Method, device, apparatus and storage medium for detecting a height of an obstacle
View Patent ↗A method, device, apparatus and a computer-readable storage medium for detecting a height of an obstacle are provided. The method can include: acquiring observation data of a plurality of reference obstacles from a frame; for each reference obstacle, determining a first evaluation value of the height of the obstacle to be detected, according to the observation data of the reference obstacle, an observed height of the obstacle to be detected in a frame, an actual height of the reference obstacle, and a distance between a bottom of the obstacle to be detected in the frame and an optical axis of a camera capturing the frame; and determining a second evaluation value of the height of the obstacle to be detected by using a plurality of first evaluation values for the plurality of reference obstacles.
1. A computer-implemented method for detecting a height of an obstacle to be detected, comprising:
capturing, with a camera, a plurality of image frames depicting the obstacle to be detected;
selecting a plurality of reference obstacles depicted in a frame of the plurality of image frames, each reference obstacle having a known height and located in a plurality of consecutive image frames prior to the frame;
acquiring observation data of the plurality of reference obstacles from the frame;
for each reference obstacle, determining a first evaluation value of the height of the obstacle to be detected, according to the observation data of the reference obstacle, an observed height of the obstacle to be detected in the frame, the known height of the reference obstacle, and a distance between a bottom of the obstacle to be detected in the frame and an optical axis of the camera, wherein the observation data of the reference obstacle comprises an observed height of the reference obstacle in the frame and a distance between a bottom of the reference obstacle in the frame and the optical axis of the camera; and
determining a second evaluation value of the height of the obstacle to be detected by using a plurality of first evaluation values for the plurality of reference obstacles.
2. The method according to claim 1 , wherein for each reference obstacle, determining a first evaluation value of the height of the obstacle to be detected, according to the observation data of the reference obstacle, an observed height of the obstacle to be detected in the frame, the known height of the reference obstacle, and a distance between a bottom of the obstacle to be detected in the frame and an optical axis of the camera comprises:
for the i-th reference obstacle, determining the first evaluation value of the height of the obstacle to be detected with the following equation:
Hp
=
Hi
hi
·
y
max
i
-
Cy
y
max
p
-
Cy
·
h
p
where Hp is the first evaluation value of the height of the obstacle to be detected;
hp is the observed height of the obstacle to be detected in the frame;
hi is an observed height of the i-th reference obstacle in the frame;
Hi is an actual height of the i-th reference obstacle;
y max p −Cy is the distance between the bottom of the obstacle to be detected in the frame and the optical axis of the camera capturing the frame; and
y max i −Cy is a distance between a bottom of the i-th reference obstacle in the frame and the optical axis of the camera.
3. The method according to claim 1 , wherein determining a second evaluation value of the height of the obstacle to be detected by using a plurality of first evaluation values for the plurality of reference obstacles comprises:
acquiring the second evaluation value of the height of the obstacle to be detected by filtering and denoising the plurality of first evaluation values.
4. The method according to claim 1 , wherein each reference obstacle further has a bottom center located in a preset area, the preset area divided into a plurality of divisions in advance, such that each division comprises no more than one reference obstacle.
5. A non-transitory computer-readable storage medium, in which a computer program is stored, wherein the computer program, when executed by a processor, implements the method of claim 1 .
6. A device for detecting a height of an obstacle to be detected, comprising:
one or more processors;
a camera; and
a non-transitory storage device configured for storing one or more programs, wherein the one or more programs are executed by the one or more processors to enable the one or more processors to:
cause the camera to capture a plurality of image frames depicting the obstacle to be detected;
select a plurality of reference obstacles depicted in a frame of the plurality of image frames, each reference obstacle having a known height and located in a plurality of consecutive image frames prior to the frame;
acquire observation data of the plurality of reference obstacles from the frame;
for each reference obstacle, determine a first evaluation value of the height of the obstacle to be detected, according to the observation data of the reference obstacle, an observed height of the obstacle to be detected in the frame, the known height of the reference obstacle, and a distance between a bottom of the obstacle to be detected in the frame and an optical axis of the camera, wherein the observation data of the reference obstacle comprises an observed height of the reference obstacle in the frame and a distance between a bottom of the reference obstacle in the frame and the optical axis of the camera; and
determine a second evaluation value of the height of the obstacle to be detected by using a plurality of first evaluation values for the plurality of reference obstacles.
7. The device according to claim 6 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: for the i-th reference obstacle, determine the first evaluation value of the height of the obstacle to be detected with the following equation:
Hp
=
Hi
hi
·
y
max
i
-
Cy
y
max
p
-
Cy
·
h
p
where Hp is the first evaluation value of the height of the obstacle to be detected;
hp is the observed height of the obstacle to be detected in the frame;
hi is an observed height of the i-th reference obstacle in the frame;
Hi is an actual height of the i-th reference obstacle;
y max p −Cy is the distance between the bottom of the obstacle to be detected in the frame and the optical axis of the camera capturing the frame; and
y max i −Cy is a distance between a bottom of the i-th reference obstacle in the frame and the optical axis of the camera.
8. The device according to claim 6 , wherein the one or more programs are executed by the one or more processors to enable the one or more processors to: acquire the second evaluation value of the height of the obstacle to be detected by filtering and denoising plurality of first evaluation values.
9. The device according to claim 6 , wherein each reference obstacle has a fixed height and a bottom center located in a preset area, the preset area divided into a plurality of divisions in advance, such that each division comprises no more than one reference obstacle.