Method, apparatus and terminal device for constructing map

1. A method for constructing a map, comprising:

building a point cloud data frame sequence using point cloud data frames acquired in real time, the point cloud data frame sequence including a plurality of point cloud data frames arranged in an order of acquisition time, adjacent point cloud data frames being generated after a set time, the point cloud data frames including point cloud data arranged in a matrix, the point cloud data including three-dimensional coordinates of a spatial position for marking an object in a surrounding environment of an unmanned vehicle;

extracting morphological data from the point cloud data frames, the morphological data used for characterizing a morphological feature of a surface of the object and a morphological feature of a line of the object, including surface point cloud data corresponding to the surface of the object and/or line point cloud data corresponding to the line of the object;

establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence, the spatial position relation being indicative of motion of the unmanned vehicle; and

determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation, and constructing a map of the surrounding environment based on the reference spatial position relation.

2. The method according to claim 1 , wherein the extracting morphological data from the point cloud data frames comprises:

determining a plurality of vectors between each point cloud data and an adjacent point cloud data in the point cloud data frames; and

assigning, when a vector satisfies a distance threshold condition and an angle threshold condition, two point cloud data corresponding to the vector as the morphological data.

3. The method according to claim 1 , wherein the establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence comprises:

determining two sets of morphological data corresponding to a given object in the two adjacent point cloud data frames; and

calculating a distance and an angle between the two sets of morphological data to obtain the spatial position relation.

4. The method according to claim 1 , wherein the determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation comprises:

counting a velocity of each object in two adjacent point cloud data frames to obtain a velocity profile, the velocity being determined by the spatial position relation and the set time; and

determining an object corresponding to a velocity having a largest ratio from the velocity profile as a stationary object, and determining a spatial position relation of the stationary object as the reference spatial position relation.

5. The method according to claim 1 , wherein the constructing a map with the reference spatial position relation comprises:

plotting the stationary object in the world coordinate system based on morphological data corresponding to the reference spatial position relation to obtain a map corresponding to the point cloud data frame sequence.

6. An apparatus for constructing a map, comprising:

at least one processor; and

a memory storing instructions, which when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:

building a point cloud data frame sequence using point cloud data frames acquired in real time, the point cloud data frame sequence including a plurality of point cloud data frames arranged in an order of acquisition time, adjacent point cloud data frames being generated after a set time, the point cloud data frames including point cloud data arranged in a matrix, the point cloud data including three-dimensional coordinates of a spatial position for marking an object in a surrounding environment of an unmanned vehicle;

extracting morphological data from the point cloud data frames, the morphological data used for characterizing a morphological feature of a surface of the object and a morphological feature of a line of the object, including surface point cloud data corresponding to the surface of the object and/or line point cloud data corresponding to the line of the object;

establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence, the spatial position relation being indicative of motion of the unmanned vehicle; and

determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation, and constructing a map of the surrounding environment based on the reference spatial position relation.

7. The apparatus according to claim 6 , wherein the extracting morphological data from the point cloud data frames comprises:

determining a plurality of vectors between each point cloud data and an adjacent point cloud data in the point cloud data frames; and

assigning, when a vector satisfies a distance threshold condition and an angle threshold condition, two point cloud data corresponding to the vector as the morphological data.

8. The apparatus according to claim 6 , wherein the establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence comprises:

determining two sets of morphological data corresponding to a given object in the two adjacent point cloud data frames; and

calculating a distance and an angle between the two sets of morphological data to obtain the spatial position relation.

9. The apparatus according to claim 6 , wherein the determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation comprises:

counting a velocity of each object in the two adjacent point cloud data frames to obtain a velocity profile, the velocity being determined by the spatial position relation and the set time; and

determining an object corresponding to a velocity having a largest ratio from the velocity profile as a stationary object, and determining a spatial position relation of the stationary object as the reference spatial position relation.

10. The apparatus according to claim 6 , wherein the constructing a map with the reference spatial position relation comprises:

plotting the stationary object in the world coordinate system based on morphological data corresponding to the reference spatial position relation to obtain a map corresponding to the point cloud data frame sequence.

11. A non-transitory computer readable storage medium storing a computer program, which when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:

building a point cloud data frame sequence using point cloud data frames acquired in real time, the point cloud data frame sequence including a plurality of point cloud data frames arranged in an order of acquisition time, adjacent point cloud data frames being generated after a set time, the point cloud data frames including point cloud data arranged in a matrix, the point cloud data including three-dimensional coordinates of a spatial position for marking an object in a surrounding environment of an unmanned vehicle;

extracting morphological data from the point cloud data frames, the morphological data used for characterizing a morphological feature of a surface of the object and a morphological feature of a line of the object, including surface point cloud data corresponding to the surface of the object and/or line point cloud data corresponding to the line of the object;

establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence, the spatial position relation being indicative of motion of the unmanned vehicle; and

determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation, and constructing a map of the surrounding environment based on the reference spatial position relation.

12. The non-transitory computer readable storage medium according to claim 11 , wherein the extracting morphological data from the point cloud data frames comprises:

determining a plurality of vectors between each point cloud data and an adjacent point cloud data in the point cloud data frames; and

assigning, when a vector satisfies a distance threshold condition and an angle threshold condition, two point cloud data corresponding to the vector as the morphological data.

13. The non-transitory computer readable storage medium according to claim 11 , wherein the establishing a spatial position relation between morphological data of two adjacent point cloud data frames in the point cloud data frame sequence comprises:

determining two sets of morphological data corresponding to a given object in the two adjacent point cloud data frames; and

calculating a distance and an angle between the two sets of morphological data to obtain the spatial position relation.

14. The non-transitory computer readable storage medium according to claim 11 , wherein the determining a reference spatial position relation corresponding to a stationary object based on the spatial position relation comprises:

counting a velocity of each object in two adjacent point cloud data frames to obtain a velocity profile, the velocity being determined by the spatial position relation and the set time; and

determining an object corresponding to a velocity having a largest ratio from the velocity profile as a stationary object, and determining a spatial position relation of the stationary object as the reference spatial position relation.

15. The non-transitory computer readable storage medium according to claim 11 , wherein the constructing a map with the reference spatial position relation comprises:

plotting the stationary object in the world coordinate system based on morphological data corresponding to the reference spatial position relation to obtain a map corresponding to the point cloud data frame sequence.