Image processing method, terminal, and storage medium

A terminal for image processing, comprising:

• one or more processors;
• and
• memory coupled to the one or more processors, the memory storing a plurality of programs that, when executed by the one or more processors, cause the terminal to perform a plurality of operations comprising:
• extracting one or more image feature points from a target frame image captured by a camera of the terminal;
• determining a plurality of grid sub-regions in the target frame image, each grid sub-region including at least one of the extracted image feature points;
• calculating a centroid location of the target frame image according to a quantity of image feature points in each of the plurality of grid sub-regions;
• in accordance with a determination that the centroid location is in a central region of the target frame image:
• determining that the target frame image is a valid frame image;
• obtaining feature information of at least one optical flow image feature point in a frame image captured by the camera immediately preceding the target frame image;
• determining, among the one or more image feature points, an image feature point corresponding to the optical flow image feature point according to the feature information of the at least one image feature point;
• calculating a displacement between the optical flow image feature point in the frame image immediately preceding the target frame image and the corresponding image feature point in the target frame image;
• and
• submitting the target frame image to a remote server when the displacement indicates that the target frame image is captured in a non-motion state.

A non-transitory computer readable storage medium storing a plurality of machine readable instructions in connection with a terminal having one or more processors, wherein the plurality of machine readable instructions, when executed by the one or more processors, cause the terminal to perform a plurality of operations including:

• extracting one or more image feature points from a target frame image captured by a camera of the terminal;
• determining a plurality of grid sub-regions in the target frame image, each grid sub-region including at least one of the extracted image feature points;
• calculating a centroid location of the target frame image according to a quantity of image feature points in each of the plurality of grid sub-regions;
• in accordance with a determination that the centroid location is in a central region of the target frame image:
• determining that the target frame image is a valid frame image;
• obtaining feature information of at least one optical flow image feature point in a frame image captured by the camera immediately preceding the target frame image;
• determining, among the one or more image feature points, an image feature point corresponding to the optical flow image feature point according to the feature information of the at least one image feature point;
• calculating a displacement between the optical flow image feature point in the frame image immediately preceding the target frame image and the corresponding image feature point in the target frame image;
• and
• submitting the target frame image to a remote server when the displacement indicates that the target frame image is captured in a non-motion state.