Video sequence classifying method based on tensor time domain association model

Abstract

A video sequence classifying method based on a tensor time domain association model comprises the steps of representing an original video sequence in a three-grade video tensor manner; performing tensor Tucker decomposition on the three-grade video tensor for obtaining a latent kernel tensor; applying an autoregression model on the time domain of the obtained latent kernel tensor for establishing relevance between adjacent time slices; dynamically studying the front process, updating the result until an algorithm is convergent, and obtaining an optimal result. The video sequence classifying method ensures time domain relevance and dependence of the video sequence after dimension reduction through limiting the time domain of the video sequence. The video sequence classifying method has advantages of sufficiently utilizing latent useful information in the video, eliminating redundant information in the video, ensuring high continuity of the video sequence in time domain, reducing classification difficulty of the video sequence, and improving classification accuracy of the video sequence. The video sequence classifying method is better than a traditional video sequence classification method and greatly improves classification precision.

Description

technical field [0001] The invention relates to a video sequence classification method. In particular, it relates to a video sequence classification method based on the tensor time domain association model, which combines the tensor decomposition technology with the time domain association model, and performs spatial dimensionality reduction on the tensor video sequence to obtain a potential low-dimensional video sequence representation. Background technique [0002] In recent years, with the vigorous development of video acquisition equipment, the amount of video data has been significantly increased. To perform analysis on these video data, video sequence classification has received great attention. Video sequence classification is widely used in video summarization, video retrieval, action recognition, etc. Gesture and action videos of the human body are important components of video data, and they have a wide range of applications in information transmission for deaf-m...

AI Technical Summary

Problems solved by technology

In recent years, some work has begun to focus on high-dimensional time series analysis, combining multi-linear algebraic operations with time-domain smoothness constraints to process high-order time series data. However, this method does not take into account the inherent statistics of video time series. distribution law, it cannot match the structural characteristics of video sequence data effectively

Images