Anomalous entities detection using a cascade of deep learning models

TL;DR

This paper introduces a two-stage deep learning approach using pose estimation and dense CNNs to detect anomalous entities in examination hall videos, achieving high accuracy in identifying unusual behaviors.

Contribution

It presents a novel cascade of deep learning models combining pose estimation and dense CNNs specifically for anomaly detection in complex visual scenarios.

Findings

High accuracy detection of anomalous entities

Effective use of pose estimation for feature extraction

Applicable to real-world examination hall scenarios

Abstract

Human actions that do not conform to usual behavior are considered as anomalous and such actors are called anomalous entities. Detection of anomalous entities using visual data is a challenging problem in computer vision. This paper presents a new approach to detect anomalous entities in complex situations of examination halls. The proposed method uses a cascade of deep convolutional neural network models. In the first stage, we apply a pretrained model of human pose estimation on frames of videos to extract key feature points of body. Patches extracted from each key point are utilized in the second stage to build a densely connected deep convolutional neural network model for detecting anomalous entities. For experiments we collect a video database of students undertaking examination in a hall. Our results show that the proposed method can detect anomalous entities and warrant unusual behavior with high accuracy.