CPNet: Cross-Parallel Network for Efficient Anomaly Detection

Youngsaeng Jin, Jonghwan Hong, David Han, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Anomaly detection in video streams is a challenging problem because of the scarcity of abnormal events and the difficulty of accurately annotating them. To alleviate these issues, unsupervised learning-based prediction methods have been previously applied. These approaches train the model with only normal events and predict a future frame from a sequence of preceding frames by use of encoder-decoder architectures so that they result in small prediction errors on normal events but large errors on abnormal events. The architecture, however, comes with the computational burden as some anomaly detection tasks require low computational cost without sacrificing performance. In this paper, Cross-Parallel Network (CPNet) for efficient anomaly detection is proposed here to minimize computations without performance drops. It consists of N smaller parallel U-Net, each of which is designed to handle a single input frame, to make the calculations significantly more efficient. Additionally, an inter-network shift module is incorporated to capture temporal relationships among sequential frames to enable more accurate future predictions. The quantitative results show that our model requires less computational cost than the baseline U-Net while delivering equivalent performance in anomaly detection.

Original languageEnglish
Title of host publicationAVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665433969
DOIs
Publication statusPublished - 2021
Event17th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2021 - Virtual, Online, United States
Duration: 2021 Nov 162021 Nov 19

Publication series

NameAVSS 2021 - 17th IEEE International Conference on Advanced Video and Signal-Based Surveillance

Conference

Conference17th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2021
Country/TerritoryUnited States
CityVirtual, Online
Period21/11/1621/11/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'CPNet: Cross-Parallel Network for Efficient Anomaly Detection'. Together they form a unique fingerprint.

Cite this