基于FD-SSD的遥感图像多目标检测方法  

REMOTE SENSING IMAGE MULTI-TARGET DETECTION METHOD BASED ON FD-SSD

作　　者：朱敏超 冯涛[1] 张钰[1] Zhu Minchao;Feng Tao;Zhang Yu(School of Electronics and Information,Hangzhou Dianzi University,Hangzhou 310018,Zhejiang,China)

机构地区：[1]杭州电子科技大学电子与信息学院,浙江杭州310018

出　　处：《计算机应用与软件》2019年第1期232-238,共7页Computer Applications and Software

基　　金：国家自然科学基金项目(61372156)

摘　　要：针对遥感图像中目标物体过小,不易检测的难点,提出对SSD的改进网络FD-SSD(Feature Fusion and Dilated Convolution Single Shot Multibox Detector)。FD-SSD去掉了SSD网络数据预处理层的随机剪裁步骤,并结合FSSD将具有高分辨率的低层特征图和具有高语义信息的高层特征图进行融合。使用空洞卷积增大第三层特征图的感受野,利用具有高分辨率的低层特征图对小目标进行预测。同时不再使用1×1的顶层特征图产生目标框。模型训练阶段将原始遥感图像进行"二次切割"处理,增加训练样本量。在预测阶段先将原始图像进行切割预测,再将目标框映射回原图,并对原图所有的目标框进行二次非极大值抑制(NMS),保留最优目标框。FD-SSD在DOTA数据集上有良好的表现,比原始SSD的m AP提升31%。Aiming at the difficulty that the object in remote sensing image was too small to be detected easily,FD-SSD(feature fusion and dilated convolution single shot multibox detector),an improved network of SSD,was proposed.FD-SSD removed the random tailoring steps in SSD network data preprocessing layer.It was combined with FSSD to integrate the feature map with high resolution in lower layer into the feature map with high semantic information in higher layer.Dilated convolution was adopted to enlarge the receptive field of the feature map in the third layer.The feature map with high resolution in lower layer was used to predict the small targets.The top-level feature map with dimension of 1×1 was no longer used to generate the target box.In the model training phase,FD-SSD performed the secondary cutting for the original remote sensing image to increase the training samples.In the prediction stage,it cut and predicted the original image,and mapped the target frame back to the original image.All the target frames of the original image were subjected to quadratic NMS to preserve the optimal target frame.FD-SSD has an excellent performance on the DOTA dataset.Compared with mAP of the previous SSD,it increases by 31%.

关 键 词：遥感图像 目标检测 特征融合 空洞卷积 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]