Key frame extraction method based on cosine distance hierarchical clustering
A technology of cosine distance and hierarchical clustering, applied in the field of computer vision, to achieve good visualization effects, improve accuracy and recall
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.
[0042] The realization of the present invention specifically adopts the following steps in sequence:
[0043] (1) The schematic flow chart of the present invention is as figure 1 shown. First, use the data provided by the CMU motion capture database in the preprocessing module, and use the joint point rotation in each frame as the feature value of the segmented motion capture data; apply the bidirectional Butterworth with an order of 5 and a cutoff frequency of 0.1 Hz The filter realizes the denoising function of the motion capture data; the PCA method is used to map the high-dimensional data into low-dimensional data and save the effective data of each frame. Second, the keyframe extraction module is implemented in the following steps.
[0044] (2) Comparing the similarity by calculating the rate matrix of adjacent frames, the rat...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com