Jiaqi Wang1, Jie Zhang2, Genlin Ji2,*, Bo Sheng3
Intelligent Automation & Soft Computing, Vol.34, No.3, pp. 1629-1642, 2022, DOI:10.32604/iasc.2022.029535
Abstract The surveillance applications generate enormous video data and present challenges to video analysis for huge human labor cost. Reconstruction-based convolutional autoencoders have achieved great success in video anomaly detection for their ability of automatically detecting abnormal event. The approaches learn normal patterns only with the normal data in an unsupervised way due to the difficulty of collecting anomaly samples and obtaining anomaly annotations. But convolutional autoencoders have limitations in global feature extraction for the local receptive field of convolutional kernels. What is more, 2-dimensional convolution lacks the capability of capturing temporal information while videos change over time. In this paper,… More >
Login
Register
