特征增强的单阶段遥感图像目标检测模型

doi:10.19665/j.issn1001-2400.2022.03.018

Abstract

Abstract:

Purpose:The performance of remote sensing object detection has been largely improved with the development of the convolutional neural network.However,the complexity of the scene and the diversity of the target size and shape are still challenging in the remote sensing object detection task.Thus,the deep detection model of different sizes’ objects in a complex scenario is studied.Methods:Feature pyramids are an effective method for detecting objects with different sizes.But the way of transferring the feature layer by layer may lose information in the feature pyramids.Therefore,this paper proposes a feature pyramid network with shortcut connections,which can enhance the semantic and detailed information on each feature layer in the feature pyramid.Moreover,using the spatial attention weight to strengthen the possible target area is an effective method to improve the target detection rate,and it is helpful for object detection in the complex scene.But the available spatial attention will strengthen the imprecise prediction results simultaneously,so that it may interfere with the final prediction results.For this purpose,this paper proposes an anchor-based spatial attention module which mainly strengthens feature regions that are more likely to produce accurate prediction results.In this paper,the feature pyramid network with shortcut connections and the anchor-based spatial attention module are embedded into the Retina Net to form an end-to-end feature enhanced single-stage remote sensing object detection model,namely FENet (Feature Enhanced Network).Results:Experimental results show that the FENet model is 1.78% higher in mAP than the FAN (Feature Enhanced Network) on UCAS-AOD remote sensing dataset,and 1.48% higher than the FAN model on RSOD dataset.And the mAP results of the FENet are superior to those of the comparable models.In addition,the test time of the FENet for an image of 800800 pixel in a single Titan X GPU is 0.058s.Conclusions:Experimental results show that the proposed model can effectively enhance the object feature extraction ability,and thus improve the detection performance.

Key words: remote sensing image, feature pyramids, spatial attention, anchor box, single-stage object detection

CLC Number:

TP391.4

WANG Xili,LIANG Min,LIU Tao. Feature enhanced single-stage remote sensing image object detection model[J].Journal of Xidian University, 2022, 49(3): 160-170.

Figures/Tables 12

References 23

[1]	SINGH B, DAVIS L S. An Analysis of Scale Invariance in Object Detection-SNIP[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2018:3578-3587.
[2]	HU P, RAMANAN D. Finding Tiny Faces[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2017:951-959.
[3]	REN S, HE K, 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, 2017:1137-1149.
[4]	DAI J, LI Y, HE K, et al. R-FCN:Object Detection via Region-Based Fully Convolutional Networks[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. New York: ACM, 2016:379-387.
[5]	崔艳鹏, 王元皓, 胡建伟. 一种改进YOLOv3的动态小目标检测方法[J]. 西安电子科技大学学报, 2020, 47(3):1-7.
	CUI Yanpeng, WANG Yuanhao, HU Jianwei. Detection Method for a Dynamic Small Target Using the Improved YOLOv3[J]. Journal of Xidian University, 2020, 47(3):1-7.
[6]	LIU W, ANGUELOV D, ERHAN D, et al. SSD:Single Shot MultiBox Detector[C]// European Conference on Computer Vision.Heidelberg:Springer, 2016:21-37.
[7]	CAI Z, FAN Q, FERIS R S, et al. A Unified Multi-Scale Deep Convolutional Neural Network for Fast Object Detection[C]// European Conference on Computer Vision.Heidelberg:Springer, 2016:354-370.
[8]	FU C Y, LIU W, RANGA A, et al. Dssd:Deconvolutional Single Shot Detector (2017)[J/OL]. [2017-01-23]. https://arxiv.org/pdf/1701.06659v1.pdf.
[9]	ZHANG S, WEN L, BIANX, et al. Single-Shot Refinement Neural Network for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2018:4203-4212.
[10]	LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2017:2117-2125.
[11]	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[C]// Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE, 2017:2980-2988.
[12]	HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE, 2017:2961-2969.
[13]	ZHOU P, NI B, GENG C, et al. Scale-Transferrable Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2018:528-537.
[14]	KIM S W, KOOK H K, SUN J Y, et al. Parallel Feature Pyramid Network for Object Detection[C]// Proceedings of the European Conference on Computer Vision (ECCV).Heidelberg:Springer, 2018:239-256.
[15]	ZHAO Q, SHENG T, WANG Y, et al. M2Det:A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019:9259-9266.
[16]	PANG J, CHEN K, SHI J, et al. Libra R-CNN:Towards Balanced Learning for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2019:821-830.
[17]	LIU S, QI L, QIN H, et al. Path Aggregation Network for Instance Segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2018:8759-8768.
[18]	WANG J, YUAN Y, YU G. Face Attention Network:An Effective Face Detector for the Occluded Faces (2017)[J/OL]. [2017-11-20]. https://arxiv.org/pdf/1711.07246v2.pdf.
[19]	ZHU H, CHEN X, DAI W, et al. Orientation Robust Object Detection in Aerial Images Using Deep Convolutional Neural Network[C]// 2015 IEEE International Conference on Image Processing (ICIP).Piscataway:IEEE, 2015:3735-3739.
[20]	LONG Y, GONG Y, XIAO Z, et al. Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5):2486-2498. doi: 10.1109/TGRS.2016.2645610
[21]	HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2016:770-778.
[22]	TAYARA H, CHONG K. Object Detection in Very High-Resolution Aerial Images Using One-Stage Densely Connected Feature Pyramid Network[J]. Sensors, 2018, 18(10):3341. doi: 10.3390/s18103341
[23]	ZHANG Z, CHEN X, LIE J, et al. Rotated Feature Network for Multi-Orientation Object Detection (2019)[J/OL]. [2019-03-23]. https://arxiv.org/ftp/arxiv/papers/1903/1903.09839.pdf.

方法	car	plane	mAP
FAN	0.892 6	0.981 2	0.936 9
FAN+SCFPN	0.912 3	0.988 5	0.950 4

方法	car	plane	mAP
SCFPN+pool	0.912 3	0.988 5	0.950 4
SCFPN+conv	0.916 1	0.983 4	0.949 7
SCFPN+groupconv	0.909 9	0.985 6	0.947 8

方法	car	plane	mAP
FAN+SCFPN	0.912 3	0.988 5	0.950 4
FENet	0.918 0	0.991 3	0.954 7

方法	car	plane	mAP
FENet(256conv1)	0.917 2	0.987 8	0.952 5
FENet(1)	0.918 0	0.991 3	0.954 7
FENet(1conv1)	0.919 2	0.988 8	0.954 0

方法	car	plane	mAP
FENet(x+)	0.918 0	0.991 3	0.954 7
FENet(x)	0.918 0	0.986 2	0.952 1
FENet(exp)	0.922 1	0.984 8	0.953 5

Feature enhanced single-stage remote sensing image object detection model

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 23

Related Articles 6

Metrics

Comments

Recommended 10

Method	car	plane	mAP
RetinaNet	0.872 8	0.981 3	0.927 1
FAN	0.892 6	0.981 2	0.936 9
FENet	0.918 0	0.991 3	0.954 7

Method	aircraft	oil tank	overpass	playground	mAP
RFN(ResNet-101)	0.791 0	0.905 0	1.000 0	0.997 0	0.923 0
Densely Connected FPN(ResNet-50)	0.857 6	0.955 5	0.852 8	0.995 5	0.915 3
Densely Connected FPN(ResNet-101)	0.862 5	0.959 8	0.946 7	0.998 7	0.941 9
RetinaNet(ResNet-50)	0.821 5	0.970 9	0.938 7	1.000 0	0.932 7
FAN(ResNet-50)	0.844 2	0.976 0	0.951 3	1.000 0	0.942 8
FENet(ResNet-50)	0.871 6	0.983 6	0.978 3	0.996 9	0.957 6

模型	测试时间/s
BoW	5.320
COPD	1.070
Transferred CNN	5.240
RICNN	8.770
SSD	0.090
Faster R-CNN	0.160
Deformable CNN	0.200
Rotation-Insensitive CNN	2.890
Multi-Scale CN	0.110
Densely Connected FPN	0.088
FAN	0.050
FENet	0.058

[1]	ZHANG Yan,WANG Xiangyu,ZHANG Zhongwei,SUN Yemei,LIU Shudong. Boundary-aware network for building extraction from remote sensing images [J]. Journal of Xidian University, 2022, 49(1): 236-244.
[2]	DONG Ruchan,JIAO Licheng,ZHAO Jin,SHEN Weiyan. Application of the deep fusion mechanism in object detection of remote sensing images [J]. Journal of Xidian University, 2021, 48(5): 128-138.
[3]	WANG Junjun,SUN Yue,LI Ying. Cloud removal method for the remote sensing image based on the GAN [J]. Journal of Xidian University, 2021, 48(5): 23-29.
[4]	LI Hong;LIU Fang;ZHANG Kai. Remote sensing image fusion based on sparse non-negative matrix factorization [J]. Journal of Xidian University, 2016, 43(2): 193-198.
[5]	SHE Xiangyang;LI Chonggui;YAO Wanqiang. Research on the geometric correction algorithm for the remote sensing image by a support vector machine [J]. J4, 2011, 38(5): 121-128+146.
[6]	JIAN Jian-feng(1;2);YIN Zhong-hai(1);ZHOU Li-hua(1);WANG Ren-xiang(2). Target’s matching method for the remote sensing image based on the histogram invariant moments [J]. J4, 2006, 33(4): 584-587.