Sound-based portrait automatic tracking method and device, intelligent terminal and medium
An automatic tracking and intelligent terminal technology, applied in image communication, color TV parts, TV system parts, etc., can solve the problem that the camera cannot rotate in time to capture the speaker, and achieve a good user experience effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] Such as figure 1 As shown in , an embodiment of the present invention provides a sound-based automatic portrait tracking method, which can be applied to a smart terminal with a camera, and the camera can be raised and lowered and the shooting angle can be rotated. In an embodiment of the present invention, the method includes the following steps:
[0049] Step S100, real-time detection and acquisition of human speech;
[0050] When the present invention is actually implemented, it is necessary to pre-set the smart terminal with camera function to support far-field voice, and the camera structure supports up, down, left and right angle rotation or the camera has a super wide-angle function. For example, the method of the present invention is implemented on a smart TV equipped with a liftable and rotatable camera, or a liftable and rotatable camera is pre-installed on a smart terminal without a camera.
[0051] In the embodiment of the present invention, the smart termina...
Embodiment 2
[0065] Such as figure 2 As shown, a sound-based automatic portrait tracking method in this specific application embodiment includes the following steps;
[0066] This embodiment takes the smart TV system as an example. The smart TV system needs to meet the requirements that the smart device supports far-field voice and the smart device camera structure supports up, down, left and right angle rotation or the smart device camera has a super wide-angle function.
[0067] Step 10: When the smart TV detects a person speaking in the camera startup scene mode, it combines voice technology to obtain the location information of the current speaker.
[0068] For example, in the camera application, you can turn on / off the sound-based automatic portrait tracking function in the setting menu (such as the [Sound-transformed portrait automatic tracking] function), or there is no such menu, and the default [Sound-transformed portrait automatic tracking] function (voice-based automatic portr...
Embodiment 3
[0081] Such as figure 2 As shown, Embodiment 3 of the present invention provides a sound-based automatic portrait tracking method, comprising the following steps:
[0082] This embodiment realizes the automatic portrait tracking function of the camera (automatic portrait tracking based on sound), and the conditions that need to be met are that the TV chip SOC needs to be able to run the camera portrait automatic focus function algorithm or the performance of the TV SOC needs to be separately increased by at least 1 NPU (embedded neural network) Network processor) computing power, the camera portrait auto-focus algorithm runs on the NPU alone.
[0083] Step S101: When the camera is turned on in the scene mode, when a person is detected to speak, combined with voice technology, the location information of the current speaker is acquired.
[0084] For example, a smart TV opens a camera function application, obtains a currently captured picture of the camera, and displays it on ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


