Method and apparatus for controlling image display

Patent metadata

Field	Value
Publication number	US-11265529-B2
Application number	US-201916513142-A
Country	US
Kind code	B2
Filing date	Jul 16, 2019
Priority date	Jul 25, 2018
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

A method of controlling image display includes: receiving an image capture instruction from a client device, wherein the image capture instruction includes a photographing direction, and the photographing direction is determined by the client device according to a relative position relationship between a position of the client device and a user-specified display position; controlling an image capture device to perform image capture according to the photographing direction, to obtain a depth image comprising a target object image; extracting the target object image from the depth image; and sending the target object image to the client device such that the client device displays the target object image at the display position.

First claim

What is claimed is:

1. A method of controlling image display, the method being applied to a server, comprising:
receiving an image capture instruction from a client device, wherein the image capture instruction comprises a photographing direction, and the photographing direction is determined by the client device according to a relative position relationship between a position of the client device and a user-specified display position;
controlling an image capture device to perform image capture according to the photographing direction, to obtain a depth image comprising a target object image;
extracting the target object image from the depth image; and
sending the target object image to the client device such that the client device displays the target object image at the user-specified display position,
wherein the image capture device comprises at least one camera, and the method further comprises:
pre-storing a first corresponding relationship between a device identifier corresponding to each of the at least one camera and a photographing direction; and

wherein controlling the image capture device to perform image capture according to the photographing direction, to obtain the depth image comprising the target object image comprises:
obtaining at least two device identifiers corresponding to the photographing direction according to the photographing direction and the first corresponding relationship; and
controlling a camera corresponding to each of the at least two device identifiers to perform image capture for a target object, to obtain at least two depth images each of which comprises the target object image.

2. The method of claim 1 ,
wherein extracting the target object image from the depth image comprises:
extracting at least two target object images respectively from the at least two depth images; and
obtaining a spliced target object image by performing splicing for the at least two target object images.

3. The method of claim 2 , wherein extracting the at least two target object images respectively from each of the at least two depth images comprises:
obtaining corresponding image regions in the at least two depth images according to the photographing directions corresponding to the at least two depth images respectively; and
extracting the at least two target object images from the corresponding image regions in the at least two depth images.

4. The method of claim 1 , further comprising:
pre-storing a recognition model for recognizing the target object;
wherein extracting the target object image from the depth image comprising:
recognizing and extracting the target object image from the depth image by performing image recognition for the depth image according to the recognition model of the target object.

5. An apparatus for controlling image display, comprising:
a memory configured to store a computer program; and
a processor coupled with the memory and configured to execute the computer program stored in the memory and configured to:
receive an image capture instruction from a client device, wherein the image capture instruction comprises a photographing direction, and the photographing direction is determined by the client device according to a relative position relationship between a position of the client device and a user-specified display position;
control an image capture device to perform image capture according to the photographing direction, to obtain a depth image comprising a target object image;
extract the target object image from the depth image; and
send the target object image to the client device such that the client device displays the target object image at the user-specified display position,
wherein the image capture device comprises at least one camera;
wherein the memory is configured to pre-store a first corresponding relationship between a device identifier corresponding to each of the at least one camera and a photographing direction; and
wherein the processor is configured to:
obtain at least two device identifiers corresponding to the photographing direction according to the photographing direction and the first corresponding relationship stored in the memory; and
control a camera corresponding to each of the at least two device identifiers to perform image capture for a target object, to obtain at least two depth images each of which comprises the target object image.

6. The apparatus of claim 5 ,
wherein the processor is configured to:
extract at least two target object images respectively from the at least two depth images; and
obtain a spliced target object image by performing splicing for the at least two target object images.

7. The apparatus of claim 6 , wherein the processor is configured to:
obtain corresponding image regions in the at least two depth images according to the photographing directions corresponding to the at least two depth images respectively; and
extract the at least two target object images from the corresponding image regions in the at least two depth images.

8. The apparatus of claim 5 , wherein the memory is configured to pre-store a recognition model for recognizing the target object; and
wherein the processor is configured to: recognize and extract the target object image from the depth image by performing image recognition for the depth image according to the recognition model of the target object stored in the memory.

9. A non-transitory computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the method of claim 1 .

Assignees

• Beijing Xiaomi Mobile Software Co Ltd

Inventors

• Ji Jiasong
• Lin Xingsheng

Classifications

• H04N21/6587

  Control parameters, e.g. trick play commands, viewpoint selection · CPC title

• H04N13/167 Primary

  Synchronising or controlling image signals · CPC title

• H04N21/2387

  Stream processing in response to a playback request from an end-user, e.g. for trick-play · CPC title

• H04N2013/0092

  Image segmentation from stereoscopic image signals · CPC title

• H04N7/18

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title