Efficient Object Detection on Low-Resource Devices Using Lightweight MobileNet-SSD

In the modern era, lightweight and deep learning-driven detection methods are essential for devices with limited computational resources. Object detection is a critical task that powers diverse applications, ranging from autonomous vehicles and security surveillance to augmented reality systems. These applications typically operate on devices constrained by minimal processing power and memory capacity. This study proposes an efficient object detection framework tailored for resource-constrained devices, leveraging a lightweight neural network architecture. The framework integrates the MobileNet Single Shot Detector (SSD) module, utilizing depthwise separable convolutions to significantly reduce computational load while maintaining high accuracy. The proposed lightweight MobileNet-SSD achieved accuracy, precision, recall, and confidence scores of 98.25%, 100%, 95%, and 96%, respectively. Experimental evaluations demonstrate that the proposed method strikes an optimal balance between performance and efficiency, making it suitable for real-time deployment in resource-constrained environments.