计算机与现代化 ›› 2024, Vol. 0 ›› Issue (06): 43-50.doi: 10.3969/j.issn.1006-2475.2024.06.008

• 算法设计与分析 • 上一篇    下一篇

一种基于改进SIFT的视频稳像方法

  


  1. (长安大学信息工程学院,陕西 西安 710018)
  • 出版日期:2024-06-30 发布日期:2024-07-17
  • 作者简介: 作者简介:李欣(2000—),女,山东菏泽人,硕士研究生,研究方向:图像处理,视频稳像,E-mail: lxgzyxl@163.com; 通信作者:焦立男(1975—),男,陕西商洛人,硕士生导师,副教授,博士,研究方向:图像处理与分析,计算机视觉与模式识别,机器人运动规划,E-mail: lnjiao@chd.edu.cn; 柳有权(1976—),男,湖北秭归人,硕士生导师,教授,博士,研究方向:计算机图形学,虚拟现实技术,人机交互技术,E-mail: youquan@chd.edu.cn; 马彩莎(1998—),女,河南南阳人,硕士研究生,研究方向:计算机视觉,行人检测,E-mail: m2377680820@163.com。
  • 基金资助:
    国家科技重点研发计划项目(2018YFB1600802)
       

A Video Stabilization Method Based on Improved SIFT



  1. (School of Information Engineering, Chang’an University, Xi’an 710018, China)
  • Online:2024-06-30 Published:2024-07-17

摘要:
摘要:为提高计算效率并保持良好的稳像效果,本文提出一种基于改进SIFT的视频稳像方法。首先对SIFT进行改进,并命名为BO-SIFT(Binarized Octagonal SIFT)。该算法引入了同心八边形环特征描述子,通过降维和二值化对特征向量进行处理,然后使用汉明距离进行特征点匹配,有效缩短了描述和匹配时间。其次将BO-SIFT算法应用于视频稳像,提取视频帧的特征点进行匹配,并计算出帧与帧之间的运动偏移量,以此实现运动估计。最后采用卡尔曼滤波器对估计出的运动偏移量进行平滑处理,并利用仿射变换对视频帧进行逆向补偿,从而得到稳定的图像序列。实验结果表明:相较于原始的SIFT算法,BO-SIFT算法使稳像时间减少了56.404%;相较于现有的较好算法,BO-SIFT算法稳像后的视频具有更高的平均峰值信噪比。此外,本文算法在不同视频上进行稳像效果测试,也具有一定的可靠性和优越性。




关键词: 关键词:视频稳像, BO-SIFT算法, 降维, 二值化, 运动估计, 峰值信噪比

Abstract:
Abstract: This paper proposes a video stabilization method based on improved SIFT to improve computational efficiency and maintain a good video stabilization effect. Firstly, SIFT is improved and named BO-SIFT (Binarized Octagonal SIFT). The algorithm introduces concentric octagonal ring feature descriptors, processes the feature vectors by dimensionality reduction and binarization, and then uses Hamming distance for feature point matching, which effectively reduces the description and matching time. Secondly, the BO-SIFT algorithm is applied to video stabilization, extracting the feature points of the video frames for matching and calculating the motion offsets between frames to achieve motion estimation. Afterwards, the estimated motion offsets are smoothed using a Kalman filter and the video frames are inversely compensated using affine transformation to obtain a stabilized image sequence. The experimental results show that the BO-SIFT algorithm reduces the stabilization time by 56.404% compared to the original SIFT algorithm, and the stabilized video of the BO-SIFT algorithm has a higher average peak signal-to-noise ratio compared to the existing better algorithms. In addition, the algorithm in this paper is tested on different videos for video stabilization effects, which also has certain reliability and superiority.

Key words: Key words: video stabilization, BO-SIFT algorithm, dimensionality reduction, binarization, motion estimation, peak signal-to-noise ratio

中图分类号: