Abstract

en the increasing importance of human target detection in various security applications, many existing systems face challenges related to cost, accuracy, and adaptability. This work presents the development of a machine learning-based system called Human Target Detection and Acquisition, designed to assist security personnel in the detection and tracking of human targets through an adaptive and cost-effective approach. In this, standard CCTV cameras provide visual data, which intelligent algorithms process to identify and track human targets, even in challenging conditions. The system offers user-specific dashboards: administrators can monitor detections and adjust system parameters, while security personnel receive real-time alerts and tracking information. Additionally, it supports continuous improvement through its machine learning capabilities, allowing for enhanced performance over time without the need for hardware upgrades. The architecture of the platform relies on TensorFlow, OpenCV, and database integration for efficient handling of video processing and data management. Initial testing suggests that it can provide accurate and reliable human target detection while significantly reducing costs compared to hardwareintensive solutions. Future work includes expanding the system's capabilities to handle multiple camera feeds simultaneously and implementing more advanced tracking algorithms.