Assessing the efficacy of social distancing as a weapon against COVID-19 using Manhattan distance and AI-based deep learning models

Social distance detection plays a crucial role in curbing the spread of contagious diseases. In recent years, artificial intelligence (AI) and deep learning (DL) have emerged as a powerful resource for dealing with a wide range of practical challenges and delivering impressively positive outcomes. This article delves into the usage of object recognition, and deep learning to monitor personal and professional interactions between people at a distance. In this paper, it proposes an efficient stacked deep learning technique for accurate and real-time social distance detection (SDD). The proposed method combines the power of object detection and distance estimation between the objects in a stacked manner to improve the accuracy. The proposed technique is evaluated on two popular deep learning models such as MobileNetV2 and InceptionV2. In high-dimensional spaces, Manhattan distance can sometimes be more robust than Euclidean distance. This research work uses Manhattan distance to identify the social distance among the individuals in the crowd. The Manhattan distance with InceptionV2 outperformed well than the MobileNetV2. Experimental results demonstrate the effectiveness of the SDD technique in terms of accuracy and efficiency.