Distance measurement method and device, and robot and storage medium

1 . A distance measurement method, applied to a self-moving robot equipped with an image acquisition device, and comprising steps of:

acquiring a first image, wherein the first image at least comprises a to-be-detected object and a ground on which the to-be-detected object is located;

determining an initial constraint condition of the ground based on the first image;

acquiring a second image, wherein the second image at least comprises an intersection line of a line structured light beam with at least one of the ground and the to-be-detected object;

determining a position parameter of the ground based on the second image, and correcting the initial constraint condition of the ground based on the position parameter; and

determining a distance to the to-be-detected object based on the corrected initial constraint condition of the ground and the first image;

wherein, before the step of acquiring the second image, the method comprises a step of:

emitting at least one surface-scanning light beam that is not parallel to the ground by a line structured light source, the surface-scanning light beam forming at least one intersection line with the ground.

2 . The method according to claim 1 , wherein the step of emitting at least one surface-scanning light beam that is not parallel to the ground by the line structured light source, the surface-scanning light beam forming at least one intersection line with the ground, comprises a sub-step of:

alternately emitting at least two surface-scanning light beams that are perpendicular to the ground by the line structured light source, the surface-scanning light beams forming at least two intersection lines with the ground; or

emitting one transverse surface-scanning light beam that is not parallel to the ground and one surface-scanning light beam that is perpendicular to the ground by the line structured light source, the surface-scanning light beams forming at least two intersection lines with the ground.

3 . The method according to claim 2 , wherein the step of emitting one transverse surface-scanning light beam that is not parallel to the ground and one surface-scanning light beam that is perpendicular to the ground by the line structured light source, the surface-scanning light beams forming at least two intersection lines with the ground, comprises sub-steps of:

emitting one transverse surface-scanning light beam that is not parallel to the ground toward a traveling direction of the self-moving robot by the line structured light source; and

emitting one surface-scanning light beam that is perpendicular to the ground toward a side direction in traveling of the self-moving robot,

wherein the surface-scanning light beams form the at least two intersection lines with the ground.

4 . The method according to claim 3 , wherein the step of emitting one surface-scanning light beam that is perpendicular to the ground toward the side direction in traveling of the self-moving robot comprises a sub-step of:

emitting one surface-scanning light beam that is perpendicular to the ground toward a downward direction relative to the traveling direction of the self-moving robot.

5 . The method according to claim 1 , wherein

an image acquisition device for acquiring the first image is an infrared image acquisition device or a visible light image acquisition device; and

an image acquisition device for acquiring the second image is an infrared image acquisition device.

6 . The method according to claim 5 , wherein the first image acquisition device and the second image acquisition device are the same infrared image acquisition device.

7 . The method according to claim 6 , further comprising steps of:

controlling an infrared light source to respectively emit an infrared light beam in different periods of time; and

controlling a shooting time sequence to respectively obtain the first image and the second image in different periods of time by the same infrared image acquisition device.

8 . The method according to claim 1 , wherein the step of determining the distance to the to-be-detected object based on the corrected initial constraint condition of the ground and the first image comprises sub-steps of:

determining an object region of the to-be-detected object in the first image, wherein the object region is the smallest rectangle comprising the to-be-detected object;

determining a lower edge position parameter of the object region and a lower edge position parameter of the first image based on the corrected initial constraint condition of the ground; and

determining the distance to the to-be-detected object based on the lower edge position parameter of the object region and the lower edge position parameter of the first image.

9 . The method according to claim 8 , wherein the step of determining the distance to the to-be-detected object based on the lower edge position parameter of the object region and the lower edge position parameter of the first image comprises sub-steps of:

determining a reference position as an origin of coordinates in the first image;

selecting any point in a lower edge of the smallest rectangle as a first reference point, and determining a second reference point in a lower edge of the first image based on the first reference point; and

calculating the distance to the to-be-detected object based on position coordinates of the first reference point and the second reference point.

10 . The method according to claim 1 , wherein the step of determining the position parameter of the ground based on the second image comprises sub-steps of:

acquiring point cloud data for structured light based on the intersection line of the line structured light beam with the to-be-detected object;

filtering the point cloud data for structured light based on the initial constraint condition of the ground;

fitting the filtered point cloud data for structured light to obtain a ground equation; and

determining the position parameter of the ground by using the ground equation.

11 . The method according to claim 1 , wherein the step of determining the position parameter of the ground based on the second image comprises sub-steps of:

fitting the intersection line of the line structured light beam with the ground;

determining a ground equation based on at least two fitted intersection lines with the ground; and

determining the position parameter of the ground by using the ground equation.

12 . A robot, comprising a processor and a memory, wherein the memory stores computer program instructions executable by the processor, and the processor, when executing the computer program instructions, implements a distance measurement method, comprising steps of:

acquiring a first image, wherein the first image at least comprises a to-be-detected object and a ground on which the to-be-detected object is located;

determining an initial constraint condition of the ground based on the first image;

acquiring a second image, wherein the second image at least comprises an intersection line of a line structured light beam with at least one of the ground and the to-be-detected object;

determining a position parameter of the ground based on the second image, and correcting the initial constraint condition of the ground based on the position parameter; and

determining a distance to the to-be-detected object based on the corrected initial constraint condition of the ground and the first image;

wherein, before the step of acquiring the second image, the method comprises a step of:

emitting at least one surface-scanning light beam that is not parallel to the ground by a line structured light source, the surface-scanning light beam forming at least one intersection line with the ground.

13 . The robot according to claim 12 , wherein the step of emitting at least one surface-scanning light beam that is not parallel to the ground by the line structured light source, the surface-scanning light beam forming at least one intersection line with the ground, comprises a sub-step of:

alternately emitting at least two surface-scanning light beams that are perpendicular to the ground by the line structured light source, the surface-scanning light beams forming at least two intersection lines with the ground; or

emitting one transverse surface-scanning light beam that is not parallel to the ground and one surface-scanning light beam that is perpendicular to the ground by the line structured light source, the surface-scanning light beams forming at least two intersection lines with the ground.

14 . The robot according to claim 12 , wherein

an image acquisition device for acquiring the first image is an infrared image acquisition device or a visible light image acquisition device; and

an image acquisition device for acquiring the second image is an infrared image acquisition device.

15 . The robot according to claim 12 , wherein the step of determining the distance to the to-be-detected object based on the corrected initial constraint condition of the ground and the first image comprises sub-steps of:

determining an object region of the to-be-detected object in the first image, wherein the object region is the smallest rectangle comprising the to-be-detected object;

determining a lower edge position parameter of the object region and a lower edge position parameter of the first image based on the corrected initial constraint condition of the ground; and

determining the distance to the to-be-detected object based on the lower edge position parameter of the object region and the lower edge position parameter of the first image.

16 . The robot according to claim 12 , wherein the step of determining the position parameter of the ground based on the second image comprises sub-steps of:

acquiring point cloud data for structured light based on the intersection line of the line structured light beam with the to-be-detected object;

filtering the point cloud data for structured light based on the initial constraint condition of the ground;

fitting the filtered point cloud data for structured light to obtain a ground equation; and

determining the position parameter of the ground by using the ground equation.

17 . The robot according to claim 12 , wherein the step of determining the position parameter of the ground based on the second image comprises sub-steps of:

fitting the intersection line of the line structured light beam with the ground;

determining a ground equation based on at least two fitted intersection lines with the ground; and

determining the position parameter of the ground by using the ground equation.

18 . A non-transitory computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when called and executed by a processor, implement a distance measurement method, comprising steps of:

acquiring a first image, wherein the first image at least comprises a to-be-detected object and a ground on which the to-be-detected object is located;

determining an initial constraint condition of the ground based on the first image;

acquiring a second image, wherein the second image at least comprises an intersection line of a line structured light beam with at least one of the ground and the to-be-detected object;

determining a position parameter of the ground based on the second image, and correcting the initial constraint condition of the ground based on the position parameter; and

determining a distance to the to-be-detected object based on the corrected initial constraint condition of the ground and the first image;

wherein, before the step of acquiring the second image, the method comprises a step of:

emitting at least one surface-scanning light beam that is not parallel to the ground by a line structured light source, the surface-scanning light beam forming at least one intersection line with the ground.