Monitoring of people entering and exiting private areas using Computer Vision
This addresses security concerns in public places by enabling surveillance outside private areas, but it is incremental as it builds on existing single-camera datasets and methods.
The paper tackles the problem of monitoring people entering and exiting private, camera-forbidden areas like toilets and changing rooms in public spaces, presenting a new pseudo-annotated dataset (EnEx2) captured with two cameras and a spatial transition-based event detection model that achieves standard results on this dataset and other surveillance datasets.
Entry-Exit surveillance is a novel research problem that addresses security concerns when people attain absolute privacy in camera forbidden areas such as toilets and changing rooms that are basic amenities to the humans in public places such as Shopping malls, Airports, Bus and Rail stations. The objective is, if not inside these camera forbidden areas, from outside, the individuals are to be monitored to analyze the time spent by them inside and also the suspecting transformations in their appearances if any. In this paper, firstly, a pseudo-annotated dataset of a laboratory observation of people entering and exiting the camera forbidden area captured using two cameras in contrast to the state-of-the-art single-camera based EnEx dataset is presented. Conventionally the proposed dataset is named \textbf{\textit{EnEx2}}. Next, a spatial transition based event detection to determine the entry or exit of individuals is presented with standard results by evaluating the proposed model using the proposed dataset and the publicly available standard video surveillance datasets that are hypothesized to Entry-Exit surveillance scenarios. The proposed dataset is expected to enkindle active research in Entry-Exit Surveillance domain.