A terminal shooting method, terminal and computer-readable storage medium

A terminal and memory technology, applied in the field of image processing, can solve problems such as image quality reduction, focusing on other objects, blurring of the shooting subject, etc., to achieve the effect of ensuring the shooting quality

Active Publication Date: 2020-07-10
ZHUHAI DAHENGQIN TECH DEV CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, when shooting an object, it is all shot through a preset ROI, and the size of the ROI is fixed during the shooting process. Subjects of the same type occupy less positions in a fixed ROI, so it is easy to focus on other objects during shooting, making the subject blurred in the image and reducing image quality

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A terminal shooting method, terminal and computer-readable storage medium
  • A terminal shooting method, terminal and computer-readable storage medium
  • A terminal shooting method, terminal and computer-readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0071] The first embodiment of the present invention proposes a terminal shooting method, which can be applied to a terminal with a shooting function.

[0072] Here, the terminal described above may be a fixed terminal with a display screen, or a mobile terminal with a display screen.

[0073] The above-mentioned fixed terminal may be a computer, etc., and the above-mentioned mobile terminal includes, but is not limited to, a mobile phone, a notebook computer, a camera, a PDA, a PAD, a PMP, a navigation device, and the like. The terminal may be connected to the Internet, wherein the connection method may be through a mobile Internet network provided by an operator, or through a wireless access point for network connection.

[0074] Here, if the mobile terminal has an operating system, the operating system can be UNIX, Linux, Windows, Android (Android), Windows Phone and so on.

[0075] It should be noted that there is no limitation on the type, shape, size, etc. of the displa...

no. 2 example

[0093] Figure 5 It is a flow chart of the second embodiment of the method for shooting by the terminal in the embodiment of the present invention, as shown in Figure 5 As shown, the process includes:

[0094] Step 501: Acquire an initial shot image of a shooting scene.

[0095] Exemplarily, the currently set ROI is used to acquire the initial captured image of the shooting scene, or the initial captured image of the shooting scene is acquired when no ROI is set. Here, the currently set ROI may be the default ROI of the terminal or the ROI automatically adjusted during the last shooting. If no ROI is set, the obtained image may be blurred. It can be understood that since the subject is a special object, the clarity of the subject in the initial captured image obtained regardless of whether the ROI is set will be affected. ROI (focus area) to improve the accuracy of focusing on special objects and the overall quality of the image.

[0096] The special objects mentioned in ...

no. 3 example

[0118] Figure 8 It is a flow chart of the third embodiment of the method for shooting by the terminal in the embodiment of the present invention, as shown in Figure 8 As shown, the process includes:

[0119] Step 801: Acquire an initial shot image of a shooting scene.

[0120] Step 802: Identify the subject in the initial captured image.

[0121] Exemplarily, the deep learning-based image recognition technology trains different images to obtain a recognition model capable of image recognition; uses the obtained recognition model to recognize objects in the initial captured image, and determines different objects in the initial captured image.

[0122] Specifically, firstly, it is recognized that the initially captured image contains multiple objects, and further, the terminal automatically recognizes the shooting subject through a preset recognition strategy.

[0123] Here, the preset recognition strategy may include: obtaining the first parameter to the Nth parameter of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the present invention discloses a terminal shooting method, a terminal, and a computer-readable storage medium, wherein the method includes: acquiring an initial shooting image of a shooting scene; identifying the subject in the initial shooting image, and determining the shooting subject in the initial shooting image The location information of the subject; adjust the ROI of the region of interest in the initial shot image according to the location information of the subject; the percentage of the area occupied by the subject in the adjusted ROI is greater than the first threshold; use the adjusted ROI as the focus area for the shooting scene Shooting is performed to obtain a final shot image. In this way, the size of the ROI is adaptively adjusted according to the size of the subject to improve the accuracy of focusing on the subject.

Description

technical field [0001] The present invention relates to image processing technology, in particular to a terminal shooting method, a terminal and a computer-readable storage medium. Background technique [0002] Regions of Interest (ROI) are the regions in the image that most arouse the user's interest and can best express the image content. If these regions can be extracted, the efficiency and accuracy of image processing and analysis will be greatly improved. Today, ROI extraction technology has been applied in many fields, such as JPEG2000 compression coding, target area positioning and identification in machine vision, automatic identification of subtitles and signs in video information, automatic extraction and identification of license plate areas in intelligent transportation systems, Medical image analysis, etc., ROI extraction technology has a broad market potential. [0003] At present, when shooting an object, it is all shot through a preset ROI, and the size of t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04N5/232G06K9/32
CPCG06V10/25H04N23/67H04N23/62
Inventor 郭启凡
Owner ZHUHAI DAHENGQIN TECH DEV CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products