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.
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)
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)
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)
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 .
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
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)
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 .
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)