CN106161988A - A kind of augmented reality video generation method - Google Patents

Abstract

The invention discloses a kind of augmented reality video generation method, including: video camera shooting comprises the first video-frequency band of portrait image；In the first video-frequency band, identify and separate portrait image, form portrait video flowing；The template video of described portrait video flowing with user's selection is synthetically formed result video, and the real-time video that the present invention utilizes the video superimpose technology of augmented reality to realize on mobile phone merges, it is convenient to provide experience and the service of augmented reality for people.

Description

A method for generating augmented reality video

technical field

The present invention relates to the technical field of video image processing, in particular to an augmented reality video generation method.

Background technique

In recent years, the computing power of mobile intelligent terminals has developed rapidly, and the multimedia processing performance has been continuously improved. At the same time, the terminal integrates modules such as cameras and GPS, which provides favorable conditions for the application of augmented reality technology on mobile intelligent terminals. Combined with the real-time online , intelligent perception, wide coverage and other characteristics, can study the specific application scheme of the augmented reality system for mobile intelligent terminals, realize the mobile application of augmented reality technology with the help of mobile Internet, and form new value-added services on the mobile Internet. The augmented reality system has the characteristics of combination of real and virtual, real-time interaction, and three-dimensional registration, which can make the system's windows, graphics and objects in the real environment produce superimposed visual effects, bringing people a real experience of augmented reality scenes .

Contents of the invention

The purpose of the present invention is to provide a method for generating augmented reality video, which uses augmented reality video overlay technology to realize real-time video merger on mobile phones, and can conveniently provide people with augmented reality experience and services.

In order to achieve the above object of the invention, the present invention provides a method for generating augmented reality video, including:

The camera captures the first video segment containing the portrait image, identifies and separates the portrait image in the first video segment, and forms a portrait video stream;

Combining the portrait video stream with the template video selected by the user to form a result video.

Preferably, the identifying and separating the portrait image in the first video segment to form the portrait video stream specifically includes: performing edge detection on the portrait of each frame, and identifying the pixel located inside the edge of the portrait as the target pixel, The target pixels in each frame are extracted to form a portrait video stream.

Preferably, the number of frames of the portrait video stream and the template video is the same, and pixel addition is performed on the portrait video stream and the template video to realize video merging.

Preferably, the pixels of the person image in the portrait video stream are used as the foreground video in the result video.

Preferably, the portrait video stream is synthesized with the template video stream to form a result video stream, and the portrait video stream is at a predetermined position in the result video stream.

Preferably, the enhanced data applied by the user to the target portrait is superimposed on the video frame image of the result video, the enhanced data includes interactive elements and/or interactive events, wherein the interactive elements include images, audio, web pages, text, 3D models, One or more of URI addresses.

Preferably, the template video is saved locally as a configuration file, or the template video is saved as a configuration file on a remote server for the local client to download.

The invention utilizes the augmented reality video overlay technology to realize the real-time video combination on the mobile phone, and can conveniently provide augmented reality experiences and services for people. It can convert the background of the character video taken at will. For example, the user can shoot a character video at home, and then convert the video background to outer space, making people feel interstellar.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings on the premise of not paying creative labor:

FIG. 1 is a schematic flowchart of a method for generating an augmented reality video according to an embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

An embodiment of the present invention will be described in detail below with reference to FIG. 1 .

Referring to FIG. 1 , it is a schematic flow chart of a method for generating an augmented reality video in an embodiment of the present invention. The method for generating an augmented reality video in this embodiment includes the following steps:

S101: The camera shoots a first video segment containing a portrait image;

S102: Identify and separate the portrait image in the first video segment to form a portrait video stream; in this step, identifying and separating the portrait image can adopt edge detection for the portrait of each frame, and place the pixels inside the edge of the portrait The point is identified as the target pixel, and the target pixel in each frame is extracted to form a portrait video stream.

S103: Synthesize the portrait video stream with the template video selected by the user to form a result video. In this embodiment, the number of frames of the first video segment taken needs to be the same as the number of template video frames, so that the obtained portrait video stream and the template video frame number are the same, and video synthesis uses the portrait video stream and template video for pixel addition. Implement video merging.

In order to obtain a better effect, it is preferable to use the pixels of the person image in the portrait video stream as the foreground video in the resulting video.

In another embodiment, in order to obtain a better result video, when the portrait video stream is synthesized with the template video stream to form a result video stream, the portrait video stream is set at a predetermined position in the result video stream.

In another embodiment, in order to make the resulting video interactive, the enhanced data applied by the user to the target portrait can also be superimposed on the video frame image of the resulting video, the enhanced data includes interactive elements and/or interactive events, wherein The interactive elements include one or more of images, audio, web pages, texts, 3D models, and URI addresses. When the augmented reality video generated by this method is played after adding interactive elements and interactive events, the user can interact, for example, by clicking on a character's clothing, the user can enter the clothing purchase link.

In the embodiment of the present invention, the template video is saved locally in the form of a configuration file, or the template video is saved in the form of a configuration file on a remote server for the local client to download. The template video is usually provided by a software service provider, or it can be Created and shared by other users, only need to meet the predetermined format.

The invention utilizes the augmented reality video overlay technology to realize the real-time video combination on the mobile phone, and can conveniently provide augmented reality experiences and services for people. It can convert the background of the character video taken at will. For example, the user can shoot a character video at home, and then convert the video background to outer space, making people feel interstellar.

All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and/or steps.

Any feature disclosed in this specification (including any appended claims, abstract and drawings), unless expressly stated otherwise, may be replaced by alternative features which are equivalent or serve a similar purpose. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features.

The present invention is not limited to the foregoing specific embodiments. The present invention extends to any new feature or any new combination disclosed in this specification, and any new method or process step or any new combination disclosed.

Claims (7)

1. an augmented reality video generation method, it is characterised in that including:

Video camera shooting comprises the first video-frequency band of portrait image；

In the first video-frequency band, identify and separate portrait image, form portrait video flowing；

The template video of described portrait video flowing with user's selection is synthetically formed result video.

2. video generation method as claimed in claim 1, it is characterised in that: described in the first video-frequency band Identify and separate portrait image, form portrait video flowing particularly as follows: the portrait of each frame is carried out rim detection, And will be located in the pixel within described portrait edge and regard as object pixel, by the object pixel in each frame Extract, form portrait video flowing.

3. video generation method as claimed in claim 2, it is characterised in that: described portrait video flowing and mould Plate video frame number is identical, and portrait video flowing and template video carry out pixel addition, it is achieved video merges.

4. video generation method as claimed in claim 3, it is characterised in that: the personage in portrait video flowing The pixel of image is as the foreground video in result video.

5. video generation method as claimed in claim 4, it is characterised in that: by described portrait video flowing with Template video stream is synthetically formed result video flowing, and described portrait video flowing is in predetermined in result video flowing Position.

6. the video generation method as according to any one of Claims 1-4, it is characterised in that by user Put on target person picture strengthen data investigation on the video frame images of result video, described enhancing packet Include interactive elements and or alternative events, wherein interactive elements includes image, audio frequency, webpage, text, 3D One or more in model, URI address.

7. video generation method as claimed in claim 1, it is characterised in that described template video is with configuration Document form is saved in this locality, or is saved on far-end server for local client download.