Wearing safety helmets is an important way to ensure the safety of workers’ lives. To address the challenges associated with low accuracy, large parameter values, and slow detection speed of existing safety helmet detection algorithms, we propose a receptive field-enhanced lightweight safety helmet detection algorithm called YOLOv5s-CR. First, we use a lightweight backbone, a high-resolution feature fusion network, and a small object detection layer to improve the detection accuracy of small objects while substantially decreasing the model parameters. Next, we embed a coordinate attention mechanism into the feature extraction network to improve the localization accuracy of the detected object. Finally, we propose a new receptive field enhancement module (RFEM) to substitute the SPPF module in the original network, enabling the model to acquire features under multiple receptive fields, thereby enhancing the detection precision of multi-scale objects. Using the Safety Helmet Detection dataset for validation, in contrast to the initial YOLOv5s, the parameters of the improved algorithm were reduced by 62.8% to 2.61 M, and P, R, and mAP0.5 were increased by 1.5%, 1.2%, and 2.0%, respectively. The detection speed can reach 149FPS on the RTX3070 GPU, which satisfies the accuracy and real-time requirements for detecting safety helmets.