Automatic Unusual Activities Recognition Using Deep Learning in Academia

Abstract

In the current era, automatic surveillance has become an active research problem due to its vast real-world applications, particularly for maintaining law and order. A continuous manual monitoring of human activities is a tedious task. The use of cameras and automatic detection of unusual surveillance activity has been growing exponentially over the last few years. Various computer vision techniques have been applied for observation and surveillance of real-world activities. This research study focuses on detecting and recognizing unusual activities in an academic situation such as examination halls, which may help the invigilators observe and restrict the students from cheating or using unfair means. To the best of our knowledge, this is the first research work in this area that develops a dataset for unusual activities in the examination and proposes a deep learning model to detect those unusual activities. The proposed model has been named Automatic Unusual Activity Recognition (AUAR), which employs motion-based frame extraction approaches to extract key-frames and then applies advanced deep learning Convolutional Neural Network algorithm with diverse configurations. The evaluation using standard performance measures confirm that the AUAR model outperforms the already proposed approaches for unusual activity recognition. Apart from evaluating the proposed model on the examination dataset, we also apply AUAR on Violent and Movies datasets, widely used in the relevant literature to detect suspicious activities. The results reveal that AUAR performs well on various data sets compared to existing state-of-the-art models.

Abnormal Behavior Detection in Online Exams Using Deep Learning and Data Augmentation Techniques

“…They created a dataset for out-of-the-ordinary behaviors during the examination and suggested a deeplearning model to detect them. This work's data-augmentation process included rotation range, width shift, flipping the data horizontally or vertically, and rescaling [20].…”

Effectiveness of Pre-Trained CNN Networks for Detecting Abnormal Activities in Online Exams

“…First started with cheating activities in physical exams, then moved on to online exam cheating, and finally in those studies where both online and physical exams were taken using machine learning, deep learning, and hybrid models. Ramzan et al [8] identified and recognized anomalous activities of students in exam rooms, to assist invigilators in observing students from cheating or employing unfair techniques. Their research compared the effectiveness of several CNN networks that have been used to look for unusual physical exam activity.…”

Unusual Driver Behavior Detection in Videos Using Deep Learning Models

“…Situations such as an abandoned object, a patient falling in the hospital, students cheating during exams [ 1 ], driver drowsiness [ 2 ], road accidents, traffic rules violations, and in public places such as slapping, punching, hitting, firing, abuse, snatching, fighting, terrorism, robbery, illegal parking, fire disaster. According to World Health Organization (WHO) statistics, road accidents are currently one of the top ten reasons for death worldwide [ 3 ].…”