An Anomaly Comprehension Neural Network for Surveillance Videos on Terminal Devices

Anomaly comprehension in surveillance videos is more challenging than detection. This work introduces the design of a lightweight and fast anomaly comprehension neural network. For comprehension, a spatio-temporal LSTM model is developed based on the structured, tensorized time-series features extra...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng, Yuan, Huang, Guangtai, Zhen, Peining, Liu, Bin, Chen, Hai-Bao, Wong, Ngai, Yu, Hao
Format: Conference Proceeding
Language:English
Subjects:
AI on IOT
anomaly comprehension
Feature extraction
Hardware
Neural networks
Quantization (signal)
Surveillance
surveillance videos
Tensors
Videos
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Anomaly comprehension in surveillance videos is more challenging than detection. This work introduces the design of a lightweight and fast anomaly comprehension neural network. For comprehension, a spatio-temporal LSTM model is developed based on the structured, tensorized time-series features extracted from surveillance videos. Deep compression of network size is achieved by tensorization and quantization for the implementation on terminal devices. Experiments on large-scale video anomaly dataset UCF-Crime demonstrate that the proposed network can achieve an impressive inference speed of 266 FPS on a GTX-1080Ti GPU, which is 4.29 faster than ConvLSTM-based method; a 3.34% AUC improvement with 5.55% accuracy niche versus the 3D-CNN based approach; and at least 15k× parameter reduction and 228× storage compression over the RNN-based approaches. Moreover, the proposed framework has been realized on an ARM-core based IOT board with only 2.4W power consumption.
ISSN:1558-1101
DOI:10.23919/DATE48585.2020.9116533