A 2D amplitude-modulation frequency-modulation representation for motion estimation

机译：用于运动估计的2D调幅调频表示

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We present a new approach for motion estimation from digital videos based on the use of 2D amplitude-modulation frequency-modulation (AM-FM) models. The proposed approach uses an AM-FM representation to derive AM and FM based equations that can be applied to two consecutive frames to derive motion estimates. We test the proposed method using complex synthetic examples, with both amplitude-modulated and frequency-modulated components, for both sinusoidal, periodic motions and constant motion and compare against the popular Horn-Schunk and Lucas and Kanade method. Compared to the standard Horn-Schunk and Lucas and Kanade methods, the proposed approach leads to dramatic reductions in the mean-squared error for both constant, translational motion (from 19.73% to 95.46% reduction) and complex sinusoidal, periodic motions (up to 67.95% reduction).

机译：我们提出了一种基于2D幅度调制频率调制（AM-FM）模型的数字视频运动估计新方法。所提出的方法使用AM-FM表示来得出基于AM和FM的方程，该方程可应用于两个连续帧以得出运动估计。我们使用复杂的合成示例（包括振幅调制和频率调制的分量）对正弦，周期性运动和恒定运动进行测试，并与流行的Horn-Schunk和Lucas和Kanade方法进行比较。与标准的Horn-Schunk和Lucas和Kanade方法相比，所提出的方法导致恒定的平移运动（从19.73％降低到95.46％）和复杂的正弦周期运动（最大达到）的均方误差显着降低。减少67.95％）。

著录项

来源
《Proceedings of the 2016 IEEE ANDESCON》|2016年|1-4|共4页
会议地点 Arequipa(PE)
作者
Victor Murray; Alvaro Dasso; Juan Llanos; Paul Rodriguez; Marios S. Pattichis;
展开▼
作者单位

Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, New Mexico 87131, USA;

Department of Electrical Engineering, Universidad de Ingeniería y Tecnología, Lima, Lima 43, Peru;

Department of Electrical Engineering, Universidad de Ingeniería y Tecnología, Lima, Lima 43, Peru;

Department of Electrical Engineering, Pontificia Universidad Católica del Perú, San Miguel, Lima 32, Peru;

Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, New Mexico 87131, USA;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Motion estimation; Videos; Frequency modulation; Frequency estimation; Two dimensional displays; Mathematical model; Optical imaging;

机译：运动估计;视频;频率调制;频率估计;二维显示;数学模型;光学成像;

相似文献

外文文献
中文文献
专利

1. S3D Motion Estimation Based on 2D Motion Field Using Neural Networks [J] . Yunhua Zhang, Yaming Wang, Sun Li, Asian Journal of Information Technology . 2007,第7期

机译：基于2D运动场的神经网络S3D运动估计
2. Estimation of Multiple, Time-Varying Motions Using Time-Frequency Representations and Moving-Objects Segmentation [J] . Alexiadis D. S., Sergiadis G. D. IEEE Transactions on Image Processing . 2008,第6期

机译：使用时频表示和运动对象分割估计多个时变运动
3. Two-Step Sparse Representation Based 2D DOA Estimation with Single Moving Acoustic Vector Sensor [J] . Wireless personal communications: An Internaional Journal . 2020,第4期

机译：基于两步稀疏表示的2D DOA估计用单流式声学矢量传感器
4. A 2D amplitude-modulation frequency-modulation representation for motion estimation [C] . Victor Murray, Alvaro Dasso, Juan Llanos, IEEE ANDESCON Conference . 2016

机译：运动估计的2D幅度调制频率调制表示
5. Motion estimation and encoding algorithms for hierarchical representation of digital video. [D] . Zafar, Sohail. 1994

机译：用于数字视频分层表示的运动估计和编码算法。
6. JTHERGAS: Thermodynamic Estimation from 2D Graphical Representations of Molecules [O] . Edward Blurock, V. Warth, X. Grandmougin, -1

机译：JTERGAS：来自分子的2D图形表示的热力学估计
7. Rigid 3D motion estimation using neural networks and initially estimated 2D motion data [O] . Dimitrios Tzovaras, Nikiforos Ploskas, Michael G. Strintzis, 2000

机译：使用神经网络和初始估计的2D运动数据的刚性3D运动估计

A 2D amplitude-modulation frequency-modulation representation for motion estimation

摘要

著录项

相似文献

相关主题

期刊订阅