基于强化底层特征的无人机航拍图像小目标检测算法  

Small object detection algorithm on UAV aerial images based on enhanced lower feature

作　　者：吕晓君 向伟[1,2,4,5] 刘云鹏 Lyu Xiaojun;Xiang Wei;Liu Yunpeng(Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics&Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of Opto-electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China;Key Laboratory of Image Understanding&Computer Vision,Shenyang 110016,China)

机构地区：[1]中国科学院沈阳自动化研究所,沈阳110016 [2]中国科学院机器人与智能制造创新研究院,沈阳110169 [3]中国科学院大学,北京100049 [4]中国科学院光电信息处理重点实验室,沈阳110016 [5]辽宁省图像理解与视觉计算重点实验室,沈阳110016

出　　处：《计算机应用研究》2021年第5期1567-1571,共5页Application Research of Computers

基　　金：中国科学院科技创新重点基金资助项目(Y8K4160401)。

摘　　要：针对无人机航拍图像小目标检测整体精度低、漏检误检的问题,提出了一种新的基于强化底层特征的多尺度小目标检测方法。该方法以Faster R-CNN-ResNet-50-FPN为基础模型,首先,设计提出了新的DetNet-59特征提取网络;其次,设计了扁平的Flat-FPN特征融合网络来提高强化底层特征;最后通过引入soft-NMS解决小目标重叠问题。所提出的算法在VOC2007和VisDrone2019数据集上进行仿真实验测试,在时间消耗提升不大于2%的情况下,mAP较基础模型提高了约11%,并且检测精度也优于现阶段的常用算法。实验结果表明,该算法在保证实时性的同时可以有效提高小目标检测精度。In order to solve the problem of low accuracy and residual error in small object detection on UAV aerial images,this paper proposed a new kind of multi-scale small target detection method based on enhanced lower feature.Basing on Faster R-CNN ResNet-50-FPN model,the algorithm enhanced the lower feature by designing the structure of DetNet-59 feature extraction network and Flat-FPN feature fusion network,and applied soft-NMS to face the appearance of overlapping small objects.From simulation test on VOC2007 and VisDrone2019,the method is able to increase mAP by 11%compared to the base model when time consumption is no more than 2%,and it also performs better in terms of accuracy than current common algorithms.It was proved that the algorithm can effectively improve the detection accuracy of small targets while ensuring real-time performance.

关 键 词：无人机 底层特征 深度学习 小目标检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]