在城市安全背景下，人车密集的智慧园区安全问题日益引起关注。实时检测进入园区内的人员、车辆，可以为应急情景下制定园区内人车的合理疏散策略提供重要的数据参考。为解决当前目标检测在应急事件发生时的环境复杂、目标密集、遮挡等导致的精度问题，以及模型计算量导致的快速性问题，提出了一种基于改进轻量级YOLOv5的人车混杂目标检测算法。在原始YOLOv5模型的基础上，将骨干网中的结构空间金字塔池化（spatial pyramid pooling-fast, SPPF）改进为SimSPPF，保持并改善模型实时性。在中尺度层增加一条额外的边，引入通道注意力模块（coordinate attention, CA），使得模型在检测人车混杂的场景中的准确度得到提高。实验结果表明，相较于YOLOv5s，该算法在保持检测速度在142帧/s的同时，精度上提高了2.1%，满足了智慧园区对于人、车混杂动态检测的准确性与实时性需求。

In the context of urban security, the security problem of intelligent parks with dense human and vehicle has attracted increasing attention. Real-time detection of people and vehicles entering the park can provide important data reference for formulating reasonable evacuation strategies for people and vehicles in the park under emergency scenarios. To solve the accuracy problems caused by the complex environment, dense objects and occlusion of the current object detection during the occurrence of emergency events, as well as the rapidity problems caused by the number of model calculations, a hybrid object detection algorithm based on the improved lightweight YOLOv5 was proposed. Based on the original YOLOv5 model, the spatial pyramid pool structure spatial pyramid pooling-fast(SPPF) in the backbone network was improved to SimSPPF to improve the real-time performance of the model. By adding an extra edge to the mesoscale layer and introducing the channel attention mechanism coordinate attention(CA), the accuracy of the model in detecting the hybrid scene was improved. The experimental results show that compared with YOLOv5s, the algorithm not only maintains the detection speed at 142 frame/s but also improves the accuracy by 2.1% which meets the accuracy and real-time requirements of the hybrid dynamic detection of people and vehicles in the smart park.