Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery

Yona Falinie A. Gaus, Neelanjan Bhowmik, Brian K. S. Isaac-Medina, Hubert P. H. Shum, Amir Atapour-Abarghouei and Toby P. Breckon
Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023

Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery

Abstract

Anomaly detection is a classical problem within automated visual surveillance, namely the determination of the normal from the abnormal when operational data availability is highly biased towards one class (normal) due to both insufficient sample size, and inadequate distribution coverage for the other class (abnormal). In this work, we propose the dual use of both visual appearance and localized motion characteristics, derived from optic flow, applied on a per-region basis to facilitate object-wise anomaly detection within this context. Leveraging established object localization techniques from a region proposal network, optic flow is extracted from each object region and combined with appearance in the far infrared (thermal) band to give a 3-channel spatiotemporal tensor representation for each object (1X thermal - spatial appearance; 2X optic flow magnitude as x and y components - temporal motion). This formulation is used as the basis for training contemporary semi-supervised anomaly detection approaches in a region-based manner such that anomalous objects can be detected as a combination of appearance and/or motion within the scene. Evaluation is performed using the Long-Term infrared (thermal) Imaging (LTD) benchmark dataset against which successful detection of both anomalous object appearance and motion characteristics are demonstrated using a range of semi-supervised anomaly detection approaches.

Downloads

YouTube

Citations

BibTeX

@inproceedings{gaus23region,
 author={Gaus, Yona Falinie A. and Bhowmik, Neelanjan and Isaac-Medina, Brian K. S. and Shum, Hubert P. H. and Atapour-Abarghouei, Amir and Breckon, Toby P.},
 booktitle={Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
 series={CVPRW '23},
 title={Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery},
 year={2023},
 month={6},
 pages={2995--3005},
 numpages={11},
 doi={10.1109/CVPRW59228.2023.00301},
 publisher={IEEE/CVF},
 location={Vancouver, Canada},
}

RIS

TY  - CONF
AU  - Gaus, Yona Falinie A.
AU  - Bhowmik, Neelanjan
AU  - Isaac-Medina, Brian K. S.
AU  - Shum, Hubert P. H.
AU  - Atapour-Abarghouei, Amir
AU  - Breckon, Toby P.
T2  - Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
TI  - Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery
PY  - 2023
Y1  - 6 2023
SP  - 2995
EP  - 3005
DO  - 10.1109/CVPRW59228.2023.00301
PB  - IEEE/CVF
ER  - 

Plain Text

Yona Falinie A. Gaus, Neelanjan Bhowmik, Brian K. S. Isaac-Medina, Hubert P. H. Shum, Amir Atapour-Abarghouei and Toby P. Breckon, "Region-Based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery," in CVPRW '23: Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2995-3005, Vancouver, Canada, IEEE/CVF, Jun 2023.

Supporting Grants

The Ministry of Defence (DASA)
Autonomous Persistent Wide Area Surveillance of Human and Vehicle Activity
Defence and Security Accelerator (Ref: DSTL0000007030, ACC6031106): £93,978, Co-Investigator (PI: Prof. Toby P. Breckon)
Received from The Ministry of Defence (DASA), UK, 2022-2023
Project Page

Similar Research

Shoujiang Xu, Edmond S. L. Ho, Nauman Aslam and Hubert P. H. Shum, "Unsupervised Abnormal Behaviour Detection with Overhead Crowd Video", Proceedings of the 2017 International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 2017
Brian K. S. Isaac-Medina, Matthew Poyser, Daniel Organisciak, Chris G. Willcocks, Toby P. Breckon and Hubert P. H. Shum, "Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark", Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
Daniel Organisciak, Dimitrios Sakkos, Edmond S. L. Ho, Nauman Aslam and Hubert P. H. Shum, "Unifying Person and Vehicle Re-Identification", IEEE Access, 2020

 

 

Last updated on 14 April 2024
RSS Feed