基于YOLO的公共区域人群社交距离检测方法
A Social Distancing Detection Method for Public Area Crowds Based on YOLO

针对人流密集的公共区域，本论文提出了一种基于YOLO模型的人群社交距离检测方法，旨在进行有效的人流控制和预防疫情传播。该方法首先利用YOLO模型对公共区域的视频进行行人检测，获取每个行人的位置关键点信息。接着，通过KD-tree算法检测每个行人的邻居行人，并估计它们之间的距离。根据预设的安全距离阈值，对行人的社交距离进行风险评估，包括危险、安全或需要注意的状态。为了更好地呈现结果，本文将危险状态标识为红色危险标识，安全状态标识为绿色安全标识，而中间状态则标识为紫色注意标识。实验结果表明，所提出的行人社交距离检测方法具有较高的实时性和准确性。
This paper presents a crowd social distancing detection method based on the YOLO model, aiming to effectively control crowd movement and prevent the transmission of infectious diseases in densely populated public areas. The proposed method leverages the YOLO model to perform pedestrian detection on videos captured in public areas, thereby extracting precise positional key point information for each individual. Subsequently, the KD-tree algorithm is employed to identify neighboring pedestrians for each detected individual and estimate the inter-person distances between them. By utilizing a predefined threshold for a safe distance, a risk assessment is conducted to categorize the social distancing status of pedestrians into dangerous, safe, or attention-required states. To enhance the interpretability of the results, this study employs a red danger symbol to represent the dangerous state, a green safety symbol to represent the safe state, and a purple attention symbol to represent the intermediate state. Experimental results demonstrate that the proposed crowd social distancing detection method achieves high real-time performance and accuracy in assessing and monitoring social distancing compliance among pedestrians.