Object recognition apparatus and vehicle having the same

1 . An object recognition apparatus comprising:

a Lidar sensor; and

one or more processors, at least one of the one or more processors configured to:

recognize objects based on data received from the Lidar sensor;

obtain a minimum value and a maximum value among values of a ground height for each object based on the data;

generate a ground trend line using a multiple linear regression model for the minimum value of each object;

obtain a reference value of the ground height for each object based on the generated ground trend line; and

determine an actual value of the ground height for each object based on a difference between the minimum value, the maximum value, and the reference value of the ground height for each object.

2 . The apparatus according to claim 1 , wherein the at least one processor is configured to:

obtain an X-axis value and a Y-axis value for each object based on the data received from the Lidar sensor; and

obtain a Z map in which a Z-axis value corresponding to the X-axis value and the Y-axis value for each object is matched, wherein the Z-axis value represents the ground height.

3 . The apparatus according to claim 2 , further comprising a memory configured to store information on a height for a type for each object, wherein the at least one processor is configured to:

recognize a type, size, and yaw angle for each object based on the X-axis value and the Y-axis value for each object; and

obtain the height corresponding to the type for each object based on the information stored in the memory.

4 . The apparatus according to claim 3 , wherein, to determine the actual value of the ground height of a first object of the objects, the at least one processor is configured to:

obtain a first difference value between the maximum value and the minimum value of the ground height of the first object;

obtain a second difference value between the maximum value and the reference value of the ground height of the first object; and

determine the actual value of the ground height of the first object based on whether the obtained first difference value and the height of the first object are the same and whether the obtained second difference value and the height of the first object are the same.

5 . The apparatus according to claim 4 , wherein the at least one processor is configured to determine the actual value of the ground height of the first object as the minimum value of the ground height of the first object based on the first difference value and the height of the first object being the same and the second difference value and the height of the first object being the same.

6 . The apparatus according to claim 4 , wherein the at least one processor is configured to determine the actual value of the ground height of the first object as the minimum value of the ground height of the first object based on the first difference value and the height of the first object being the same and the second difference value and the height of the first object being different.

7 . The apparatus according to claim 4 , wherein the at least one processor is configured to determine the actual value of the ground height of the first object as the reference value of the ground height of the first object based on the first difference value and the height of the first object being different and the second difference value and the height of the first object being the same.

8 . The apparatus according to claim 7 , wherein the at least one processor is configured to subtract the height of the first object from the maximum value of the ground height of the first object and determine the subtracted value as the actual value of the ground height of the first object based on the first difference value and the height of the first object being different and the second difference value and the height of the first object being different.

9 . The apparatus according to claim 7 , wherein the at least one processor is configured to determine the actual value of the ground height of the first object as the minimum value of the ground height of the first object based on the first difference value and the height of the first object being different, the second difference value and the height of the first object being different, and the reference value and the minimum value of the ground height of the first object being the same.

10 . The apparatus according to claim 1 , wherein the at least one processor is configured to:

obtain a distance between the object and a vehicle for each object;

list the objects from a short distance to a long distance; and

generate the ground trend line using the multiple linear regression model for the minimum values based on the list of the objects.

11 . An object recognition apparatus comprising:

a Lidar sensor; and

one or more processors, at least one of the one or more processors configured to:

obtain X-axis values and Y-axis values of objects based on data received from the Lidar sensor;

recognize a type and a height of each object based on the X-axis values and the Y-axis values of the object;

obtain Z-axis values corresponding to the X-axis values and the Y-axis values of the object, respectively;

obtain a minimum value and a maximum value among the Z-axis values;

generate a ground trend line using a multiple linear regression model for the minimum values among the Z-axis values of the objects; and

obtain reference value using the generated ground trend line; and

determine an actual value of a ground height of each object based on the minimum value, the maximum value, the reference value, and the height of the object.

12 . The apparatus according to claim 11 , wherein, for each object, the at least one processor is configured to:

obtain a first difference value between the maximum value and the minimum value of the ground height;

obtain a second difference value between the maximum value and the reference value of the ground height; and

determine the actual value of the ground height as the minimum value of the ground height based on the first difference value and the height being the same and the second difference value and the height being the same.

13 . The apparatus according to claim 12 , wherein, for each object, the at least one processor is configured to determine the actual value of the ground height as the reference value of the ground height based on the first difference value and the height being different and the second difference value and the height being the same.

14 . The apparatus according to claim 12 , wherein, for each object, the at least one processor is configured to subtract the height from the maximum value and determine the subtracted value as the actual value of the ground height based on the first difference value and the height being different, the second difference value and the height being different, and the maximum value and the reference value being the same.

15 . The apparatus according to claim 12 , wherein, for each object, the at least one processor is configured to determine the actual value of the ground height as the minimum value of the ground height based on the first difference value and the height being different, the second difference value and the height being different, and the reference value and the minimum value of the ground height being the same.

16 . The apparatus according to claim 11 , wherein the at least one processor is configured to:

obtain a distance between the object and a vehicle for each object;

list the objects from a short distance to a long distance; and

generate the ground trend line using the multiple linear regression model for the minimum values based on the list of the objects.

17 . A vehicle comprising:

a vehicle body;

a camera mounted in or on the vehicle body;

a Lidar sensor mounted in or on the vehicle body;

an object recognition apparatus configured to:

obtain X-axis values and Y-axis values of an object based on data received from the Lidar sensor;

recognize a type and a height of the object based on the X-axis values and the Y-axis values of the object;

obtain Z-axis values corresponding to the X-axis values and the Y-axis values of the object, respectively;

obtain a minimum value and a maximum value among the Z-axis values;

determine an actual value of a ground height of the object based on the minimum value, the maximum value, a reference value, and the height of the object; and

generate a three-dimensional box for the object based on the determined actual value of the ground height of the object; and

a controller configured to control autonomous driving or collision warning based on image information obtained by the camera and the determined actual value of the ground height of the object,

wherein the object is provided in plural, and

wherein the object recognition apparatus is configured to:

generate a ground trend line using a multiple linear regression model for the maximum value among the Z-axis values of the objects; and

obtain the reference value using the generated ground trend line.

18 . The vehicle according to claim 17 , wherein the object recognition apparatus is configured to:

obtain a first difference value between the maximum value and the minimum value of the ground height of the object;

obtain a second difference value between the maximum value and the reference value of the ground height of the object; and

determine the actual value of the ground height of the object based on whether the first difference value and the height of the object are the same and whether the second difference value and the height of the object are the same.

19 . The vehicle according to claim 18 , wherein the object recognition apparatus is configured to:

determine the actual value of the ground height of the object as the reference value of the ground height of the object based on a determination that the first difference value and the height of the object are different and a determination that the second difference value and the height of the object are the same; and

subtract the height of the object from the maximum value and determine the subtracted value as the actual value of the ground height of the object based on a determination that the first difference value and the height of the object are different, a determination that the second difference value and the height of the object are different, and a determination that the maximum value and the reference value are the same.

20 . The vehicle according to claim 17 , wherein the object recognition apparatus is configured to:

obtain an X-axis value and a Y-axis value for each object based on the data received from the Lidar sensor; and

obtain a Z map in which a Z-axis value corresponding to the X-axis value and the Y-axis value for each object is matched, and wherein the Z-axis value represents the ground height of the object.