Non-reference video stability quality evaluation method based on inter-frame motion smoothness

A video stabilization and quality evaluation technology, applied in the field of video processing, can solve problems such as inaccurate evaluation methods and contradictions in subjective quality evaluation

Active Publication Date: 2017-08-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a non-reference video stable quality evaluation based on inter-frame motion smoothness in view of the existing non-refe

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
  • Non-reference video stability quality evaluation method based on inter-frame motion smoothness
  • Non-reference video stability quality evaluation method based on inter-frame motion smoothness
  • Non-reference video stability quality evaluation method based on inter-frame motion smoothness

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] This embodiment describes a specific embodiment of applying a non-reference video stabilization quality evaluation method based on inter-frame motion smoothness of the present invention.

[0064] Adopt method described in the present invention, concrete realization steps are as follows:

[0065] Step A, the SURF algorithm extracts adjacent frame feature points;

[0066] Specifically in this embodiment, for the video to be evaluated, the feature points of adjacent frames are extracted, specifically:

[0067] In an image, there are many features representing image attributes or categories, including shape features, color features, texture features, etc.; in order to obtain the motion transformation relationship between frames, the image frame I is first detected t (t=1, 2,..., n, n represents the number of image frames) feature points. When extracting feature points, generally select Harris corner points or SIFT feature points (D.G.Lowe.Object recognition from local sca...

Embodiment 2

[0112] In this embodiment, the effectiveness of the present invention is verified by comparing the stabilization quality evaluation results of the stabilized video obtained by using six video stabilization algorithms and the original shaken video with the subjective evaluation results through objective calculation.

[0113] The original video data set is divided into twelve types of videos, including simple, rotation, zooming, riding, running, climbing, driving, rolling shutter, dark, crowd, large parallax and near-range object. The six video stabilization algorithms are the full-frame method (FF), the spatially and temporally optimized method (STO), bundled paths methods (PB), Adobe AfterEffects (AE) warp stabilizer, Google YouTube stabilizer, and VirtualDub Deshaker. The calculation results are shown in Table 1:

[0114] Table 1 Ranking of different video stabilization algorithms: the video stabilization quality evaluation results of the present invention and the subjective ...

Embodiment 3

[0118] This embodiment calculates the correlation between the evaluation results of the other three no-reference video stabilization quality evaluation algorithms and the evaluation results of subjective quality evaluation, and then compares it with the correlation of the results calculated by the present invention in Example 2 to verify Advantages of the present invention.

[0119] The three no-reference video stabilization quality evaluation algorithms used in this embodiment are ITF (Battiato S, Gallo G, Puglisi G, et al.SIFT Features Tracking for Video Stabilization[C] / / International Conference on Image Analysis and Processing. IEEE Xplore,2007:825-830.); LHR(Liu S, Yuan L, Tan P, et al.Bundled camera paths for videostabilization[J].Acm Transactions on Graphics,2013,32(4):1-10. ); There is also an evaluation method for 2D curvature. The original video data set used is the twelve types of videos in Example 2. The comparison results are shown in Table 2:

[0120] Table 2 ...

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 non-reference video stability quality evaluation method based on inter-frame motion smoothness, and belongs to the field of video processing. The method comprises the following steps: extracting adjacent frame feature points by using a SURF (Speed Up Robust Features) algorithm; performing grid processing on video frames; calculating grid homograph matrixes; constructing binding paths by the homograph matrixes; calculating the smoothness of the binding paths; and synthesizing the smoothness of all the binding paths to obtain a final video stability quality evaluation result. Compared with an existing method, the method has the advantages that the smoothness degrees of the paths are represented by intrinsic geodesic curvatures of binding motion paths, so that very high consistence with subjective quality evaluation, and relatively high robustness, flexibility and efficiency are achieved.

Description

technical field [0001] The invention relates to a video stabilization quality evaluation method, in particular to a no-reference video stabilization quality evaluation method based on motion smoothness between frames, and belongs to the field of video processing. Background technique [0002] With the cheapness of video capture devices, more and more video capture devices are used in our lives, involving entertainment, safety, production and other aspects. However, due to the limitations of the use environment and users, such as the impact of strong winds on surveillance cameras, and the fact that amateurs do not have professional camera stabilization equipment such as tripods and pan-tilts, the collected video data often has certain jitter or Shaking affects the viewing experience of the human eye and further processing in the later stage. [0003] Scholars at home and abroad have done a lot of basic research on video stabilization, which has high application value. Now t...

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): H04N17/00
CPCH04N17/00
Inventor 黄华郑清卓张磊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap