浏览全部资源
扫码关注微信
1.南京理工大学 电子工程与光电技术学院,江苏 南京 210094
2.南京理工大学 江苏省光谱成像与智能感知重点实验室,江苏 南京 210094
E-mail: minjiewan1992@njust.edu.cn; gghnjust@mail.njust.edu.cn
收稿日期:2021-03-27,
修回日期:2021-04-16,
移动端阅览
陈欣,万敏杰,马超等.采用多尺度特征融合SSD的遥感图像小目标识别[J].光学精密工程,
CHEN Xin,WAN Min-jie,MA Chao,et al.Remote sensing image small target recognition using multi-scale feature fusion-based SSD[J].Optics and Precision Engineering,
陈欣,万敏杰,马超等.采用多尺度特征融合SSD的遥感图像小目标识别[J].光学精密工程, DOI:10.37188/OPE..0001
CHEN Xin,WAN Min-jie,MA Chao,et al.Remote sensing image small target recognition using multi-scale feature fusion-based SSD[J].Optics and Precision Engineering, DOI:10.37188/OPE..0001
针对复杂背景下遥感小目标的识别问题,提出了一种改进型多尺度特征融合SSD方法。首先,设计了一种特征图融合机制,将分辨率高的浅层特征图与具有丰富语义信息的深层特征图进行融合,并在特征图间构建特征金字塔,对小目标特征进行增强。然后,引入通道注意力模块,通过构建权重参数空间,将注意力更多的集中在关注目标区域的通道,以减小背景干扰。最后,对先验框相对于原图的比例进行了调整,使其能够更好地适应遥感小目标尺度。利用采集的遥感飞机图像数据集对方法性能进行定性和定量测试,结果表明:改进方法检测精度相较SSD提高了4.3%,其能够适应复杂场景下的遥感多尺度目标识别任务,降低小目标的漏检率。
For the recognition of small remote sensing targets in complex backgrounds, an improved multi-scale feature fusion-based single shot multi-box detector (SSD) method is proposed. First, a feature map fusion mechanism is designed to fuse shallow high-resolution feature maps and deep feature maps with rich semantic information, and feature pyramids between feature maps are built to enhance small target features. Then, the channel attention module is introduced to overcome the background interference by constructing a weight parameter space to put more attention on the channels that focus on the target region. Finally, the scale between the priori box and the original map is adjusted to better fit the remote sensing small target scale. Qualitative and quantitative tests based on remote sensing aircraft image datasets are implemented, and the results show that the proposed method improves the detection accuracy by 4.3% when compared with SSD, and can adapt to multi-scale remote sensing target recognition tasks in complex scenes and reduce the missing detection rate of small targets.
范丽丽 , 赵宏伟 , 赵浩宇 , 等 . 基于深度卷积神经网络的目标检测研究综述 [J]. 光学 精密工程 , 2020 , 28 ( 5 ): 1152 - 1164 .
FAN L L , ZHAO H W , ZHAO H Y , et al . Survey of target detection based on deep convolutional neural networks [J]. Opt. Precision Eng. , 2020 , 28 ( 5 ): 1152 - 1164 . (in Chinese)
方路平 , 何杭江 , 周国民 . 目标检测算法研究综述 [J]. 计算机工程与应用 , 2018 , 54 ( 13 ): 11 - 18, 33 .
FANG L P , HE H J , ZHOU G M . Research overview of object detection methods [J]. Computer Engineering and Applications , 2018 , 54 ( 13 ): 11 - 18, 33 . (in Chinese)
徐胜军 , 欧阳朴衍 , 郭学源 , 等 . 多尺度特征融合空洞卷积 ResNet遥感图像建筑物分割 [J]. 光学 精密工程 , 2020 , 28 ( 7 ): 1588 - 1599 .
XU S J , OUYANG P Y , GUO X Y , et al . Building segmentation in remote sensing image based on multiscale-feature fusion dilated convolution resnet [J]. Opt. Precision Eng. , 2020 , 28 ( 7 ): 1588 - 1599 . (in Chinese)
陈彦彤 , 李雨阳 , 吕石立 , 等 . 基于深度语义分割的多源遥感图像海面溢油监测 [J]. 光学 精密工程 , 2020 , 28 ( 5 ): 1165 - 1176 .
CHEN Y T , LI Y Y , LÜ S L , et al . Research on oil spill monitoring of multi-source remote sensing image based on deep semantic segmentation [J]. Opt. Precision Eng. , 2020 , 28 ( 5 ): 1165 - 1176 . (in Chinese)
REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 .
LIU W , ANGUELOV D , ERHAN D , et al . SSD : Single Shot MultiBox Detector [M]. Computer Vision-ECCV 2016. Cham : Springer International Publishing , 2016 : 21 - 37 .
REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once: unified, real-time object detection [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2730,2016 , Las Vegas, NV, USA . IEEE , 2016 : 779 - 788 .
王博 , 董登峰 , 周维虎 , 等 . 面向激光跟踪仪跟踪恢复的合作目标视觉检测 [J]. 光学 精密工程 , 2020 , 28 ( 2 ): 271 - 282 .
WANG B , DONG D F , ZHOU W H , et al . Visual detection of target ball for laser tracker target tracking recovery [J]. Opt. Precision Eng. , 2020 , 28 ( 2 ): 271 - 282 . (in Chinese)
FU C Y , LIU W , RANGA A , et al . DSSD: deconvolutional single shot detector [EB/OL]. 2017
LI Z X , ZHOU F Q . FSSD: feature fusion single shot multibox detector [EB/OL]. 2017
王建林 , 付雪松 , 黄展超 , 等 . 改进YOLOv2卷积神经网络的多类型合作目标检测 [J]. 光学 精密工程 , 2020 , 28 ( 1 ): 251 - 260 .
WANG J L , FU X S , HUANG Z C , et al . Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network [J]. Opt. Precision Eng. , 2020 , 28 ( 1 ): 251 - 260 . (in Chinese)
王俊强 , 李建胜 , 周学文 , 等 . 改进的SSD算法及其对遥感影像小目标检测性能的分析 [J]. 光学学报 , 2019 , 39 ( 6 ): 0628005 .
WANG J Q , LI J S , ZHOU X W , et al . Improved SSD algorithm and its performance analysis of small target detection in remote sensing images [J]. Acta Optica Sinica , 2019 , 39 ( 6 ): 0628005 . (in Chinese)
LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2126,2017 , Honolulu, HI, USA . IEEE , 2017 : 936 - 944 .
姚群力 , 胡显 , 雷宏 . 基于多尺度卷积神经网络的遥感目标检测研究 [J]. 光学学报 , 2019 , 39 ( 11 ): 1128002 .
YAO Q L , HU X , LEI H . Object detection in remote sensing images using multiscale convolutional neural networks [J]. Acta Optica Sinica , 2019 , 39 ( 11 ): 1128002 . (in Chinese)
0
浏览量
675
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构