Road target detection is a very challenging task in the field of computer vision because it is easily affected by complex backgrounds and sparse features of small targets. YOLOv3 (You Only Look Once v3) is currently one of the state-of-the-art object detection methods of deep learning. However, because the k-means clustering algorithm is sensitive to the initial clustering center, the local fragile visual field features related to small objects in the prediction map are severely lost and the final decision-making theory (The grid located in the center of the foreground object is responsible for predicting this object) of the network ignores the detailed information of the neighboring grid, there are still many problems in object detection. In this paper, we propose an improved algorithm based on YOLOv3 for small-scale object detection. We use the improved k-medians clustering method instead of the previous k-means to improve the model instability caused by the singularity; We propose a local enhancement method to strengthen weak features for small-scale object detection by paralleling a branch on the backbone. Besides, a flexible offset sampling structure added in parallel for information compensation is also designed. A series of experiments showing that our system has achieved good detection results on the KITTI and UA-DETRAC public datasets, and the distinguishing performance for small-scale objects is significantly improved. Therefore, our method is effective in road target detection tasks.

道路目标检测是计算机视觉领域中一项非常具有挑战性的任务，因为它容易受到复杂背景和小目标稀疏特征的影响。YOLOv3（You Only Look Once v3）是目前最先进的深度学习对象检测方法之一。然而，由于k-means聚类算法对初始聚类中心敏感，预测图中与小物体相关的局部脆弱视野特征严重丢失，最终决策理论（位于中心的网格）前景物体负责预测这个物体）的网络忽略了相邻网格的详细信息，物体检测仍然存在很多问题。在本文中，我们提出了一种基于 YOLOv3 的改进算法，用于小规模物体检测。我们使用改进的k-medians聚类方法代替之前的k-means来改善奇异点引起的模型不稳定；我们提出了一种局部增强方法，通过在主干上并行分支来增强小规模目标检测的弱特征。此外，还设计了一种用于信息补偿的并行添加的灵活偏移采样结构。一系列实验表明，我们的系统在KITTI和UA-DETRAC公共数据集上取得了良好的检测效果，对小尺度物体的区分性能得到显着提升。因此，我们的方法在道路目标检测任务中是有效的。我们提出了一种局部增强方法，通过在主干上并行分支来增强小规模目标检测的弱特征。此外，还设计了一种用于信息补偿的并行添加的灵活偏移采样结构。一系列实验表明，我们的系统在KITTI和UA-DETRAC公共数据集上取得了良好的检测效果，对小尺度物体的区分性能得到显着提升。因此，我们的方法在道路目标检测任务中是有效的。我们提出了一种局部增强方法，通过在主干上并行分支来增强小规模目标检测的弱特征。此外，还设计了一种用于信息补偿的并行添加的灵活偏移采样结构。一系列实验表明，我们的系统在KITTI和UA-DETRAC公共数据集上取得了良好的检测效果，对小尺度物体的区分性能得到显着提升。因此，我们的方法在道路目标检测任务中是有效的。对小尺度物体的区分性能显着提高。因此，我们的方法在道路目标检测任务中是有效的。对小尺度物体的区分性能显着提高。因此，我们的方法在道路目标检测任务中是有效的。