基于自适应特征增强的小目标检测网络  

Small-Target Detection Network Based on Adaptive Feature Enhancement

作　　者：吴萌萌 张泽斌[1] 宋尧哲 舒子婷 李宝清[1] Wu Mengmeng;Zhang Zebin;Song Yaozhe;Shu Ziting;Li Baoqing(Key Laboratory of Microsystem Technology,Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences,Shanghai 201800,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院上海微系统与信息技术研究所微系统技术重点实验室,上海201800 [2]中国科学院大学,北京100049

出　　处：《激光与光电子学进展》2023年第6期55-62,共8页Laser & Optoelectronics Progress

摘　　要：由于尺寸有限、外观和几何线索较少以及缺少大规模小目标数据集,从图像中检测小目标仍然是计算机视觉领域中一个具有挑战性的难题.针对这个问题,提出一种自适应特征增强的目标检测网络(YOLO-AFENet)来改善小目标的检测精度.首先,通过引入特征融合因子,设计改进的自适应双向特征融合模块,充分利用各个尺度的特征图,提高网络的特征表达能力;其次,结合网络自身的特点,提出空间注意力生成模块,通过学习图像中感兴趣区域的位置信息以提高网络的特征定位能力.在UAVDT数据集上实验结果表明:所提YOLO-AFENet的平均精度(AP)比改进前的YOLOv5提高了 6.3个百分点,同时也优于其他目标检测网络.Smalltarget detection from images remains a challenge in the field of computer vision because of the limited size,small appearance and geometric clues,and lack of largescale smalltarget datasets.To solve this issue,an adaptive featureenhanced target detection network called YOLOAFENet is proposed to improve the accuracy of smalltarget detection.First,by introducing the feature fusion factor,an improved adaptive bidirectional feature fusion module is designed using feature maps of various scales to improve the network’s feature expression ability.Second,combined with the network characteristics,a spatial attention generation module is proposed to improve the network’s feature localization ability by identifying the location information of the region of interest in the image.The experimental results of the UAVDT dataset show that YOLOAFENet has a 6.3 percentage points higher average accuracy compared with YOLOv5 and is better than other targetdetection networks.

关 键 词：图像处理 目标检测 小目标 多尺度特征融合 空间注意力 UAVDT 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]