To enhance small object detection in complex road senses, an improved you only look once version 8 (YOLOv8) algorithm is introduced. Firstly, the quadruple down-sampling branch is added to improve the learning ability of the network for small object features. Secondly, a spatial pyramid pooling fast bi-level routing spatial attention (SPPF-BRSA) module is designed to remove irrelevant regions in a query adaptive manner, which effectively reduces the interference of complex background on detection performance. In addition, the C2fDynamic module is used in the neck of YOLOv8 to strengthen the feature expression ability of the model by dynamically selecting the convolution kernel. Finally, the wise intersection over union (Wise-IoU) v3 loss function is used to obtain more accurate detection results by adjusting the gradient gain distribution. The experimental results show that on Huawei SODA10M dataset, the improved algorithm improves precision (P), recall (R), F1 score and mean average precision at IoU threshold of 0.50 (mAP50) by 4.6%, 4.1%, 4.3% and 5.4%, respectively compared with the original algorithm.