Abstract: Dense pedestrian detection constitutes a critical component in smart city systems for crowd monitoring and behavioral analysis. To address limitations in existing models, such as low accuracy in small-object detection, excessive parameter size, and deployment constraints, this paper proposes DRS-YOLO—an improved lightweight dense pedestrian detection algorithm based on YOLO11. A DualConv module is introduced into the neck network of YOLO11 to replace the standard convolution structure, enhancing cross-scale feature fusion and spatial modeling capabilities while mitigating the insufficient extraction of contextual information by traditional convolutions in dense scenes. This modification reduces computational redundancy while improving detection accuracy. Additionally, an RSBlock is designed to strengthen semantic feature reconstruction and global information modeling, thereby enhancing model robustness and generalization under complex occlusion scenarios while effectively reducing parameter count. A SASP module is constructed to alleviate the loss of small-object details during downsampling, reinforcing the model's focus perception and contextual understanding of small targets. Experimental results demonstrate that the improved algorithm achieves increases of 1.8%, 2.7%, 1.4%, and 0.6% in Precision, Recall, mAP50, and mAP50:95 respectively on the WiderPerson dataset; 1.7%, 1.7%, 1.2%, and 0.8% on CrowdHuman; and 2.1%, 1.0%, 1.0%, and 0.5% on BDD100K, while the model size is reduced to 4.9 MB. Deployed on an RK3588-based embedded device, the algorithm achieves an average inference time of 61.4 ms per frame with an mAP50 of 80.3%, indicating an optimal balance between lightweight design, detection accuracy, and real-time performance.

摘要： 密集行人检测是智慧城市实现人流监测与行为分析的关键环节之一。针对现有模型在小目标检测精度低以及模型参数量大、部署受限等问题，本文提出了一种改进YOLO11的轻量化密集行人检测算法——DRS-YOLO。在YOLO11的颈部网络（Neck）中引入DualConv模块以替换标准卷积结构，增强跨尺度特征融合与空间建模能力，缓解传统卷积在密集场景下上下文信息提取不足的问题，从而在减少计算冗余的同时提升检测精度；设计RSBlock结构，强化语义特征重构与全局信息建模能力，提升模型在复杂遮挡环境下的鲁棒性与泛化性能，并有效减少参数量；构建SASP模块，缓解小目标在下采样过程中的细节丢失现象，强化模型对小目标的聚焦感知与上下文理解能力。实验结果表明，改进算法的Precision、Recall、mAP50和mAP50:95在WiderPerson数据集上分别提升1.8%、2.7%、1.4%、0.6%，在CrowdHuman上提升1.7%、1.7%、1.2%、0.8%，在BDD100K上提升2.1%、1.0%、1.0%、0.5%，同时模型大小下降至4.9MB。将算法部署在以RK3588为核心的嵌入式设备上，单帧图像平均运行时间为61.4ms，mAP50为80.3%，表明该算法在保证轻量化的同时兼顾检测精度与实时性。