Motion Key-Frames Extraction Based on Locally Linear Embedding

Xu Long Dong; Dong Sheng Zhou; Qiang Zhang

doi:10.4028/www.scientific.net/AMM.538.476

Paper Titles

Image Measurement of Traffic Flow Parameters and its Traffic Congestion Evaluation
p.455

An Analysis of Factors Influencing Foreign Language Self-Efficacy Based on C5.0 Decision Tree Algorithm in Data Mining
p.460

A New Application of Kalman Filtering Algorithm Based on Interval Calculation in Navigation System
p.465

Optimization of Control Parameters Based on Multi-Objective Genetic Algorithms for Spacecraft Large Angle Attitude
p.470

Motion Key-Frames Extraction Based on Locally Linear Embedding
p.476

Human Motion Capture Data Segmentation Based on LLE Algorithm
p.481

Input-to-State Stability of Multi-Agent Systems
p.486

A Novel Multi-Service Passive Optical Network Based on the Wavelength-Division-Multiplexed Technology
p.490

Design of Intelligent Transportation Wireless Module Based on STM32F207
p.494

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 538Motion Key-Frames Extraction Based on Locally...

Motion Key-Frames Extraction Based on Locally Linear Embedding

Abstract:

A motion key-frames extraction algorithm based on LLE was presented. First, the dimensionality of motion capture data was reduced by LLE method to obtain the low dimension feature curve. Second, the initial key-frames were obtained by extracting the local extreme points. In the end, according to the difference of feature curve amplitude and the threshold, the corresponding key-frames were inserted to get the final key-frames. A amount of experiments showed that the algorithm could generalize the content of original motion sequence on the basis of the compression ratio and low error rate.