Improved SSD based aircraft remote sensing image target detection

Hao-tong WANG; Zhong-hua GUO

doi:10.37188/CJLCD.2021-0203

您当前的位置：

首页 >

文章列表页 >

Improved SSD based aircraft remote sensing image target detection

Image Processing | 更新时间：2022-01-19

- Improved SSD based aircraft remote sensing image target detection
- Chinese Journal of Liquid Crystals and Displays Vol. 37, Issue 1, Pages: 116-127(2022)
- 作者机构：
  
  1.宁夏大学物理与电子电气工程学院, 宁夏银川 750021
  2.宁夏沙漠信息智能感知重点实验室, 宁夏银川 750021
- 作者简介：
- 基金信息：
  
  Natural Science Foundation of Ningxia Hui Autonomous Region(2020AAC03026)
- DOI：10.37188/CJLCD.2021-0203
  CLC： TP394.1;TH691.9
- Received：05 August 2021，
  
  Revised：09 September 2021，
  
  Published：2022-01
- 稿件说明：
移动端阅览
Hao-tong WANG, Zhong-hua GUO. Improved SSD based aircraft remote sensing image target detection[J]. Chinese journal of liquid crystals and displays, 2022, 37(1): 116-127.
DOI：

Hao-tong WANG, Zhong-hua GUO. Improved SSD based aircraft remote sensing image target detection[J]. Chinese journal of liquid crystals and displays, 2022, 37(1): 116-127. DOI： 10.37188/CJLCD.2021-0203.

摘要

针对当前飞机遥感图像目标检测算法的精度和实时性不能兼顾的问题，提出了基于SSD（Single Shot MultiBox Detector）的飞机遥感图像目标检测算法。首先使用经过改进后的深度残差网络替换SSD的骨架网络，对于特征图之间缺少特征信息关联和特征通道间缺少差异性权重值的问题，设计了一种含有特征感受野增强模块与注意力机制模块的新型特征金字塔网络。该网络用以融合不同层级的特征信息和训练特征通道间的权重系数，使得深层网络和浅层网络都得到结构层次丰富的融合特征，为后续网络的分类与定位提供了良好的前提。另外，在改进后的SSD算法中还使用了聚焦分类损失函数来解决正负样本不平衡的问题。在飞机遥感数据集上进行相关实验，精度均值达到92.45%，每秒帧率为35.6。结果表明，改进后的SSD算法能够同时兼顾高检测精度和实时性。

Abstract

Aiming at the problem that the accuracy and real-time performance of current aircraft remote sensing image target detection algorithms can not be balanced

an aircraft remote sensing image target detection algorithm based on single shot multibox detector(SSD) is proposed. Firstly

the improved deep residual network is used to replace the skeleton network of SSD. For the problems of lack of feature information association between feature maps

and different channels from feature maps have no weight values

this paper designs a new feature pyramid network with feature receptive field enhancement module and attention mechanism module. The network is used to fuse the feature information of different levels and the weight coefficients between the training feature channels

so that both the deep network and the shallow network can obtain fusion features with rich structural levels

which provides a good prerequisite for the classification and positioning of the subsequent network. In addition

the focus classification loss function is also used in the improved SSD algorithm to solve the problem of imbalance between positive and negative samples. Related experiments are carried out on the aircraft remote sensing data set

and the average accuracy reaches 92.45%

and the frame per second is 35.6. The results show that the improved SSD algorithm can balance high detection accuracy and real-time performance at the same time.

关键词

Keywords

references

张艳 , 杜会娟 , 孙叶美 , 等 . 基于改进SSD算法的遥感图像目标检测 . 计算机工程 , 2021 . 47 ( 9 ): 252 - 258,265 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202109031.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202109031.htm , .

Y ZHANG , H J DU , Y M SUN , 等 . Object detection in remote sensing images based on improved SSD algorithm . Computer Engineering , 2021 . 47 ( 9 ): 252 - 258,265 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202109031.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202109031.htm , .

林娜 , 冯丽蓉 , 张小青 . 基于优化Faster-RCNN的遥感影像飞机检测 . 遥感技术与应用 , 2021 . 36 ( 2 ): 275 - 284 . https://www.cnki.com.cn/Article/CJFDTOTAL-YGJS202102004.htm https://www.cnki.com.cn/Article/CJFDTOTAL-YGJS202102004.htm , .

N LIN , L R FENG , X Q ZHANG . Aircraft detection in remote sensing image based on optimized faster-RCNN . Remote Sensing Technology and Application , 2021 . 36 ( 2 ): 275 - 284 . https://www.cnki.com.cn/Article/CJFDTOTAL-YGJS202102004.htm https://www.cnki.com.cn/Article/CJFDTOTAL-YGJS202102004.htm , .

王浩桐, 郭中华. 锚框策略匹配的SSD飞机遥感图像目标检测[J/OL]. 计算机科学与探索, (2021-07-26)[2021-08-18] . http://kns.cnki.net/kcms/detail/11.5602.TP.20210726.1310.002.html http://kns.cnki.net/kcms/detail/11.5602.TP.20210726.1310.002.html .

WANG H T, GUO Z H. Target detection of SSD aircraft remote sensing images based on anchor frame strategy matching[J/OL]. Journal of Frontiers of Computer Science and Technology , (2021-07-26)[2021-08-18]. http://kns.cnki.net/kcms/detail/11.5602.TP.20210726.1310.002.html http://kns.cnki.net/kcms/detail/11.5602.TP.20210726.1310.002.html . (in Chinese)

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Proceedings of the 25th International Conference on Neural Information Processing Systems . Lake Tahoe, Nevada: Curran Associates Inc., 2012: 1097-1105.

GIRSHICK R. Fast R-CNN[C]// 2015 IEEE International Conference on Computer Vision (ICCV) . Santiago, Chile: IEEE, 2015: 1440-1448.

S Q REN , K M HE , R GIRSHICK , 等 . Faster R-CNN: towards real-time object detection with region proposal networks . IEEE Transactions on pattern Analysis and Machine Intelligence , 2017 . 39 ( 6 ): 1137 - 1149 . DOI: 10.1109/TPAMI.2016.2577031 http://doi.org/10.1109/TPAMI.2016.2577031 .

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]// Conference on Computer Vision and Pattern Recognition . Las Vegas, USA: IEEE, 2016: 779-788.

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot MultiBox detector[C]// 14th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 21-37.

董旭彬 , 赵清华 . 改进Mask R-CNN在航空影像目标检测的研究应用 . 计算机工程与应用 , 2021 . 57 ( 8 ): 133 - 144 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201921024.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201921024.htm , .

X B DONG , Q H ZHAO . Research and application of improved Mask R-CNN in aerial image target detection . Computer Engineering and Applications , 2021 . 57 ( 8 ): 133 - 144 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201921024.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG201921024.htm , .

李靓 , 贺柏根 , 霍家道 . FPN在遥感图像检测中的应用 . 指挥控制与仿真 , 2019 . 41 ( 2 ): 130 - 136 . DOI: 10.3969/j.issn.1673-3819.2019.02.025 http://doi.org/10.3969/j.issn.1673-3819.2019.02.025 .

L LI , B G HE , J D HUO . Application of FPN in remote sensing image . Command Control & Simulation , 2019 . 41 ( 2 ): 130 - 136 . DOI: 10.3969/j.issn.1673-3819.2019.02.025 http://doi.org/10.3969/j.issn.1673-3819.2019.02.025 .

叶子琦 , 王晓寅 , 张恒瑞 . 基于Faster R-CNN的遥感图像目标检测技术 . 电子世界 , 2020 . ( 8 ): 63 - 64 . https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202008040.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202008040.htm , .

Z Q YE , X Y WANG , H R ZHANG . Remote sensing image target detection technology based on faster R-CNN . Electronics World , 2020 . ( 8 ): 63 - 64 . https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202008040.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW202008040.htm , .

X YU , L R FU , B S DAI , 等 . Soybean leaf morphology classification based on FPN-SSD and knowledge distillation . Journal of Northeast Agricultural University (English Edition) , 2020 . 27 ( 4 ): 9 - 17 . .

辛鹏 , 许悦雷 , 唐红 , 等 . 全卷积网络多层特征融合的飞机快速检测 . 光学学报 , 2018 . 38 ( 3 ): 0315003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201803036.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201803036.htm , .

P XIN , Y L XU , H TANG , 等 . Fast airplane detection based on multi-layer feature fusion of fully convolutional networks . Acta Optica Sinica , 2018 . 38 ( 3 ): 0315003 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201803036.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201803036.htm , .

LIN T Y, DOLLÁR P, GIRSHICK R, et al . Feature pyramid networks for object detection[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu, USA: IEEE, 2017: 936-944.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, USA: IEEE, 2016: 770-778.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556 , 2014.

李克文 , 李新宇 . 基于SENet改进的Faster R-CNN行人检测模型 . 计算机系统应用 , 2020 . 29 ( 4 ): 266 - 271 . https://www.cnki.com.cn/Article/CJFDTOTAL-XTYY202004041.htm https://www.cnki.com.cn/Article/CJFDTOTAL-XTYY202004041.htm , .

K W LI , X Y LI . Pedestrian detection model based on improved faster R-CNN with SENet . Computer Systems & Applications , 2020 . 29 ( 4 ): 266 - 271 . https://www.cnki.com.cn/Article/CJFDTOTAL-XTYY202004041.htm https://www.cnki.com.cn/Article/CJFDTOTAL-XTYY202004041.htm , .

T Y LIN , P GOYAL , R GIRSHICK , 等 . Focal loss for dense object detection . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 . 42 ( 2 ): 318 - 327 . DOI: 10.1109/TPAMI.2018.2858826 http://doi.org/10.1109/TPAMI.2018.2858826 .

邹慧海, 侯进. 基于改进SSD算法的道路小目标检测研究[J/OL]. 计算机工程, (2021-06-09)[2021-07-13] . https://kns.cnki.net/kcms/detail/31.1289.tp.20210608.1800.003.html https://kns.cnki.net/kcms/detail/31.1289.tp.20210608.1800.003.html .

ZOU H H, HOU J. Research on road small target detection based on improved SSD algorithm[J/OL]. Computer Engineering , (2021-06-09)[2021-07-13]. https://kns.cnki.net/kcms/detail/31.1289.tp.20210608.1800.003.html https://kns.cnki.net/kcms/detail/31.1289.tp.20210608.1800.003.html . (in Chinese)

刘建伟 , 赵会丹 , 罗雄麟 , 等 . 深度学习批归一化及其相关算法研究进展 . 自动化学报 , 2020 . 46 ( 6 ): 1090 - 1120 . https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202006002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202006002.htm , .

J W LIU , H D ZHAO , X L LUO , 等 . Research progress on batch normalization of deep learning and its related algorithms . Acta Automatica Sinica , 2020 . 46 ( 6 ): 1090 - 1120 . https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202006002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO202006002.htm , .

XU J, LI Z S, DU B W, et al . Reluplex made more practical: leaky ReLU[C]// Proceedings of the 2020 IEEE Symposium on Computers and Communications ( ISCC ). Rennes, France: IEEE, 2020: 1-7.

邢永鑫, 孙游东, 王天一. 基于改进SSD算法对奶牛的个体识别[J/OL]. 计算机工程与应用, (2020-12-09)[2021-08-04] . http://kns.cnki.net/kcms/detail/11.2127.tp.20201208.1537.024.html http://kns.cnki.net/kcms/detail/11.2127.tp.20201208.1537.024.html .

XING Y X, SUN Y D, WANG T Y. Individual recognition of dairy cow based on improved SSD algorithm[J/OL]. Computer Engineering and Applications , (2020-12-09)[2021-08-04]. http://kns.cnki.net/kcms/detail/11.2127.tp.20201208.1537.024.html http://kns.cnki.net/kcms/detail/11.2127.tp.20201208.1537.024.html . (in Chinese)

胡志伟 , 杨华 , 娄甜田 . 采用双重注意力特征金字塔网络检测群养生猪 . 农业工程学报 , 2021 . 37 ( 5 ): 166 - 174 . https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU202105019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU202105019.htm , .

Z W HU , H YANG , T T LOU . Instance detection of group breeding pigs using a pyramid network with dual attention feature . Transactions of the Chinese Society of Agricultural Engineering , 2021 . 37 ( 5 ): 166 - 174 . https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU202105019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-NYGU202105019.htm , .

西北工业大学. NWPU VHR-10[EB/OL]. (2014-04-24)[2021-09-09] . https://hyper.ai/datasets/5422 https://hyper.ai/datasets/5422 .

Northwestern Polytechnical University. NWPU VHR-10[EB/OL]. (2014-04-24)[2021-09-09] . https://hyper.ai/datasets/5422 https://hyper.ai/datasets/5422 . (in Chinese)

李娜 , 姜志 , 王军 , 等 . 基于Faster R-CNN的仪表识别方法 . 液晶与显示 , 2020 . 35 ( 12 ): 1291 - 1298 . DOI: 10.37188/YJYXS20203512.1291 http://doi.org/10.37188/YJYXS20203512.1291 DOI: 10.37188/YJYXS20203512.1291 http://doi.org/10.37188/YJYXS20203512.1291 .

N LI , Z JIANG , J WANG , 等 . Instrument recognition method based on Faster R-CNN . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 12 ): 1291 - 1298 . DOI: 10.37188/YJYXS20203512.1291 http://doi.org/10.37188/YJYXS20203512.1291 DOI: 10.37188/YJYXS20203512.1291 http://doi.org/10.37188/YJYXS20203512.1291 .

唐悦 , 吴戈 , 朴燕 . 改进的GDT-YOLOV3目标检测算法 . 液晶与显示 , 2020 . 35 ( 8 ): 852 - 860 . DOI: 10.37188/YJYXS20203508.0852 http://doi.org/10.37188/YJYXS20203508.0852 .

Y TANG , G WU , Y PIAO . Improved algorithm of GDT-YOLOV3 image target detection . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 8 ): 852 - 860 . DOI: 10.37188/YJYXS20203508.0852 http://doi.org/10.37188/YJYXS20203508.0852 .

任彬 , 王宇庆 , 丛振 , 等 . 基于MPSOC的航空图像目标检测系统设计 . 液晶与显示 , 2021 . 36 ( 7 ): 1006 - 1017 . DOI: 10.37188/CJLCD.2020-0310 http://doi.org/10.37188/CJLCD.2020-0310 .

B REN , Y Q WANG , Z CONG , 等 . Design of aerial image target detection system based on MPSOC . Chinese Journal of Liquid Crystals and Displays , 2021 . 36 ( 7 ): 1006 - 1017 . DOI: 10.37188/CJLCD.2020-0310 http://doi.org/10.37188/CJLCD.2020-0310 .

REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 6517-6525.

REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv: 1804.02767 , 2018.

FU C Y, LIU W, RANGA A, et al . DSSD: deconvolutional single shot detector[J]. arXiv: 1701.06659 , 2017.

李明山 , 韩清鹏 , 张天宇 , 等 . 改进SSD的安全帽检测方法 . 计算机工程与应用 , 2021 . 57 ( 8 ): 192 - 197 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202108025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202108025.htm , .

M S LI , Q P HAN , T Y ZHANG , 等 . Safety helmet detection method of improved SSD . Computer Engineering and Applications , 2021 . 57 ( 8 ): 192 - 197 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202108025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202108025.htm , .

Views

140

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Attention and feature fusion for aircraft target detection in optical remote sensing images

Water body segmentation in remote sensing images based on multi-scale fusion attention module improved UNet

High precision detection method of safety helmet based on convolution neural network

Related Author

Xu-ting LAN

Chang-hao LI

Hao-tong WANG

Zhong-hua GUO

Xu-ting LAN

Hao-tong WANG

Chang-hao LI

SHI Tian-tian

Related Institution

School of Physics and Electronic and Electrical Engineering， Ningxia University

School of Physics and Electronic-Electrical Engineering， Ningxia University

Ningxia Key Lab on Information Sensing & Intelligent Desert， Ningxia University

Electric Power Research Institute, State Grid Sichuan Electric Power Company

Key Laboratory of Artificial Intelligence in Sichuan Province, Sichuan University of Science & Engineering

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰