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

Global motion vector estimating method, monitoring video stabilizing method, and device

A global motion vector and motion vector technology, applied in TV, color TV, image communication, etc., can solve the problems of long time delay and low efficiency of video image stabilization processing methods, achieve real-time processing, reasonable technology selection, and complex calculation low degree of effect

Active Publication Date: 2016-05-25
SUZHOU KEDA TECH
View PDF8 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Therefore, the technical problem to be solved by the present invention is to overcome the defects of long time delay and low efficiency of the video image stabilization processing method in the prior art

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
  • Global motion vector estimating method, monitoring video stabilizing method, and device
  • Global motion vector estimating method, monitoring video stabilizing method, and device
  • Global motion vector estimating method, monitoring video stabilizing method, and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] In this embodiment, a monitoring video image stabilization method is provided, which can be used to process the image of the monitoring video, remove the influence of shaking on the image, and improve the quality of the image. The monitoring video image stabilization method in the present embodiment comprises the following steps, such as figure 1 Shown:

[0059] The first step is to initialize the anti-shake. This step is used to obtain the detection threshold of the feature points. This step is not performed every time, but only in the initial stage of anti-shake and after the anti-shake processing fails. The specific steps are as follows, such as figure 2 Shown:

[0060] Step 1, perform N times downsampling processing on the input image components of one frame in the horizontal and vertical directions respectively, and N can be determined according to the size of the input image. For the 1080p size image in the present invention, N can be set to 4.

[0061] Step ...

Embodiment 2

[0083]This embodiment provides a global motion vector estimation method, which can be used in the image stabilization process in Embodiment 1, and can also be used in other processes that need to obtain a global motion vector. The global motion vector estimation in this embodiment The method includes the following steps:

[0084] S1. Downsampling the current frame image in horizontal and vertical directions.

[0085] S2. Perform feature point detection on the downsampled current frame image to obtain feature points, and perform FAST feature point detection on the downsampled image using a feature point detection threshold. The feature point detection threshold here can be preset, or can be obtained through adjustment in other ways.

[0086] S3. For the detected feature points, extract image blocks centered on the feature points of the current frame image, and perform block matching on the previous frame image within the search range. The block matching here is only correspond...

Embodiment 3

[0099] A monitoring video image stabilization method is provided in this embodiment, comprising the following steps:

[0100] S31. Acquire the global motion vector, which may use the global motion vector acquisition method in Embodiment 2, or other appropriate global motion acquisition methods in the prior art.

[0101] S32. Perform smoothing processing on the global motion vector to obtain a global motion smoothing vector. Accumulate the global motion vectors after initial anti-shake, and use the Kalman filtering method to smooth and filter the accumulated global motion vectors, and obtain the filtered motion vectors as global motion smoothing vectors.

[0102] S33. Calculate a shaking motion vector according to the difference between the global motion smoothing vector and the global motion vector.

[0103] S34. Determine whether the shake motion vector exceeds a preset range, and if not, perform image compensation according to the shake motion vector, output a stabilized im...

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

This invention provides a global motion vector estimating method and a monitoring video stabilizing method. A final global motion vector is computed according to a global motion vector of an upper sampling image and a corrected global motion vector; feature points are detected and matched in a lower sampling image to quickly estimate a global motion; and then, block matching is performed on the matched feature points; the block matching has higher accuracy and efficiency. A jitter motion vector is computed according to the difference between a global motion smooth vector and the global motion vector; whether the jitter motion vector is out of a preset range or not is judged; if not, an image compensation is performed according to the jitter motion vector to output video stabilizing images. By adopting the methods provided by the invention, aiming at the characteristics of the monitoring video, the images are stabilized; the technical selection is more reasonable and specific; the algorithm with low complexity is selected on the premise of ensuring an effective algorithm; and thus, the methods are more efficient in real time.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a method for estimating a global motion vector and a method and device for image stabilization of a monitoring video. Background technique [0002] With the development of surveillance technology, there are more and more video surveillance applications. Surveillance cameras will vibrate in many applications, for example, the camera at a traffic intersection will vibrate due to wind or the vibration of passing vehicles. Due to the vibration or shaking of the camera, the video image is unstable, and the impact of the high-zoom camera is more obvious. [0003] Unstable images tend to fatigue the viewer's vision. On the contrary, a stable video image can better express the image details, thereby improving the quality of video surveillance. At the same time, the stable image provides a video source that is more conducive to compression for the back-end digital video recording ...

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): H04N5/14H04N5/232
CPCH04N5/144H04N23/681
Inventor 赵海宾汤峰峰章勇曹李军
Owner SUZHOU KEDA 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