Method, apparatus and terminal for detecting image stability

An apparatus for detecting image stability, comprising at least a processor executing program codes stored in a memory, which configure the apparatus to:

• acquire N consecutive image frames, wherein N represents an integer equal to 2 or larger;
• wherein in each of the N consecutive image frames, the apparatus is further configured to:
• detect corner points in the image frame,
• divide the image frame into multiple areas,
• record distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;
• wherein the dividing of the image frame into multiple areas, and the recording of the distribution of the corner points in each of the multiple areas to obtain the description vector of the image frame, comprises the apparatus configured to:
• divide the image frame to obtain M areas, recording each of the M areas whether a corner point exists in;
• obtain the description vector of the image based on a length of M, wherein the description vector indicates the existing state of the corner points in the M areas, wherein M represents an integer greater than 1, wherein for each area in the M areas, if corner points are existed in, recording as “1”, if no corner points are existed in, recording as “0”, wherein the recorded “1”s are utilized to obtain the description vector of each image in order to obtain the length of M;
• calculate a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;
• and
• determine whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

A terminal for detecting image stability, comprises at least a processor executing program codes stored in a memory, which configure the terminal to:

• acquire N consecutive image frames, wherein N represents an integer equal to 2 or larger;
• wherein in each of the N consecutive image frames, the terminal is further configured to:
• detect corner points in the image frame,
• divide the image frame into multiple areas;
• and
• record distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;
• wherein the dividing of the image frame into multiple areas, and the recording of the distribution of the corner points in each of the multiple areas to obtain the description vector of the image frame, comprises the apparatus configured to:
• divide the image frame to obtain M areas, recording each of the M areas whether a corner point exists in;
• obtain the description vector of the image based on a length of M, wherein the description vector indicates the existing state of the corner points in the M areas, wherein M represents an integer greater than 1, wherein for each area in the M areas, if corner points are existed in, recording as “1”, if no corner points are existed in, recording as “0”, wherein the recorded “1”s are utilized to obtain the description vector of each image in order to obtain the length of M
• calculate a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;
• determine whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.

A non-transitory computer-readable storage medium having stored thereon, a computer program having at least one code section being executable by a machine for causing the machine to perform steps in detecting image stability, comprising:

• acquiring N consecutive image frames, wherein N is an integer equal to 2 or larger;
• performing in each of the N consecutive image frames, the following:
• detecting corner points in the image frame,
• dividing the image frame into multiple areas, and
• recording distribution of the corner points in each of the multiple areas of the image frame in order to obtain a description vector of the image frame;
• wherein the dividing of the image frame into multiple areas, and the recording of the distribution of the corner points in each of the multiple areas to obtain the description vector of the image frame, comprises:
• dividing the image frame to obtain M areas, recording each of the M areas whether a corner point exists in;
• obtaining the description vector of the image based on a length of M, wherein the description vector indicates the existing state of the corner points in the M areas, wherein M represents an integer greater than 1, wherein for each area in the M areas, if corner points are existed in, recording as “1”, if no corner points are existed in, recording as “0”, wherein the recorded “1”s are utilized to obtain the description vector of each image in order to obtain the length of M;
• calculating a number of areas according to the description vector of the image frame over the N consecutive image frames, wherein an existing state of the corner points has changed;
• determining whether the N consecutive image frames are stable, based on the number of areas which the existing state of the corner points has changed over the N consecutive image frames.