Real-time object detection has emerged as a critical application in computer vision, enabling intelligent systems to perceive and interact with their environment. This study presents a comparative analysis of lightweight deep learning models, namely MobileNet-SSD and YOLO-based architectures, for real-time object detection using OpenCV and Python. The proposed system processes live video streams by leveraging OpenCV’s DNN module to perform efficient inference on CPU hardware. The performance of the models is evaluated based on frame processing speed (FPS), detection accuracy, and computational efficiency. Experimental results demonstrate that MobileNet-SSD achieves higher processing speed, making it suitable for resource-constrained environments, while YOLO-based models provide improved detection accuracy. The study highlights the trade-off between speed and accuracy and provides insights into selecting appropriate models for real-time applications such as surveillance, automation, and smart monitoring systems.
Rai et al. (Tue,) studied this question.