Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electronic image stabilization algorithm based on vehicle-mounted rearview mirror system

A vehicle-mounted rearview mirror and electronic image stabilization technology, applied in the field of image processing, can solve problems such as video frame sequence jitter, and achieve the effects of short time consumption, high accuracy and accurate parameters

Pending Publication Date: 2021-08-13
HUBEI UNIV OF TECH
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide an electronic image stabilization method to solve the problem of video frame sequence jitter caused by high-frequency unintentional motion caused by wind excitation and road bumps when the vehicle is driving

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
  • Electronic image stabilization algorithm based on vehicle-mounted rearview mirror system
  • Electronic image stabilization algorithm based on vehicle-mounted rearview mirror system
  • Electronic image stabilization algorithm based on vehicle-mounted rearview mirror system

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0083] Specific implementation mode one: the following combination figure 1 , illustrate the specific embodiment of the present invention, concrete steps are as follows:

[0084] (1) Sampling of the original video frame is carried out, and the data volume of the processing video frame is reduced according to the method of variable sampling interval;

[0085] (2) Carry out partition processing on the high-information frame sequence sampled in step (1), which are the body area and the non-body area respectively. The corners of the body area are active motion, and the non-body area is local motion. Set the body area The number of corner points is X, the number of corner points in the non-body area is Y, and then the SURF algorithm is used to detect and track the corner points;

[0086] (3) Use the optimized RANSAC algorithm to eliminate the mismatching of the feature points extracted in step (2). The feature points of the body area and non-body area after elimination are U, V, and...

specific Embodiment approach 2

[0091] Specific implementation mode two: the following combination figure 2 , illustrate the specific embodiment of the present invention, described step (1), because the video sequence frame that obtains is more and mostly similar, then adopt the method for variable sampling distance to carry out the video sequence frame that sampling process obtains little change, described preprocessing It is to perform Gaussian filtering on the extracted video frame sequence to suppress noise, wherein Gaussian filtering uses a two-dimensional zero-mean discrete Gaussian function as a smoothing filter, namely:

[0092]

[0093] In the formula, G(x, y) is a Gaussian function, μ is a mathematical expectation, σ 2 is the standard deviation, and (x, y) is the coordinates of the pixel.

specific Embodiment approach 3

[0094] Specific embodiment three: present embodiment is to further illustrate specific embodiment one, and in step (2), described SURF algorithm is used for extracting and tracking feature point, basic steps are as follows:

[0095] (1) Construct the Hessian matrix

[0096] The core of SURF is the Hessian matrix. The Hessian matrix H is composed of functions and partial derivatives. Each pixel can find a Hessian matrix for feature extraction, namely:

[0097]

[0098] In the formula, (x, y) is the coordinate of the pixel, f(x, y) represents the coordinate relationship of the pixel, Indicates taking two derivatives of x, Indicates to take the derivative of x and then take the derivative of y, Indicates taking two derivatives with respect to y.

[0099] The discriminant of the Hessian matrix is ​​as follows:

[0100]

[0101] Among them, H represents a matrix, and x and y are pixel coordinates.

[0102] The value of the discriminant is the eigenvalue of the H matri...

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 invention discloses an electronic image stabilization algorithm based on a vehicle-mounted rearview mirror system, and the algorithm comprises the following specific steps: extracting images of continuous adjacent frames of an original video, carrying out the preprocessing, and employing an SURF algorithm to detect and track the corresponding angular points of a vehicle body region and a non-vehicle body region in two frames; adopting an optimized RANSAC algorithm, eliminating and mismatched angular points; calculating a corresponding transformation model according to the matching points in the two frames; performing smoothing processing on motion parameters estimated by the affine transformation model; and performing frame-by-frame compensation on the video sequence by using the smoothed parameters to obtain a stable video sequence. According to the method, the motion parameters are solved by adopting a weighting method, the compensated video frame is more stable, the image stabilization effect is better, the speed is higher, and the consumed time is short.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an electronic image stabilization algorithm based on a vehicle rearview mirror system. Background technique [0002] With the development of science and technology, cars have become an inaccessible means of transportation for people. In order to solve the problem of the car's vision, car electronic rearview mirrors have gradually replaced physical rearview mirrors. However, in the actual application process, due to the influence of natural factors such as uneven road surface and wind, the obtained video is not clear, which in turn leads to the instability of the displayed video screen, which has a certain impact on the driver's observation. , so it is very important to solve this problem. [0003] At present, there are three main categories of video image stabilization methods: mechanical image stabilization, optical image stabilization, and electronic image stabilization. Mecha...

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 Applications(China)
IPC IPC(8): G06T7/246G06T7/277G06T3/00G06T5/00G06T5/20
CPCG06T7/248G06T7/277G06T5/20G06T2207/10016G06T2207/20024G06T3/02G06T5/70
Inventor 王正家吴春林何涛柯黎明王少东刘城逍陈长乐朱泽文
Owner HUBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com