Anomalous entities detection using a cascade of deep learning models
This addresses a specific computer vision problem for surveillance in educational settings, but appears incremental as it combines existing deep learning components.
The paper tackles the problem of detecting anomalous human entities in examination hall videos by proposing a cascade of deep convolutional neural networks that first extracts pose keypoints then analyzes patches around them, achieving high accuracy detection on their collected student exam video dataset.
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.