Obstacle three-dimensional position acquisition method and apparatus for roadside computing device

An electronic device, comprising:

• at least one processor;
• and
• a memory communicatively connected with the at least one processor;
• wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method of obstacle three-dimensional (3D) position acquisition for a roadside computing device, wherein the method comprises:
• acquiring pixel coordinates of an obstacle in a to-be-processed image;
• determining coordinates of a bottom surface center point of the obstacle according to the pixel coordinates;
• acquiring a homography relationship between a ground surface corresponding to the to-be-processed image and a ground surface corresponding to a template image;
• transforming the coordinates of the bottom surface center point of the obstacle into coordinates on the template image according to the homography relationship;
• and
• determining 3D coordinates of the bottom surface center point of the obstacle according to the coordinates obtained by transformation and a ground equation corresponding to the template image,
• wherein the acquiring a homography relationship between a ground surface corresponding to the to-be-processed image and a ground surface corresponding to a template image comprises:
• acquiring a 3*3 homography matrix with 8 degrees of freedom,
• wherein the acquiring a 3*3 homography matrix with 8 degrees of freedom comprises:
• acquiring, for four regions of interest selected in the template image, corresponding regions of interest from the to-be-processed image respectively;
• acquiring, for any region of interest in the to-be-processed image, corresponding relationships among a pixel center point of the region of interest and pixel center points of the corresponding regions of interest in the template image as a matching pair;
• and
• determining the homography matrix according to the acquired four matching pairs,
• wherein the acquiring, for any region of interest in the to-be-processed image, corresponding relationships among a pixel center point of the region of interest and pixel center points of the corresponding regions of interest in the template image as a matching pair comprises:
• performing the following processing respectively for any region of interest in the to-be-processed image:
• taking the region of interest as a to-be-processed region of interest;
• acquiring a first offset corresponding to the to-be-processed region of interest and used for calculating the homography matrix, and correcting coordinates of a pixel center point of the to-be-processed region of interest by using the first offset;
• and
• recording corresponding relationships among the coordinates of the pixel center point of the to-be-processed region of interest and coordinates of pixel center points of the corresponding regions of interest in the template image as a matching pair.

A non-transitory computer readable storage medium with computer instructions stored thereon, wherein the computer instructions are used for causing a computer to perform a method of obstacle three-dimensional (3D) position acquisition for a roadside computing device, wherein the method comprises:

• acquiring pixel coordinates of an obstacle in a to-be-processed image;
• determining coordinates of a bottom surface center point of the obstacle according to the pixel coordinates;
• acquiring a homography relationship between a ground surface corresponding to the to-be-processed image and a ground surface corresponding to a template image;
• transforming the coordinates of the bottom surface center point of the obstacle into coordinates on the template image according to the homography relationship;
• and
• determining 3D coordinates of the bottom surface center point of the obstacle according to the coordinates obtained by transformation and a ground equation corresponding to the template image,
• wherein the acquiring a homography relationship between a ground surface corresponding to the to-be-processed image and a ground surface corresponding to a template image comprises:
• acquiring a 3*3 homography matrix with 8 degrees of freedom,
• wherein the acquiring a 3*3 homography matrix with 8 degrees of freedom comprises:
• acquiring, for four regions of interest selected in the template image, corresponding regions of interest from the to-be-processed image respectively;
• acquiring, for any region of interest in the to-be-processed image, corresponding relationships among a pixel center point of the region of interest and pixel center points of the corresponding regions of interest in the template image as a matching pair;
• and
• determining the homography matrix according to the acquired four matching pairs,
• wherein the acquiring, for any region of interest in the to-be-processed image, corresponding relationships among a pixel center point of the region of interest and pixel center points of the corresponding regions of interest in the template image as a matching pair comprises:
• performing the following processing respectively for any region of interest in the to-be-processed image:
• taking the region of interest as a to-be-processed region of interest;
• acquiring a first offset corresponding to the to-be-processed region of interest and used for calculating the homography matrix, and correcting coordinates of a pixel center point of the to-be-processed region of interest by using the first offset;
• and
• recording corresponding relationships among the coordinates of the pixel center point of the to-be-processed region of interest and coordinates of pixel center points of the corresponding regions of interest in the template image as a matching pair.