A Review of Methodologies for Detecting Missing and Wanted People Using Machine Learning and Video Surveillance

Abstract

This literature review explores recent advancements in machine learning and image processing techniques for the detection of missing and wanted individuals through video surveillance. Sixteen studies were analyzed, focusing on various methodologies such as convolutional neural networks (CNNs), gait analysis, Bayesian networks, and 2D-3D facial recognition frameworks. The review highlights the applications, strengths, and limitations of these approaches in terms of accuracy, real- time applicability, and robustness in challenging conditions such as low-resolution footage and occlusion. This work aims to provide insights into the current research landscape and identify potential areas for future exploration, with a focus on improving the efficiency and scalability of surveillance-based identification systems.