Method and apparatus for determining rotation angle of engineering mechanical device

1. A method for determining a rotation angle of an engineering mechanical device, the method comprising:

acquiring a depth image sequence acquired by a binocular camera disposed at a rotating portion of the engineering mechanical device during rotation of the rotating portion of the engineering mechanical device;

converting the depth image sequence into a three-dimensional point cloud sequence; and

determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence, and determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, wherein the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames, comprises:

using rotation angle sensing data corresponding to the three-dimensional point cloud frames as an initial estimation range of a rotation angle corresponding to the three-dimensional point cloud frames, and determining the rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames within the initial estimation range.

2. The method according to claim 1 , wherein the method further comprises:

acquiring rotation angle sensing data acquired by an angle sensor disposed on a rotating shaft of the rotating portion of the engineering mechanical device during the rotation of the rotating portion of the engineering mechanical device.

3. The method according to claim 1 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

determining, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, a matching point between the current three-dimensional point cloud frame and a previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, based on three-dimensional coordinates of the matching point between the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame in the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame, a rotation angle between the current three-dimensional point cloud frame and a depth image frame corresponding to the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

adding sequentially rotation angles between depth image frames corresponding to adjacent three-dimensional point cloud frames in the three-dimensional point cloud sequence according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

4. The method according to claim 1 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

sampling a three-dimensional point cloud frame in the three-dimensional point cloud sequence to obtain a sampling sequence, wherein the sampling sequence comprises a first three-dimensional point cloud frame and a last three-dimensional point cloud frame in the three-dimensional point cloud sequence;

determining, for each three-dimensional point cloud frame pair composed of adjacent three-dimensional point cloud frames in the sampling sequence, a matching point between two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, based on three-dimensional coordinates of the matching point between the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair, a rotation angle between depth image frames corresponding to the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

adding sequentially rotation angles between depth image frames corresponding to two three-dimensional point cloud frames in three-dimensional point cloud frame pairs according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

5. The method according to claim 1 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

performing feature point extraction on the three-dimensional point cloud frames; and

matching feature points of two extracted three-dimensional point cloud frames to obtain a matching point between the two three-dimensional point cloud frames.

6. An apparatus for determining a rotation angle of an engineering mechanical device, the apparatus comprising:

at least one processor; and

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

acquiring a depth image sequence acquired by a binocular camera disposed at a rotating portion of the engineering mechanical device during rotation of the rotating portion of the engineering mechanical device;

converting the depth image sequence into a three-dimensional point cloud sequence; and

determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence, and determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, wherein the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames, comprises:

using rotation angle sensing data corresponding to the three-dimensional point cloud frames as an initial estimation range of a rotation angle corresponding to the three-dimensional point cloud frames, and determining the rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames within the initial estimation range.

7. The apparatus according to claim 6 , wherein the operations further comprise:

acquiring rotation angle sensing data acquired by an angle sensor disposed on a rotating shaft of the rotating portion of the engineering mechanical device during the rotation of the rotating portion of the engineering mechanical device.

8. The apparatus according to claim 6 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

determining, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, a matching point between the current three-dimensional point cloud frame and a previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, based on three-dimensional coordinates of the matching point between the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame in the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame, a rotation angle between the current three-dimensional point cloud frame and a depth image frame corresponding to the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

adding sequentially rotation angles between depth image frames corresponding to adjacent three-dimensional point cloud frames in the three-dimensional point cloud sequence according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

9. The apparatus according to claim 6 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

sampling a three-dimensional point cloud frame in the three-dimensional point cloud sequence to obtain a sampling sequence, wherein the sampling sequence comprises a first three-dimensional point cloud frame and a last three-dimensional point cloud frame in the three-dimensional point cloud sequence;

determining, for each three-dimensional point cloud frame pair composed of adjacent three-dimensional point cloud frames in the sampling sequence, a matching point between two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, based on three-dimensional coordinates of the matching point between the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair, a rotation angle between depth image frames corresponding to the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

adding sequentially rotation angles between depth image frames corresponding to two three-dimensional point cloud frames in three-dimensional point cloud frame pairs according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

10. The apparatus according to claim 6 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

performing feature point extraction on the three-dimensional point cloud frames; and

matching feature points of two extracted three-dimensional point cloud frames to obtain a matching point between the two three-dimensional point cloud frames.

11. A non-transitory computer readable medium, storing a computer program thereon, the program, when executed by a processor, causes the processor to perform operations, the operations comprising:

acquiring a depth image sequence acquired by a binocular camera disposed at a rotating portion of an engineering mechanical device during rotation of the rotating portion of the engineering mechanical device;

converting the depth image sequence into a three-dimensional point cloud sequence; and

determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence, and determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, wherein the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames, comprises:

using rotation angle sensing data corresponding to the three-dimensional point cloud frames as an initial estimation range of a rotation angle corresponding to the three-dimensional point cloud frames, and determining the rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames within the initial estimation range.

12. The non-transitory computer readable medium according to claim 11 , wherein the operations further comprise:

acquiring rotation angle sensing data acquired by an angle sensor disposed on a rotating shaft of the rotating portion of the engineering mechanical device during the rotation of the rotating portion of the engineering mechanical device.

13. The non-transitory computer readable medium according to claim 11 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

determining, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, a matching point between the current three-dimensional point cloud frame and a previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, for each current three-dimensional point cloud frame in the three-dimensional point cloud sequence, based on three-dimensional coordinates of the matching point between the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame in the current three-dimensional point cloud frame and the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame, a rotation angle between the current three-dimensional point cloud frame and a depth image frame corresponding to the previous three-dimensional point cloud frame of the current three-dimensional point cloud frame; and

adding sequentially rotation angles between depth image frames corresponding to adjacent three-dimensional point cloud frames in the three-dimensional point cloud sequence according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

14. The non-transitory computer readable medium according to claim 11 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

sampling a three-dimensional point cloud frame in the three-dimensional point cloud sequence to obtain a sampling sequence, wherein the sampling sequence comprises a first three-dimensional point cloud frame and a last three-dimensional point cloud frame in the three-dimensional point cloud sequence;

determining, for each three-dimensional point cloud frame pair composed of adjacent three-dimensional point cloud frames in the sampling sequence, a matching point between two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

the determining a rotation angle of the binocular camera during the rotation of the rotating portion of the engineering mechanical device based on the matching point between the three-dimensional point cloud frames as the rotation angle of the engineering mechanical device, comprises:

estimating, based on three-dimensional coordinates of the matching point between the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair, a rotation angle between depth image frames corresponding to the two three-dimensional point cloud frames in the three-dimensional point cloud frame pair; and

adding sequentially rotation angles between depth image frames corresponding to two three-dimensional point cloud frames in three-dimensional point cloud frame pairs according to positions of corresponding depth images in the depth image sequence, to obtain a relative rotation angle of the binocular camera when acquiring images between a first frame image and a last frame image in the depth image sequence as the rotation angle of the engineering mechanical device.

15. The non-transitory computer readable medium according to claim 11 , wherein the determining a matching point between three-dimensional point cloud frames in the three-dimensional point cloud sequence comprises:

performing feature point extraction on the three-dimensional point cloud frames; and

matching feature points of two extracted three-dimensional point cloud frames to obtain a matching point between the two three-dimensional point cloud frames.