Abstract:

Vehicle-road collaboration aims to achieve intelligent and efficient traffic management through information exchange and collaboration， in which accurate， lightweight， and easily deployable vehicle and pedestrian detection from the roadside perspective is crucial. To this end， a lightweight traffic object detection model based on improved YOLOv8 was proposed. Firstly， the FasterBlock from FasterNet was introduced to replace certain bottleneck components in the original C2f， thereby reducing Giga FLOating-Point operations （GFLOPs） and parameters effectively， thus reducing the overall model complexity. Secondly， the GSConv （Group Shuffle Convolution） that balanced speed and precision was adopted in the neck network of the model to replace the original convolutional kernel， and the SlimNeck feature fusion module was introduced， enabling each feature layer to consider the semantic information of deep features and the details of shallow features simultaneously. Thirdly， the MPDIoU （Minimum Point Distance based Intersection over Union） was used to replace the original loss function， so as to improve the bounding box regression performance of the model. Finally， the channel pruning was performed to remove redundant connections in the model network， thereby reducing the model size and improving the detection speed. Experimental results show that compared to the original YOLOv8s， the improved and pruned model has the precision increased by 1.0 percentage points， the mean Average Precision （mAP） increased by 1.2 percentage points， and the computational cost and parameters reduced by 70.1% and 69.4% respectively. Under the conditions of edge device Atlas 200I DK A2 （computing power 4 TOPS， power consumption 9 W）， the proposed model has a detection speed of 58.03 frame/s.

Key words: vehicle-road collaboration, YOLOv8, loss function, model pruning, embedded deployment, edge computing

摘要：

车路协同旨在通过信息交换和协作实现智能高效的交通管理，其中高精度、轻量化且易于部署的路侧视角下的车辆与行人检测至关重要。因此，提出基于改进YOLOv8的轻量化交通目标检测模型。首先，引入FasterNet中的FasterBlock替换原始C2f中的某些瓶颈组件，以减少浮点运算量（GFLOPs）和参数量，降低整体模型的复杂性；其次，在模型的颈部网络采用兼顾速度和精度的GSConv（Group Shuffle Convolution）替代原有的卷积核，并引入SlimNeck特征融合模块，使每个特征层能够同时考虑深层特征的语义信息和浅层特征的细节；再次，使用MPDIoU（Minimum Point Distance based Intersection over Union）替换原有的损失函数，以提高模型的边界框回归性能；最后，通过通道剪枝修剪模型网络中的冗余连接，以减小模型规模并提高检测速度。实验结果表明，经过改进和剪枝的模型与原始YOLOv8s相比，精度提升了1.0个百分点，平均精度均值（mAP）提升了1.2个百分点，计算量和参数量分别降低了70.1%和69.4%。并且，在边缘设备Atlas 200I DK A2（算力4 TOPS，功耗9 W）的条件下，所提模型达到了58.03 frame/s的检测速度。

关键词: 车路协同, YOLOv8, 损失函数, 模型剪枝, 嵌入式部署, 边缘计算