Open AccessA Shallow Prediction Model with Enhanced Features for Video Time Series
Author(s) -
Yifei Zhang,
Hongxia Bie
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/790/1/012002
Subject(s) - computer science , pixel , series (stratigraphy) , artificial intelligence , time series , context (archaeology) , anomaly detection , computation , spatial correlation , deep learning , pattern recognition (psychology) , data mining , machine learning , computer vision , algorithm , geography , paleontology , telecommunications , archaeology , biology
Fast video time series prediction is an important part in video anomaly detection in deep learning framework. Time series deep learning models have good performance in time-series data prediction, such as traffic flow, rainfall and network traffic. The models, such as ConvLSTM, ConvGRU with complex structure and large amount of computation, are difficult to fit the video time series prediction. In this paper, we analyze data characteristics of video sequences and propose a shallow video series prediction model. We not only consider the spatial correlation in continuous video frames, but also investigate the interval video frames, which also maintain spatial correlation. We explore the gray scale pixel values of the interval frames which appear specific trend properties when we connect the context pixels together. Based on the enhanced features, we design a shallow 2D convolutional video time series prediction model with good prediction performance and much less total parameters.