Apparatus for controlling vehicle and method thereof

A method performed by an apparatus of a vehicle, the method comprising:

• obtaining, from a sensor, a plurality of points associated with surroundings of the vehicle;
• based on the plurality of points and a first neural network model, obtaining at least one of:
• a first virtual box for representing a target object in the surroundings of the vehicle, or
• a first class for indicating a type of the target object;
• based on the plurality of points and a second neural network model, obtaining at least one of:
• first partial points among the plurality of points, wherein the first partial points correspond to at least part of the target object, or
• a second class identified based on the first partial points, and wherein the second class indicates the type of the target object;
• based on at least one of the first virtual box, the first class, the first partial points, or the second class, outputting a signal indicating a bounding box, wherein the bounding box corresponds to the target object;
• and
• controlling, based on the signal, autonomous driving of the vehicle.

A vehicle comprising:

• a sensor configured to obtain point cloud data representing surroundings of the vehicle;
• a memory configured to store a first neural network model and a second neural network model;
• a driving control circuit configured to control autonomous driving of the vehicle;
• and
• a processor circuit configured to cause the vehicle to:
• obtain, based on the point cloud data and the first neural network model, a first virtual box and a first class, wherein the first virtual box and the first class are associated with a target object,
• obtain, based on the point cloud data and the second neural network model, first partial points and a second class, wherein the first partial points and the second class are associated with the target object, and wherein the first partial points correspond to at least part of the target object,
• generate a bounding box representing the target object based on at least one of the first virtual box, the first class, the first partial points, or the second class,
• track the bounding box across a plurality of frames of the point cloud data,
• calibrate the point cloud data based on the tracked bounding box and update the bounding box based on the calibrated point cloud data,
• output a signal indicating the updated bounding box, and
• control, via the driving control circuit and based on the signal, autonomous driving of the vehicle.