The field of human body detection, a pivotal area in computer vision, merits comprehensive discussion. Remarkable advancements have been achieved in the techniques for human body detection over the past few decades, with significant applications spanning various sectors. This discussion delves into the potential of human detection technology within the realm of security - a field that necessitates efficient and accurate human detection technology to promptly identify potential threats, suspicious behaviors, or unusual activities. Deep learning-based human detection algorithms have substantially improved capabilities in this domain, facilitating real-time tracking and identification of the human form, thereby enabling security personnel to respond swiftly. This paper employs the Faster-RCNN algorithm for model training, utilizing the Information and Automation Research (INRIA) database. The deep learning-trained model proves highly accurate in human body detection, effectively recognizing human movements and behaviors. Such capabilities hold immense potential for implementation within the security sphere, including video surveillance systems and other similar applications where effectiveness is crucial.