Three-dimensional object detection method and device and readable storage medium

1 . A three-dimensional (3D) object detection method comprising:

determining first plane coordinates of multiple landing points of a first object based on a projection frame of the 3D first object in a to-be-detected image, the to-be-detected image being captured by an image acquisition device;

obtaining first world coordinate information based on a world coordinate system established based on position information and size information of the first object, the first world coordinate information including first world coordinates of the multiple landing points of the first object and first world coordinates of multiple vertices of the first object, the size information being obtained based on image characteristics of the first object;

using coordinate conversion processing to obtain external parameter information that converts the world coordinates of the first object into camera coordinate based on the first plane coordinates, the first world coordinates of the multiple landing points of the first object, and the internal parameter information of the image acquisition device, the external parameter information being used to obtain first camera coordinate information of the first object based on the first world coordinate information;

using the coordinate conversion processing to obtain second world coordinates of multiple landing points of a second object in the world coordinate system of the first object based on the external parameter information, the internal parameter information, and second plane coordinates of multiple landing points of the second object in the to-be-detected image; and

using the coordinate conversion processing to determine a height of the second object based on the second plane coordinates of a vertex of the second object and the second world coordinates of the multiple landing points, wherein:

the size information of the second object is unknown, a distance between the second object and the first object is less than a distance threshold, and the height of the second object is used to determine the second world coordinates of multiple vertices of the second object.

2 . The method of claim 1 further comprising:

using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object.

3 . The method of claim 2 , wherein using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object includes:

determining second world coordinate system information of the second object based on the second world coordinates of the multiple landing points and the height of the second object; and

using the external parameter information to determine the second camera coordinate information of the second object based on the second world coordinate system information.

4 . The method of claim 1 , wherein using the coordinate conversion processing to determine the height of the second object based on the second plane coordinates of the vertex of the second object and the second world coordinates of the multiple landing points includes:

using the second world coordinates of the corresponding landing point of the second object vertex as two plane parameters in the second world coordinates of the second object vertex; and

using the coordinate conversion processing to determine the height of the second object based on the two plane parameters in the second plane coordinate of the second object vertex and the second world coordinate corresponding to the second object vertex.

5 . The method of claim 1 , wherein:

the second object is one second object of multiple second objects; and

using the coordinate conversion processing to determine the height of the second object based on the second plane coordinates of the vertex of the second object and the second world coordinates of the multiple landing points includes:

using the coordinate conversion processing to determine the height heights of the multiple second objects based on second plane coordinates of multiple vertices of the multiple second object objects and the second world coordinates of the multiple landing points; and

averaging the heights of the multiple second objects to determine the height of the one second object.

6 . The method of claim 2 , wherein using the coordinate conversion processing to obtain second world coordinates of multiple landing points of the second object in the world coordinate system of the first object based on the external parameter information, the internal parameter information, and second plane coordinates of multiple landing points of the second object in the to-be-detected image include:

obtaining N pieces of external parameter information corresponding to N first objects in a one-to-one correspondence, N being an integer greater than 1, the distances between the second object and the N first objects being all being less than the distance threshold;

using the coordinate conversion processing to obtain N sets of second world coordinates that correspond one-to-one to the world coordinate systems of the second object and the N first objects, each set of the second world coordinates including the second world coordinates of the multiple landing points of the second object;

correspondingly, using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object includes:

using the N pieces of external parameter information to determine N set of second camera coordinates based on the N sets of second world coordinates and the height of the second object, each set of second camera coordinates including multiple second camera coordinates of the landing points and the vertex; and

performing weighting processing on each second camera coordinate in the N sets of second camera coordinates to obtain processed second camera coordinate information.

7 . The method of claim 1 , wherein obtaining the first world coordinate information based on the world coordinate system established based on the position information and the size information of the first object includes:

establishing the world coordinate system of the first object with a landing point of the first object as a coordinate origin; and

determining the first world coordinate information in the world coordinate system based on the size information of the first object.

8 . The method of claim 1 , wherein using the coordinate conversion processing to obtain the external parameter information that converts the world coordinates of the first object into the camera coordinate based on the first plane coordinates, the first world coordinates of the multiple landing points of the first object, and the internal parameter information of the image acquisition device include:

using the coordinate conversion processing to obtain a homography matrix of the first object based on the first world coordinates of the multiple landing points of the first object and the multiple landing points; and

obtaining the external parameter information based on the internal parameter information and the homography matrix.

9 . A 3D object detection device comprising:

a first determination module, the first determination module being configured to determine first plane coordinates of multiple landing points of a first object based on a projection frame of the 3D first object in a to-be-detected image, the to-be-detected image being captured by an image acquisition device;

a first acquisition module, the first acquisition module being configured to obtain first world coordinate information based on a world coordinate system established based on position information and size information of the first object, the first world coordinate information including first world coordinates of the multiple landing points of the first object and first world coordinates of multiple vertices of the first object, the size information being obtained based on image characteristics of the first object;

a second acquisition module, the second acquisition module being configured to use coordinate conversion processing to obtain external parameter information that converts the world coordinates of the first object into camera coordinate based on the first plane coordinates, the first world coordinates of the multiple landing points of the first object, and the internal parameter information of the image acquisition device, the external parameter information being used to obtain first camera coordinate information of the first object based on the first world coordinate information;

a third acquisition module, the third acquisition module being configured to use the coordinate conversion processing to obtain second world coordinates of multiple landing points of a second object in the world coordinate system of the first object based on the external parameter information, the internal parameter information, and second plane coordinates of multiple landing points of the second object in the to-be-detected image; and

a second determination module, the second determination module being configured to use the coordinate conversion processing to determine a height of the second object based on the second plane coordinates of a vertex of the second object and the second world coordinates of the multiple landing points, wherein:

the size information of the second object is unknown, a distance between the second object and the first object is less than a distance threshold, and the height of the second object is used to determine the second world coordinates of multiple vertices of the second object.

10 . A non-transitory computer-readable storage medium containing computer-executable instructions for, when executed by one or more processors, performing a 3D object detection method, the method comprising:

determining first plane coordinates of multiple landing points of a first object based on a projection frame of the 3D first object in a to-be-detected image, the to-be-detected image being captured by an image acquisition device;

obtaining first world coordinate information based on a world coordinate system established based on position information and size information of the first object, the first world coordinate information including first world coordinates of the multiple landing points of the first object and first world coordinates of multiple vertices of the first object, the size information being obtained based on image characteristics of the first object;

using coordinate conversion processing to obtain external parameter information that converts the world coordinates of the first object into camera coordinate based on the first plane coordinates, the first world coordinates of the multiple landing points of the first object, and the internal parameter information of the image acquisition device, the external parameter information being used to obtain first camera coordinate information of the first object based on the first world coordinate information;

using the coordinate conversion processing to obtain second world coordinates of multiple landing points of a second object in the world coordinate system of the first object based on the external parameter information, the internal parameter information, and second plane coordinates of multiple landing points of the second object in the to-be-detected image; and

using the coordinate conversion processing to determine a height of the second object based on the second plane coordinates of a vertex of the second object and the second world coordinates of the multiple landing points, wherein:

the size information of the second object is unknown, a distance between the second object and the first object is less than a distance threshold, and the height of the second object is used to determine the second world coordinates of multiple vertices of the second object.

11 . The non-transitory computer-readable storage medium of claim 10 , wherein the method further comprising:

using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object.

12 . The non-transitory computer-readable storage medium of claim 11 , wherein using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object includes:

determining second world coordinate system information of the second object based on the second world coordinates of the multiple landing points and the height of the second object; and

using the external parameter information to determine the second camera coordinate information of the second object based on the second world coordinate system information.

13 . The non-transitory computer-readable storage medium of claim 10 , wherein using the coordinate conversion processing to determine the height of the second object based on the second plane coordinates of the vertex of the second object and the second world coordinates of the multiple landing points includes:

using the second world coordinates of the corresponding landing point of the second object vertex as two plane parameters in the second world coordinates of the second object vertex; and

using the coordinate conversion processing to determine the height of the second object based on the two plane parameters in the second plane coordinate of the second object vertex and the second world coordinate corresponding to the second object vertex.

14 . The non-transitory computer-readable storage medium of claim 10 , wherein;

the second object is one second object of multiple second objects; and

using the coordinate conversion processing to determine the height of the second object based on the second plane coordinates of the vertex of the second object and the second world coordinates of the multiple landing points includes:

using the coordinate conversion processing to determine the height heights of the multiple second objects based on second plane coordinates of multiple vertices of the multiple second object objects and the second world coordinates of the multiple landing points; and

averaging the heights of the multiple second objects to determine the height of the one second object.

15 . The non-transitory computer-readable storage medium of claim 11 , wherein using the coordinate conversion processing to obtain second world coordinates of multiple landing points of the second object in the world coordinate system of the first object based on the external parameter information, the internal parameter information, and second plane coordinates of multiple landing points of the second object in the to-be-detected image include:

obtaining N pieces of external parameter information corresponding to N first objects in a one-to-one correspondence, N being an integer greater than 1, the distances between the second object and the N first objects being all being less than the distance threshold;

using the coordinate conversion processing to obtain N sets of second world coordinates that correspond one-to-one to the world coordinate systems of the second object and the N first objects, each set of the second world coordinates including the second world coordinates of the multiple landing points of the second object;

correspondingly, using the external parameter information to determine second camera coordinate information of the second object based on the second world coordinates of the multiple landing points of the second object and the height of the second object includes:

using the N pieces of external parameter information to determine N set of second camera coordinates based on the N sets of second world coordinates and the height of the second object, each set of second camera coordinates including multiple second camera coordinates of the landing points and the vertex; and

performing weighting processing on each second camera coordinate in the N sets of second camera coordinates to obtain processed second camera coordinate information.

16 . The non-transitory computer-readable storage medium of claim 10 , wherein obtaining the first world coordinate information based on the world coordinate system established based on the position information and the size information of the first object includes:

establishing the world coordinate system of the first object with a landing point of the first object as a coordinate origin; and

determining the first world coordinate information in the world coordinate system based on the size information of the first object.

17 . The non-transitory computer-readable storage medium of claim 10 , wherein using the coordinate conversion processing to obtain the external parameter information that converts the world coordinates of the first object into the camera coordinate based on the first plane coordinates, the first world coordinates of the multiple landing points of the first object, and the internal parameter information of the image acquisition device include:

using the coordinate conversion processing to obtain a homography matrix of the first object based on the first world coordinates of the multiple landing points of the first object and the multiple landing points; and

obtaining the external parameter information based on the internal parameter information and the homography matrix.