Picture focusing method, apparatus, terminal, and corresponding storage medium
AssigneeKandao Technology Co., Ltd.
InventorsRui MA, Panpeng LI
Life of this patent
Estimating the term…
Abstract
Provided by the present invention is a picture focusing method, comprising: acquiring a video picture, and, according to an instruction command, determining a target object in the video picture; determining picture depth information of a video picture region in which the target object is located; acquiring parameter information of a camera corresponding to multiple video picture frames; using the picture depth information of the video picture region and the parameter information of the camera as the input of a preset focusing neural network model; and using focus adjustment information of the camera to perform a focus adjustment operation on the camera.
Claims11
A picture focusing method, comprising the following steps:
- acquiring a video picture, and determining a target object in the video picture according to an instruction;
- determining picture depth information of a video picture region where the target object is located according to sharpness change information of the video picture region where the target object is located in multiple video picture frames;
- acquiring parameter information of a shooting camera corresponding to the multiple video picture frames;
- enabling a focusing neural network model, which is preset, to output focusing adjustment information of the shooting camera corresponding to the video picture by taking the picture depth information of the video picture region and the parameter information of the shooting camera as inputs of the focusing neural network model, which is preset;
- and
- performing a focusing operation on the shooting camera by using the focusing adjustment information of the shooting camera.
A picture focusing apparatus, comprising:
- a video picture acquisition module, configured to acquire a video picture, and determine a target object in the video picture according to an instruction;
- a picture depth information determination module, configured to determine picture depth information of a video picture region where the target object is located according to sharpness change information of the video picture region where the target object is located in multiple video picture frames;
- a parameter information acquisition module, configured to acquire parameter information of a shooting camera corresponding to the multiple video picture frames;
- a focusing adjustment information output module, configured to enable a focusing neural network model, which is preset, to output focusing adjustment information of the shooting camera corresponding to the video picture by taking the picture depth information of the video picture region and the parameter information of the shooting camera as inputs of the focusing neural network model, which is preset;
- and
- a focusing module, configured to perform a focusing operation on the shooting camera by using the focusing adjustment information of the shooting camera.
A computer readable storage medium, storing instructions executed by a processor, wherein the processor executes the instructions to provide a picture focusing method, comprising:
- acquiring a video picture, and determining a target object in the video picture according to an instruction;
- determining picture depth information of a video picture region where the target object is located according to sharpness change information of the video picture region where the target object is located in multiple video picture frames;
- acquiring parameter information of a shooting camera corresponding to the multiple video picture frames;
- enabling a preset focusing neural network model to output focusing adjustment information of the shooting camera corresponding to the video picture by taking the picture depth information of the video picture region and the parameter information of the shooting camera as inputs of the preset focusing neural network model;
- and
- performing a focusing operation on the shooting camera by using the focusing adjustment information of the shooting camera.
Dependencies are inferred from the claim text.