Reliability of bench-mark datasets for crowd analytic surveillance

Abstract

This paper presents an evaluation on the reliability of the bench-mark datasets for outdoor crowd analytic surveillance systems. The credibility of the databases are assessed based on their diverseness to yield challenges of dynamic environments. The main object of this paper is to assess the challenges imposed by the databases for sudden illumination variance and effect of wavering trees.Two bench-mark databases, PETS 2010 and OTCBVS, along with our proposed dataset are evaluated using the three most popular background modelling algorithms in crowd analytic surveillance; Approximate Median Method, Gaussian Mixture Model and Codebook. The diverseness of these databases are assessed, with respect to the performance of the basic algorithms using qualitatively and quantitatively. Eventually the reliability of these bench-mark databases for outdoor crowed analytic surveillance is assessed.

Emotion estimation in crowds: a survey

“…All the presented situations are mainly poor in terms of emotional behavior, except for the scenario S3 (event recognition) where an evacuation (rapid dispersion) is observed and can be associated to an emotional state of fear. The authors of CAD [28] recreated several normal collective behaviors adding the challenges of change in illumination and wavering trees in the background, however, the captured situations are not representative of any emotional behavior. Taking advantage of the large number of people attending the World Exposition of 2010 in Shanghai, the massive dataset Shanghai Expo 10 [29] was gathered.…”