Video image processing method, device and terminal equipment
A technology of video image and processing method, applied in the field of information processing, can solve the problems of not achieving the expected advertising effect, disturbing the normal video viewing experience of the audience, and disgusting the audience, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] figure 1 is a flow chart showing a video image processing method according to Embodiment 1 of the present invention. The method is performed by a device comprising video image processing means.
[0044] refer to figure 1 , in step S110, detecting at least one target object from the video image, and determining feature points of at least one target object.
[0045] In this step, the video image may be an image in a live video, or an image in a video that is pre-recorded and played later. The target object is an object that exists in the video image and is easy to be viewed by the audience, including but not limited to: human body (including human face and body parts, etc.), actions (including postures and gestures, etc.), background, etc. The target object generally has a certain number of feature points. For example, the traditional 68 feature points in the face mainly include the eyes, nose, mouth, and facial contours. For example, the hand mainly includes the featu...
Embodiment 2
[0060] figure 2 Shown is a flowchart of a video image processing method according to Embodiment 2 of the present invention. The video image processing method in this embodiment can be executed by any device with data collection, processing and transmission functions, including but not limited to mobile terminals and PCs. This embodiment takes a mobile terminal as an example to describe the video image processing method provided by the embodiment of the present invention, and other devices may refer to this embodiment for execution.
[0061] refer to figure 1 , in step S210, at least one target object is detected from the video image, and feature points of at least one target object are determined.
[0062] The video image may be an image corresponding to a video data frame in the video, and each image has a certain target object, such as a person, a gesture, a background, and the like. Detecting the target object in the video image and determining the feature points may be...
Embodiment 3
[0100] image 3 Shown is a flowchart of a video image processing method according to Embodiment 3 of the present invention.
[0101] refer to image 3 , in step S310, at least one target object is detected from the video image, and feature points of at least one target object are determined.
[0102] Wherein, the step content of the above-mentioned step S310 is the same as that of the step S110 in the first embodiment above, and will not be repeated here.
[0103] In step S320, the type of at least one target object is determined according to the feature points of at least one target object.
[0104] Here, after the feature points of the target object are obtained, the type of the target object can be determined by using an existing related detection, classification or learning method. Wherein, the type of the target object includes but not limited to: face type, background type, hand type and action type. Among them, the face type is used to indicate that the face occupie...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


