Apparatus for controlling vehicle and method thereof

1 . An apparatus for controlling a vehicle, the apparatus comprising:

a sensor; and

a processor,

wherein the processor is configured to:

generate, based on obtaining a virtual box corresponding to an object at a first time point through the sensor, a tracking box by converting the virtual box to a virtual box at a second time point after the first time point;

determine virtual boxes associated with the tracking box among a plurality of virtual boxes at the second time point, based on obtaining the plurality of virtual boxes at the second time point formed by a plurality of points obtained at the second time point through the sensor;

determine that the object is unobstructed;

determine a stationary state or a moving state of the object, based on:

a type of the object being determined as:

a first type including a pedestrian, or

a third type different from a second type including a specialty vehicle, and

a number of the plurality of virtual boxes at the second time point being smaller than a specified number;

selectively merge all or part of the determined virtual boxes based on at least one of:

a distance between the plurality of virtual boxes at the second time point,

whether the plurality of virtual boxes at the second time point are located outside a road edge, or

a type of the plurality of virtual boxes at the second time point; and

output a signal indicating the selectively merged virtual boxes.

2 . The apparatus of claim 1 , wherein the processor is configured to:

determine the virtual boxes associated with the tracking box among the plurality of virtual boxes at the second time point further based on:

the tracking box overlapping each of the plurality of virtual boxes at the second time point by a specified ratio or more, or

a distance between a plurality of first points included in the tracking box and a plurality of second points included in the plurality of virtual boxes at the second time point being within a correlation distance.

3 . The apparatus of claim 1 , wherein the processor is configured to:

determine that the object is in the stationary state;

determine that at least one of a width or a length of the tracking box is greater than or equal to a first reference length;

determine a first straight line perpendicular to a line segment forming a first virtual box from a first center point of the first virtual box among the plurality of virtual boxes at the second time point, based on the object being in the stationary state and at least one of the width or the length of the tracking box being greater than or equal to the first reference length; and

selectively skip merging at least a portion of the determined virtual boxes based on a distance between the first straight line and a second center point of a second virtual box among the plurality of virtual boxes at the second time point being greater than or equal to a second reference length.

4 . The apparatus of claim 1 , wherein the processor is configured to:

determine that a road, on which the vehicle including the apparatus is driving, is a straight line road;

determine that the object is in the stationary state; and

determine all or part of the determined virtual boxes within a first specified distance in a direction perpendicular to a front of the vehicle.

5 . The apparatus of claim 4 , wherein the processor is configured to:

determine a first region including the road and the road edge;

determine a second region different from the first region including the road and the road edge; and

selectively skip merging all or part of the determined virtual boxes, which are detected in the second region, from among all or part of the determined virtual boxes detected within the first specified distance.

6 . The apparatus of claim 1 , wherein the processor is configured to:

receive an entry signal indicating that a vehicle including the apparatus enters an enclosed space;

determine that the object is in the stationary state

determine that the determined virtual boxes are located within a second specified distance, in a direction perpendicular to the object;

determine that a length of each of the determined virtual boxes is greater than or equal to a reference length; and

selectively skip merging all or part of the determined virtual boxes based on determining that a number of points included in the determined virtual boxes is greater than or equal to a first reference number.

7 . The apparatus of claim 1 , wherein the processor is configured to:

determine that the object is in the stationary state

determine that a size of the tracking box is greater than or equal to a reference size;

determine that a number of points included in the tracking box is greater than or equal to a second reference number; and

selectively skip merging all or part of the determined virtual boxes based on a type of the determined virtual boxes being determined as a third type that is different from a first type associated with a pedestrian and different from a second type associated with a vehicle.

8 . The apparatus of claim 7 , wherein the processor is configured to:

determine the type of the determined virtual boxes based on density of points included in the determined virtual boxes.

9 . The apparatus of claim 8 , wherein the processor is configured to:

determine that the type of the determined virtual boxes is the third type, based on the density of the points being greater than or equal to reference density.

10 . A method for controlling a vehicle, the method comprising:

generating, by an apparatus and based on obtaining a virtual box corresponding to an object at a first time point through a sensor, a tracking box by converting the virtual box to a virtual box at a second time point after the first time point;

determining virtual boxes associated with the tracking box among a plurality of virtual boxes at the second time point, based on obtaining the plurality of virtual boxes at the second time point formed by a plurality of points obtained at the second time point through the sensor;

determining that the object is unobstructed;

determining a stationary state or a moving state of the object, based on:

a type of the object being determined as:

a first type including a pedestrian, or

a third type different from a second type including a specialty vehicle, and

a number of the plurality of virtual boxes at the second time point being smaller than a specified number;

selectively merging all or part of the determined virtual boxes based on at least one of:

a distance between the plurality of virtual boxes at the second time point,

whether the plurality of virtual boxes at the second time point are located outside a road edge, or

a type of the plurality of virtual boxes at the second time point; and

outputting a signal indicating the selectively merged virtual boxes.

11 . The method of claim 10 , wherein the determining the virtual boxes associated with the tracking box among the plurality of virtual boxes at the second time point is further based on:

the tracking box overlapping each of the plurality of virtual boxes at the second time point by a specified ratio or more, or

a distance between a plurality of first points included in the tracking box and a plurality of second points included in the plurality of virtual boxes at the second time point being within a correlation distance.

12 . The method of claim 11 , further comprising:

determining that the object is in the stationary state;

determining that at least one of a width or a length of the tracking box is greater than or equal to a first reference length;

determining a first straight line perpendicular to a line segment forming a first virtual box from a first center point of the first virtual box among the plurality of virtual boxes at the second time point, based on the object being in the stationary state and at least one of the width or the length of the tracking box being greater than or equal to the first reference length; and

selectively skip merging at least a portion of the determined virtual boxes based on a distance between the first straight line and a second center point of a second virtual box among the plurality of virtual boxes at the second time point being greater than or equal to a second reference length.

13 . The method of claim 10 , further comprising:

determining that a road, on which the vehicle including the apparatus is driving, is a straight line road;

determining that the object is in the stationary state; and

determining all or part of the determined virtual boxes within a first specified distance in a direction perpendicular to a front of the vehicle.

14 . The method of claim 13 , further comprising:

determining a first region including the road and the road edge;

determining a second region different from the first region including the road and the road edge; and

selectively skip merging all or part of the determined virtual boxes, which are detected in the second region, from among all or part of the determined virtual boxes detected within the first specified distance.

15 . The method of claim 10 , further comprising:

receiving an entry signal indicating that a vehicle enters an enclosed space;

determining that the object is in the stationary state;

determining that the determined virtual boxes are located within a second specified distance, in a direction perpendicular to the object;

determining that a length of each of the determined virtual boxes is greater than or equal to a reference length; and

selectively skip merging all or part of the determined virtual boxes based on determining that a number of points included in the determined virtual boxes is greater than or equal to a first reference number.

16 . The method of claim 10 , further comprising:

determining that the object is in the stationary state;

determining that a size of the tracking box is greater than or equal to a reference size;

determining that a number of points included in the tracking box is greater than or equal to a second reference number; and

selectively skip merging all or part of the determined virtual boxes based on a type of the determined virtual boxes being determined as a third type that is different from a first type associated with a pedestrian and different from a second type associated with a vehicle.

17 . The method of claim 16 , further comprising:

determining the type of the determined virtual boxes based on density of points included in the determined virtual boxes.

18 . The method of claim 17 , further comprising:

determining that the type of the determined virtual boxes is the third type, based on the density of the points being greater than or equal to reference density.

19 . The method of claim 10 , wherein the object that is unobstructed is identified at the first time point,

wherein the stationary state or the moving state is determined after the determining that the object is unobstructed, and

wherein the selectively merging all or part of the determined virtual boxes is further based on the determined stationary state or the determined moving state.

20 . The apparatus of claim 1 , wherein the object that is unobstructed is identified at the first time point,

wherein the stationary state or the moving state is determined after the determining that the object is unobstructed, and

wherein the processor is configured to selectively merge all or part of the determined virtual boxes further based on the determined stationary state or the determined moving state.