VARS: Vision-based Assessment of Risk in Security Systems
This work addresses the problem of enhancing safety and security systems by providing a more accurate framework for video-based risk detection, though it is incremental as it focuses on comparative analysis of existing methods.
The study compared machine learning and deep learning models to predict danger levels in a custom dataset of 100 videos, finding that transformer-based models achieved the highest accuracy and F1-scores for classifying alerts.
The accurate prediction of danger levels in video content is critical for enhancing safety and security systems, particularly in environments where quick and reliable assessments are essential. In this study, we perform a comparative analysis of various machine learning and deep learning models to predict danger ratings in a custom dataset of 100 videos, each containing 50 frames, annotated with human-rated danger scores ranging from 0 to 10. The danger ratings are further classified into three categories: no alert (less than 7)and high alert (greater than equal to 7). Our evaluation covers classical machine learning models, such as Support Vector Machines, as well as Neural Networks, and transformer-based models. Model performance is assessed using standard metrics such as accuracy, F1-score, and mean absolute error (MAE), and the results are compared to identify the most robust approach. This research contributes to developing a more accurate and generalizable danger assessment framework for video-based risk detection.