基于RDM-YOLOv3的头部检测

Head Detection Based on RDM-YOLOv3

现有的通用检测方法在小目标检测上仍存在漏检率较高的问题。为了提高头部的检测率,在YOLOv3基础上提出了ResNet DenseNet MDC(Mixed Dilated Convolution)YOLOv3(RDMYOLOv3)目标检测网络。首先改进了YOLOv3的特征提取网络DarkNet53,提出了一种基于ResNet和DenseNet的特征提取网络RDNet,以提取更多的语义信息。然后,使用不同膨胀率的空洞卷积对特征层进行采样,构建混合空洞卷积结构,提高对小目标的敏感度。使用RDMYOLOv3与其他方法在Brainwash数据集和HollywoodHeads数据集上进行对比实验,AP(Average Precision)值分别达到了93.1%和86.8%。所提方法的实验结果优于其他方法,对小目标的检测性能显著提升。

The existing general detection methods still have the problem of high missing rate in small target detection.To improve the detection rate of the head,the ResNet DenseNet MDC(Mixed Dilated Convolution)YOLOv3(RDMYOLOv3)target detection network is proposed on the basis of YOLOv3.Firstly,the feature extraction network DarkNet53 of YOLOv3 is improved,and a feature extraction network RDNet based on ResNet and DenseNet is proposed to extract more semantic information.Then,a mixed dilated convolution structure is constructed by sampling the feature layers using dilated convolution with different dilated rates to improve the sensitivity to small targets.Using RDMYOLOv3 to compare with other methods on B rainwash dataset and HollywoodHeads dataset,the AP(Average Precision)values reached 93.1%and 86.8%,respectively.The experimental results are better than that of other methods,and the performance of small target detection is significantly improved.