controlling the vehicle to continue driving;
• in response that the segmentation result indicates that the obstacles are not the target objects, controlling the vehicle to issue an alarm.

An electronic device comprising:

• a processor;
• and
• a non-transitory storage medium coupled to the processor and configured to store a plurality of instructions, which cause the processor to:
• in response that detecting a vehicle is in a driving state, obtain Red-Green-Blue (RGB) images of a scene in front of the vehicle;
• process the RGB images based on a trained depth estimation model, and obtain depth images corresponding to the RGB images;
• convert the depth images to three dimensional (3D) point cloud maps;
• determine 3D regions of interest of the vehicle from the 3D point cloud maps according to a size of the vehicle;
• convert the 3D regions of interest into two dimensional (2D) regions of interest according to internal parameters of a camera;
• determine whether the 2D regions of interest have obstacles;
• in response that the 2D regions of interest have no obstacles, control the vehicle to continue driving;
• in response that the 2D regions of interest have the obstacles, control the vehicle to issue an alarm.