The demand for intelligent, automated surveillance systems has surged with the proliferation of smart cities and heightened security needs. Real-time object detection is at the heart of these systems, enabling rapid identification and tracking of people, vehicles, and suspicious activities. This research paper presents a comparative study of leading object detection models—particularly YOLO (You Only Look Once) and SSD (Single Shot MultiBox Detector)—for real-time surveillance applications. We evaluate their architectures, performance metrics (accuracy, speed, resource efficiency), strengths, and limitations using benchmark datasets and real-world scenarios. The analysis provides guidance for selecting the most suitable detection model based on specific surveillance requirements.