Unlock instant, AI-driven research and patent intelligence for your innovation.

Timing smoothing method, device and electronic equipment

A smoothing and time-sequential technology, applied in image enhancement, image analysis, instrumentation, etc., can solve the problems of difficult time-series smoothing, different original probability values, etc.

Active Publication Date: 2020-12-18
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the original probability values ​​of different targets in the current image frame are different, and it is difficult to accurately time-series smooth the different targets using the same weighting coefficient.

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
  • Timing smoothing method, device and electronic equipment
  • Timing smoothing method, device and electronic equipment
  • Timing smoothing method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0068] figure 1 is a flowchart of a time series smoothing method shown according to an exemplary embodiment, such as figure 1 As shown, the timing smoothing method is used in a terminal, and includes the following steps.

[0069] In step S11, a first weighting coefficient is calculated based on the utility value of the original probability value of the target in the current image fra...

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 present disclosure relates to timing smoothing methods, devices and electronic equipment. The method includes: calculating a first weighting coefficient based on the utility value of the original probability value of the target in the current image frame, the first weighting coefficient is positively related to the utility value, and the utility value is used to represent the original probability value for Determine the effectiveness of the characteristics of the target; use the first weighting coefficient as a weighting coefficient of the original probability value of the target in the current image frame and normalize it with the smoothed probability value of the target in the previous image frame The weighted average is used to obtain the smooth probability value of the target in the current image frame. The weighted coefficient of the original probability value of the target in the current image frame can be dynamically determined based on the utility value of the original probability value of the target in the current image frame, so that the weighted coefficient is more suitable for the target, so as to achieve different targets in the current image frame. The weighting coefficient suitable for the target can be used for more accurate timing smoothing of the target.

Description

technical field [0001] The present disclosure relates to the technical field of deep learning algorithms, in particular to a time series smoothing method, device and electronic equipment. Background technique [0002] In the related art, the target in the image frame can be analyzed by a preset image analysis algorithm to determine the characteristics of the target in the image frame, for example, to determine whether the pixel in the image frame belongs to the foreground area, because the image analysis algorithm may have Therefore, the output of some image analysis algorithms can be a probability value (hereinafter referred to as the original probability value), for example, the output analysis result is the probability that the pixel in the image frame belongs to the foreground area. When image analysis algorithms are used to process multiple consecutive image frames, due to the possibility of randomly distributed noise signals, the original probability value of the targe...

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): G06T5/00G06T5/50
CPCG06T5/50G06T2207/20216G06T5/70
Inventor 宋丛礼于永航郑文
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD