基于改进VariFocalNet的微小目标检测

Tiny target detection based on improved VariFocalNet

针对航拍场景中包含的目标尺寸小、有效特征信息少的问题,提出一种基于改进的变焦网络VFNet(VariFocalNet)的航拍场景中微小目标检测算法。首先,为增强微小目标的特征表征能力,采用特征提取性能更好的循环层聚合网络(RLANet)代替ResNet作为主干网络;其次,为解决特征金字塔自顶向下融合时顶层特征信息丢失问题,引入特征增强模块(FEM);然后,为解决现有标签分配方法在微小目标标签分配上的样本分布不平衡问题,改进的VFNet采用了基于高斯感受野的标签分配方法;最后,为减小微小目标对位置偏移的敏感性,引入一种边界框回归损失函数Wasserstein损失测量预测边界框高斯分布和真值框高斯分布的相似性。在AI-TOD数据集上的实验结果表明:改进后的VFNet算法的平均精度均值(mAP)达到了14.9%;与改进前的算法相比,在航拍场景下的微小目标上的检测mAP提高了4.7个百分点。

Aiming at the problems of small target size and little effective feature information in aerial photography scenes,an improved tiny target detection algorithm based on variable focal network VFNet(VariFocalNet)was proposed.Firstly,in order to enhance the feature representation capability for tiny targets,the Recurrent Layer Aggregation Network(RLANet)with better feature extraction performance was adopted as the backbone network,replacing ResNet.Next,a Feature Enhancement Module(FEM)was introduced to solve the problem of the top-level feature information loss when the feature pyramid was fused from top to bottom.Then,to solve the problem of unbalanced sample distribution in the label assignment of tiny targets in existing label allocation methods,in the improved VFNet,the label assignment stratery based on Gaussian receptive field was adopted.Finally,to reduce the sensitivity of position deviation for tiny targets,a boundingbox regression loss function,Wasserstein loss,was introduced to measure the similarity between the Gaussian distribution of predicted bounding box and that of groundtruth bounding box.The experimental results on the AI-TOD dataset demonstrate that the mean Average Precision(mAP)of the improved VFNet algorithm reaches 14.9%;compared with the previous VFNet,the detection mAP of tiny targets increases by 4.7 percentage points in aerial photography scenes.