Detection of Salient Regions in Crowded Scenes

10/15/2014
by   Mei Kuan Lim, et al.
0

The increasing number of cameras and a handful of human operators to monitor the video inputs from hundreds of cameras leave the system ill equipped to fulfil the task of detecting anomalies. Thus, there is a dire need to automatically detect regions that require immediate attention for a more effective and proactive surveillance. We propose a framework that utilises the temporal variations in the flow field of a crowd scene to automatically detect salient regions, while eliminating the need to have prior knowledge of the scene or training. We deem the flow fields to be a dynamic system and adopt the stability theory of dynamical systems, to determine the motion dynamics within a given area. In the context of this work, salient regions refer to areas with high motion dynamics, where points in a particular region are unstable. Experimental results on public, crowd scenes have shown the effectiveness of the proposed method in detecting salient regions which correspond to unstable flow, occlusions, bottlenecks, entries and exits.

READ FULL TEXT

page 1

page 2

research
10/14/2014

Crowd Saliency Detection via Global Similarity Structure

It is common for CCTV operators to overlook inter- esting events taking ...
research
02/16/2016

A diffusion and clustering-based approach for finding coherent motions and understanding crowd scenes

This paper addresses the problem of detecting coherent motions in crowd ...
research
12/02/2018

Disentangling Propagation and Generation for Video Prediction

Learning to predict future video frames is a challenging task. Recent ap...
research
01/23/2023

Crowd3D: Towards Hundreds of People Reconstruction from a Single Image

Image-based multi-person reconstruction in wide-field large scenes is cr...
research
02/06/2015

Crowded Scene Analysis: A Survey

Automated scene analysis has been a topic of great interest in computer ...
research
08/21/2019

Video-based Bottleneck Detection utilizing Lagrangian Dynamics in Crowded Scenes

Avoiding bottleneck situations in crowds is critical for the safety and ...
research
04/15/2022

Detecting Violence in Video Based on Deep Features Fusion Technique

With the rapid growth of surveillance cameras in many public places to m...

Please sign up or login with your details

Forgot password? Click here to reset