Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models

L Kratz, K Nishino - 2009 IEEE conference on computer vision …, 2009 - ieeexplore.ieee.org
Extremely crowded scenes present unique challenges to video analysis that cannot be
addressed with conventional approaches. We present a novel statistical framework for …

[PDF][PDF] 多特征联合建模的视频对象分割技术研究

李宗民, 公绪超, 刘玉杰 - 2013 - cjc.ict.ac.cn
摘要当前很多视频对象分割方法都联合利用了多种特征进行前景提取, 但是这些特征都是通过
简单加权融合到一起的. 该文通过主成分分析法(PrincipalComponentAnalysis, PCA) …

Spatio-temporal motion pattern modeling of extremely crowded scenes

L Kratz, K Nishino - The 1st International Workshop on Machine …, 2008 - inria.hal.science
The abundance of video surveillance systems has created a dire need for computational
methods that can assist or even replace human operators. Research in this field, however …

[PDF][PDF] A Machine-Vision System to Detect Unusual Activities Online at Vehicular Intersections

SLC Magdaleno, JS Rodríguez, HJ Hernández… - Computación y …, 2009 - redalyc.org
In this article, we present a real-time machine-vision system to detect vehicles running on
red light or performing forbidden turns at crossroads. The system operates during daytime by …

Subspace discovery for video anomaly detection

I Tziakos - 2010 - qmro.qmul.ac.uk
In automated video surveillance anomaly detection is a challenging task. We address this
task as a novelty detection problem where pattern description is limited and labelling …

A Machine-Vision System to Detect Unusual Activities Online at Vehicular Intersections

SL Canchola Magdaleno, J Salas Rodríguez… - Computación y …, 2009 - scielo.org.mx
In this article, we present a real–time machine–vision system to detect vehicles running on
red light or performing forbidden turns at crossroads. The system operates during daytime by …

Un Sistema de Visión por Computadora para Detectar en Línea Actividades Inusuales en Intersecciones Vehiculares

SL Canchola Magdaleno, J Salas Rodríguez… - Computación y …, 2009 - scielo.org.mx
In this article, we present a real–time machine–vision system to detect vehicles running on
red light or performing forbidden turns at crossroads. The system operates during daytime by …