高分辨率特征增强的无人机航拍小目标检测  

Small Target Detection in UAV Aerial Images Based on High Resolution Feature Enhancement

作　　者：周璇 葛琦[1] 邵文泽[1] ZHOU Xuan;GE Qi;SHAO Wenze(College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学通信与信息工程学院,南京210003

出　　处：《数据采集与处理》2024年第4期908-921,共14页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61972213)。

摘　　要：针对无人机航拍图像背景复杂、小尺寸目标分布密集等造成的检测精度低等问题,提出一种高分辨率特征增强的无人机航拍小目标检测算法。首先,提出了高分辨率特征增强网络,通过减少主干网络的下采样倍数来扩大输出特征图的尺度,同时引入双线性插值法来减少采样后特征信息的丢失,从而保留更多语义特征与细节特征。其次,在主干网络嵌入一种结合局部跨阶段结构的快速空间金字塔池化(Spatial pyramid pooling fast cross stage partial construction,SPPFCSPC)模块,增强局部与全局特征的信息融合,从而获得更大的感受野。最后,通过马赛克混合数据增强方法来增强图像背景的复杂度,提高模型的泛化能力。在公开数据集VisDrone 2019上的实验结果表明,与“你只需看一次”(You only look once,YOLO)系列等其他主流算法相比,本文算法的平均精度均值有显著的提高,在不同场景下均验证了本文算法的优越性,表明本文算法对无人机航拍图像的密集小目标检测任务有较强的实用性。Aiming at the problem of low detection accuracy caused by complex background and dense distribution of small size targets in unmanned aerial vehicle(UAV),this paper proposes a small target detection algorithm based on high resolution feature enhancement.Firstly,a high-resolution feature enhancement network is proposed,which expands the scale of the output feature map by reducing the subsampling times of the backbone.At the same time,the bilinear interpolation is introduced to reduce the loss of feature information after up-sampling,thereby preserving more semantic and detailed features.Secondly,the spatial pyramid pooling-fast module combined with the cross stage partial structure is embedded in the backbone to enhance the information fusion of local and global features,so as to obtain a larger receptive field.Finally,the mosaic-mixup data enhancement method is used to enhance the complexity of image background and improve the generalization ability of the model.Experimental results on the public dataset VisDrone 2019 show that compared with other mainstream algorithms such as the“you only look once”(YOLO)series,the mean average precision of the proposed algorithm has significantly improved.The advantages of the proposed algorithm have been verified in different scenarios,indicating that the algorithm has strong practicality for dense small target detection tasks in UAV aerial images.

关 键 词：小目标检测 无人机航拍图像 空间金字塔池化 

分 类 号：TN911.73[电子电信—通信与信息系统]