User Tools

Site Tools


This is an old revision of the document!

10a.002.TAU_WP3 - Early Anomaly Recognition System

Project - Summary

  • Natural catastrophes and outbreaks, such as COVID-19, impose restrictions on citizens movement and daily life. Such restrictions are maintained by governmental bodies and agencies using CCTV cameras, monitored by operators, and by on site personnel. However, these conventional monitoring techniques are very labor intensive and suffer from subjective interpretations and human error due to fatigue.
  • This project aims to provide a real-time early anomaly recognition system based on advanced Computer Vision and Deep Learning algorithms that can be implemented on top of a wide CCTV infrastructure and monitoring grid.
  • The proposed system aims to detect and identify curfew infractions, social distancing violations, illegal gatherings, and general threats such as fire, smoke, unattended objects in public places, and abnormal behaviors.
  • The application domains of this project include both surveillance and empathic buildings development.

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Moncef Gabbouj PI N/A Tampere University
Serkan Kiranyaz Co-PI N/A Tampere University
Mohammad Al-Sa'd Researcher N/A Tampere University
Funded by:

Project - Novelty of Approach

  • Detecting and identifying threats and abnormal behaviors in video feeds have been a hot topic ever since computer vision algorithms recently became popular thanks to the advances made in deep learning; however, no convincing real-time solution has been provided up to date.
  • Current anomaly detection solutions excel given specific anomalies and conditions. Nonetheless, we aim to leverage various optimized techniques to yield a comprehensive early anomaly recognition system.

Project - Deliverables

1 Video feeds from different cameras optimized for efficient anomaly detection
2 Software based on existing methods written in MATLAB/Python/C++
3 Software utilizing GPUs and parallel computation for enhanced performance
4 Multi-view early anomaly recognition system framework
5 Quantitative investigation identifying strengths and potential weaknesses

Project - Benefits to IAB

The recent COVID-19 outbreak imposes immediate needs for such a comprehensive surveillance and tracking system for indoors and outdoors. The application domains include both surveillance and empathic buildings development. This is beneficial for any CVDI company who wishes to be among the pioneers of this next generation monitoring systems and empathic building.

Project - Documents

projects/year10/10a.002.tau_wp3.1620677763.txt.gz · Last modified: 2021/05/10 15:16 by sally.johnson