Object detection method, object detection device and storage medium

1. An object detection method, comprising:

performing edge detection on an image to be detected, and determining at least one contour existing in the image to be detected;

with respect to each contour, acquiring a circumscribed rectangular frame of the contour;

calculating a contour diameter of an enclosed area enclosed by the contour;

determining a shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter;

determining an object in the image to be detected and parameter information of the object based on the shape of each contour; and

wherein determining the shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter comprises:

judging a first length difference between adjacent side lengths of the circumscribed rectangular frame of the contour and a second length difference between the contour diameter and the side length of the circumscribed rectangular frame corresponding to the contour, determining the shape of the contour according to the first length difference and the second length difference.

2. The method according to claim 1 , wherein calculating the contour diameter of the enclosed area enclosed by the contour comprises:

calculating a contour area of the enclosed area enclosed by the contour based on a quantity and a size of pixel points included in the enclosed area; and

calculating the contour diameter of the enclosed area enclosed by the contour according to the contour area and based on a relationship between a circle's area and diameter.

3. The method according to claim 1 , wherein determining the shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter comprises:

judging whether the first length is within a first threshold and whether the second length is within a second threshold, and if judgment results are both positive, determining that the shape of the contour is a circle.

4. The method according to claim 1 , wherein

determining at least one contour existing in the image to be detected comprises:

determining that at least a first contour and a second contour exist in the image to be detected;

the method further comprises:

acquiring a position of a first centroid of the first contour and a position of a second centroid of the second contour; and

determining an object in the image to be detected and parameter information of the object based on the position of the first centroid, the position of the second centroid and a contour diameter corresponding to each contour.

5. The method according to claim 4 , wherein

when a difference between the position of the first centroid and the position of the second centroid is less than a third threshold and a difference between a radius of the first contour and a radius of the second contour is greater than a fourth threshold, determining that the object in the image to be detected and parameter information of the object include a concentric ring;

when a difference between the position of the first centroid and the position of the second centroid is less than the third threshold and a difference between a radius of the first contour and a radius of the second contour is less than a fifth threshold, determining that the object in the image to be detected and parameter information of the object include a concentric circle.

6. The method according to claim 5 , wherein the method further comprises:

calculating an average value of the position of the first centroid and the position of the second centroid of the concentric ring to obtain a center of the concentric ring; and

calculating a first contour radius of the concentric ring according to a distance between a pixel point on the first contour of the concentric ring and the center of the concentric ring, and calculating a second contour radius of the concentric ring according to a distance between a pixel point on the second contour of the concentric ring and the center of the concentric ring;

and/or

calculating an average value of the position of the first centroid and the position of the second centroid of the concentric circle to obtain a center of the concentric circle; and

calculating a contour radius of the concentric circle according to distances between pixel points on the first contour and the second contour of the concentric circle and the center of the concentric circle.

7. The method according to claim 6 , wherein

calculating a first contour radius of the concentric ring according to a distance between a pixel point on the first contour of the concentric ring and the center of the concentric ring, and calculating a second contour radius of the concentric ring according to a distance between a pixel point on the second contour of the concentric ring and the center of the concentric ring comprises:

taking an average value of distances between a plurality of pixel points on the first contour and the center of the concentric ring as the first contour radius of the concentric ring; and

taking an average value of distances between a plurality of pixel points on the second contour and the center of the concentric ring as the second contour radius of the concentric ring;

calculating a contour radius of the concentric circle according to distances between pixel points on the first contour and the second contour of the concentric circle and the center of the concentric circle comprises:

taking an average value of distances between a plurality of pixel points on the first contour and the second contour of the concentric circle and the center of the concentric circle as the contour radius of the concentric circle.

8. The method according to claim 1 , wherein before performing edge detection on the image to be detected, the method further comprises:

collecting a first image of the object to be detected;

performing grayscale processing on the first image; and

performing Gaussian blur on the first image after grayscale processing to obtain a binarized image to be detected.

9. The method according to claim 1 , wherein acquiring a circumscribed rectangular frame of the contour comprises:

with respect to any contour of the at least one contour, determining a vertical boundary of the contour based on boundary pixel points of the contour, and determining a circumscribed rectangular frame of the contour according to the vertical boundary;

the method further comprises:

with respect to any contour of the at least one contour, determining a contour moment of the contour; and

determining a centroid of the contour according to the contour moment of the contour.

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

removing a contour having a contour diameter less than a sixth threshold from the at least one contour;

and/or

removing a contour having a non-circular contour shape from the at least one contour.

11. An object detection device, comprising:

a memory for storing a computer program; and

a processor for executing the computer program;

wherein the processor is for

performing edge detection on an image to be detected, and determining at least one contour existing in the image to be detected;

with respect to each contour, acquiring a circumscribed rectangular frame of the contour;

calculating a contour diameter of an enclosed area enclosed by the contour;

determining a shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter;

determining an object in the image to be detected and parameter information of the object based on the shape of each contour; and

wherein the processor is specifically for judging a first length difference between adjacent side lengths of the circumscribed rectangular frame of the contour and a second length difference between the contour diameter and the side length of the circumscribed rectangular frame corresponding to the contour, and determining the shape of the contour according to the first length difference and the second length difference.

12. The device according to claim 11 , wherein the processor is specifically for

calculating a contour area of the enclosed area enclosed by the contour based on a quantity and a size of pixel points included in the enclosed area; and

calculating the contour diameter of the enclosed area enclosed by the contour according to the contour area and based on a relationship between a circle's area and diameter.

13. The device according to claim 11 , wherein the processor is specifically for judging whether the first length is within a first threshold and whether the second length is within a second threshold, and if judgment results are both positive, determining that the shape of the contour is a circle.

14. The device according to claim 11 , wherein

the processor is specifically for determining that at least a first contour and a second contour exist in the image to be detected; and

the processor is further for

acquiring a position of a first centroid of the first contour and a position of a second centroid of the second contour; and

determining an object in the image to be detected and parameter information of the object based on the position of the first centroid, the position of the second centroid and a contour diameter corresponding to each contour.

15. The device according to claim 14 , wherein the processor is specifically for

when a difference between the position of the first centroid and the position of the second centroid is less than a third threshold and a difference between a radius of the first contour and a radius of the second contour is greater than a fourth threshold, determining that the object in the image to be detected and parameter information of the object include a concentric ring; and

when a difference between the position of the first centroid and the position of the second centroid is less than the third threshold and a difference between a radius of the first contour and a radius of the second contour is less than a fifth threshold, determining that the object in the image to be detected and parameter information of the object include a concentric circle.

16. The device according to claim 15 , wherein the processor is specifically for

calculating an average value of the position of the first centroid and the position of the second centroid of the concentric ring to obtain a center of the concentric ring; and

calculating a first contour radius of the concentric ring according to a distance between a pixel point on the first contour of the concentric ring and the center of the concentric ring, and calculating a second contour radius of the concentric ring according to a distance between a pixel point on the second contour of the concentric ring and the center of the concentric ring;

and/or

calculating an average value of the position of the first centroid and the position of the second centroid of the concentric circle to obtain a center of the concentric circle; and

calculating a contour radius of the concentric circle according to distances between pixel points on the first contour and the second contour of the concentric circle and the center of the concentric circle.

17. The device according to claim 16 , wherein the processor is specifically for

taking an average value of distances between a plurality of pixel points on the first contour and the center of the concentric ring as the first contour radius of the concentric ring; and

taking an average value of distances between a plurality of pixel points on the second contour and the center of the concentric ring as the second contour radius of the concentric ring;

or taking an average value of distances between a plurality of pixel points on the first contour and the second contour of the concentric circle and the center of the concentric circle as the contour radius of the concentric circle.

18. The device according to claim 11 , wherein

the processor is specifically for, with respect to any contour of the at least one contour, determining a vertical boundary of the contour based on boundary pixel points of the contour, and determining a circumscribed rectangular frame of the contour according to the vertical boundary; and

the processor is further for

with respect to any contour of the at least one contour, determining a contour moment of the contour; and

determining a centroid of the contour according to the contour moment of the contour.

19. The device according to claim 11 , wherein the processor is specifically for

removing a contour having a contour diameter less than a sixth threshold from the at least one contour;

and/or

removing a contour having a non-circular contour shape from the at least one contour.

20. A non-transitory computer readable storage medium storing a computer program, wherein when executed by one or more processors, the computer program causes the one or more processors to implement steps of a method comprising

performing edge detection on an image to be detected, and determining at least one contour existing in the image to be detected;

with respect to each contour, acquiring a circumscribed rectangular frame of the contour;

calculating a contour diameter of an enclosed area enclosed by the contour;

determining a shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter; and

determining an object in the image to be detected and parameter information of the object based on the shape of each contour;

wherein determining the shape of the contour based on side lengths of the circumscribed rectangular frame and the contour diameter comprises:

judging whether a first length difference between adjacent side lengths of the circumscribed rectangular frame of the contour is within a first threshold and whether a second length difference between the contour diameter and the side length of the circumscribed rectangular frame corresponding to the contour is within a second threshold, and if judgment results are both positive, determining that the shape of the contour is a circle.