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

Image stabilizing method capable of accurate detection of complex jittering in video sequence

A video sequence, complex technology, applied in color TV parts, TV system parts, TV and other directions, can solve the problem of motion transformation parameter error, limit engineering application and so on

Inactive Publication Date: 2015-11-25
INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional gradient optical flow method can be used to calculate the transformation parameters including translation, rotation and scaling motion, and has high precision, but when the motion between video sequences is discontinuous, the motion transformation parameters calculated by the traditional gradient optical flow method have Large error limits its engineering application

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
  • Image stabilizing method capable of accurate detection of complex jittering in video sequence
  • Image stabilizing method capable of accurate detection of complex jittering in video sequence
  • Image stabilizing method capable of accurate detection of complex jittering in video sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] 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 specific embodiments and with reference to the accompanying drawings.

[0040] Firstly, an L-level pyramid model is constructed for each frame of image. The original image is regarded as the 0th layer, which has the highest resolution, which is sequentially down-sampled from the 0th layer, and the L+1 layer is obtained by sampling the L-th layer image after smoothing and interlacing. Then, the motion vector estimation is performed on the topmost layer, and the motion transformation parameters between video sequences are roughly estimated, and this parameter is used as the initial estimation of the next layer, and iterates successively until the 0th layer.

[0041] 1) Set the number of pyramid layers L=4, and delineate the calculation area Ω.

[0042] 2) Perform L-layer downsampling on two ad...

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 image stabilizing method capable of accurate detection of complex jittering in a video sequence. According to the method, first of all, pyramid decomposition is carried out on an image, through performing sampling on an original 0-th layer in an interlacing inter-row and inter-column mode after smoothing, a high layer with quite low resolution is obtained, then from the top layer, affine motion parameters between corresponding layers of two frames of images are calculated, afterwards, the calculated affine motion parameters are transmitted to a layer with quite high resolution, parameter iteration is performed, and accurate affine motion parameters can be solved through iteration calculation to the bottom of a pyramid. According to the invention, a good image stabilizing effect can be obtained through performing compensation on a jittering video according to the solved accurate affine motion parameters. Experiments show that an optical flow algorithm combining a pyramid multi-resolution layered technology solves the problem of quite large errors caused by motion estimation by use of a conventional gradient optical flow method under the condition of discontinuous motion between video sequences, and the method can obtain the good image stabilizing effect for the motion sequences comprising such complex motion as rotation, zooming, translation and the like.

Description

technical field [0001] The invention belongs to the field of electronic image stabilization, and relates to an image stabilization method capable of accurately detecting complex shaking in video sequences. Background technique [0002] Irregular motion will appear in the video sequence due to the change of carrier posture or motion interference, and the external performance is video jitter. Shaky video is not conducive to observation and extraction of useful information in the video, so image stabilization processing of shaky video has important application prospects in image recognition, image tracking and other fields. [0003] The traditional gradient optical flow method can be used to calculate the transformation parameters including translation, rotation and scaling motion, and has high precision, but when the motion between video sequences is discontinuous, the motion transformation parameters calculated by the traditional gradient optical flow method have The large e...

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
IPC IPC(8): H04N5/232H04N5/14G06T7/20
Inventor 赖丽君徐智英张栩铫
Owner INST OF OPTICS & ELECTRONICS - CHINESE ACAD OF SCI
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