基于关键点估计的实时道路元素检测算法

针对手工设计神经网络结构成本较高、基于锚框的分类回归任务计算量较大以及小目标检测能力较弱的问题,文中使用基于神经网络结构搜索的EfficientNet-B3作为特征提取网络,改进基于双向特征金字塔网络的特征融合方法作为特征融合网络,利用关键点估计代替锚框,执行分类与回归任务,提出基于关键点估计的实时道路元素检测算法.在BDD100K数据集上的实验表明,文中算法在实时检测的基础上可达到较优的检测效果,在小目标上检测精度较高.

Real-Time Road Element Detection Based on Keypoints Estimation

Aiming at the problems of high cost of manually designing neural network structure, large amount of calculation of the classification and regression task based on the anchor boxes, and weak detection ability for small targets, a real-time road element detection model based on keypoint estimation is proposed. NAS-based EfficientNet-B3 is employed as the feature extraction network. An improved bi-directional feature pyramid network(BiFPN) method is exploited as the feature fusion network. Instead of anchor boxes, keypoint estimation is utilized for classification and regression tasks. The experiment on BDD100K dataset shows that the proposed model achieves a good precision in real-time detection and a high precision for small objects.