Real-time video image stabilization method based on timing grid flow superimposing

A real-time video and grid technology, applied in the field of image processing, can solve unsolvable problems

Active Publication Date: 2018-11-13
ZHEJIANG UNIV
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, none of them can solve the need for video stabilization in NoMotion scenarios to keep the lens completely still in the entire video sequence.

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
  • Real-time video image stabilization method based on timing grid flow superimposing
  • Real-time video image stabilization method based on timing grid flow superimposing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.

[0021] figure 1 It is a flow chart of the real-time video image stabilization method based on time-series grid stream superposition provided by the embodiment. Such as figure 1 As shown, the real-time video image stabilization method includes the following steps:

[0022] S101. Acquire a piece of video, and downsample each video frame to a fixed size.

[0023] Downsampling can speed up the calculation rate and ensure real-time performance. Moreover, similar processing speeds can be maintained for different videos. In general, downsampling a video frame with a resolu...

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 a real-time video image stabilization method based on timing grid flow superimposing. The real-time video image stabilization method comprises the steps that 1, each obtained video frame is down-sampled to the fixed size; 2, the first frame is taken as an initial reference frame, and a reference frame feature point is acquired; 3, video frame feature points are extracted and matched with the reference frame feature point, the optimal matched feature point of the video frame feature points is obtained, and a global homography matrix is constructed; 4, a part of the videoframe feature points are removed by means of the global homography matrix; 5, grids are distributed to the video frames, and motion vectors of grid vertexes are obtained according to the video framefeature points; 6, the reference frame changes in cycles, and motion vectors of the grid vertexes in each cycle are obtained by adopting a time domain superimposing method according to the reference frame of the cycle; and 7, motion vectors of pixels are calculated according to the motion vectors of the grid vertexes, and the pixels are adjusted according to the motion vectors of the pixels. According to the method, a lens is kept to be completely static in the overall video sequence.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a real-time video image stabilization method based on time series grid stream superposition. Background technique [0002] With the development of communication technology, short videos have gradually become the main carrier of mass entertainment consumption. The creation of short videos involves the production of some special effects, and the production of these short video special effects has very high requirements on the stability of the video. A local specific part of the element presents a dynamic effect. For shooting with handheld devices, slight jitter is unavoidable, but such jitter will greatly affect the generation of video special effects. Therefore, it is of great practical significance to use fast and effective image stabilization to remove shaking in video. [0003] The existing video image stabilization algorithms, whether based on 2D image transforma...

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): G06T7/246G06T5/00H04N5/14
CPCG06T5/002G06T7/246G06T2207/10016H04N5/144
Inventor 孙凌云帅世辉杨智渊尤伟涛杨昌源
Owner ZHEJIANG UNIV
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