Multi-target Detection in Remote Sensing Images Based on Dilated Spatial Pyramid Pooling U-Net

ZHANG Shanwen; XU Xinhua; QI Guohong

doi:10.15892/j.cnki.djzdxb.2023.05.001

Journal of Projectiles, Rockets, Missiles and Guidance >

2023 , Vol. 43 >Issue 5: 1 - 8

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2023.05.001

Multi-target Detection in Remote Sensing Images Based on Dilated Spatial Pyramid Pooling U-Net

ZHANG Shanwen ,
XU Xinhua ,
QI Guohong

Expand

School of Electronic and Information Engineering, Zhengzhou Sias University, Zhengzhou 451150, Henan, China

Received date: 2022-01-01

Online published: 2024-12-30

Fold

Abstract

Target detection in remote sensing image (RSI) is an important and challenging research. Aiming at the problems of relatively small targets, uneven non-target, complex background and diverse deformation in RSI, a dilated spatial pyramid pooling U-Net (DSPPU) model is constructed for multi-target detection in RSI. In DPPU, dilated multi-scale convolution is used to extract the classification features of multi-scale targets, and dilated spatial pooling pyramid (DSPP) module is used to enlarge the convolutional receptive field to extract more adequate target features. Moreover, attention mechanism, residual connection and skip connection are used to fully retain the sensitive features of the RSI extracted by the convolutional layer. Experimental results on EORSSD, a public remote sensing image database show that the proposed method can detect multi-scale objects from complex and diverse RSI with a detection accuracy of 96.56%.

Key words： multi-target detection in remote sensing image; dilated multi-scale convolution; dilated spatial pyramid pooling; DSPP U-Net

Cite this article

ZHANG Shanwen , XU Xinhua , QI Guohong . Multi-target Detection in Remote Sensing Images Based on Dilated Spatial Pyramid Pooling U-Net[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2023 , 43(5) : 1 -8 . DOI: 10.15892/j.cnki.djzdxb.2023.05.001

[an error occurred while processing this directive]

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	GUO Z, SONG P, ZHANG Y, et al. Aircraft detection method based on deep convolutional neural network for remote sensing images[J]. Journal of Electronics and Information Technology, 2018, 40(11): 2684-2690.

[2]	李晓斌, 江碧涛, 杨渊博, 等. 光学遥感图像目标检测技术综述[J]. 航天返回与遥感, 2019, 40(4): 95-104. LI X B, JIANG B T, YANG Y B, et al. A survey on object detection technology in optical remote sensing images[J]. Spacecraft Recovery & Remote Sensing, 2019, 40(4): 95-104.

[3]	YE M. A lightweight model of VGG-16 for remote sensing image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 6916-6922.

[4]	CHENG G, HAN J. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2016, 117: 11-28.

[5]	LUO J, ZENG J X, FU J, et al. Aircraft target recognition in remote sensing images based on saliency maps and invariant moments[C]// International Sociaty of Geometry and Graphics. Proceedings of the 18th International Conference on Geometry and Graphics. Milan: ISGG, 2019: 1358-1365.

[6]	李婕, 周顺, 朱鑫潮, 等. 结合多通道注意力的遥感图像飞机目标检测[J]. 计算机工程与应用, 2022, 58(1): 209-217. DOI LI J, ZHOU S, ZHU X C, et al. Remote sensing image aircraft target detection combined with multiple channel attention[J]. Computer Engineering and Applications, 2022, 58(1): 209-217. DOI

[7]	YU P D, WANG X, LIU J H, et al. Bridge target detection in remote sensing image based on improved YOLOv4 algorithm[C]// ACM. Proceedings of the 2020 4th International Conference on Computer Science and Artificial Intelligence. New York: ACM, 2020: 139-145.

[8]	ZHANG Q J, CONG R M, LI C Y, et al. Dense attention fluid network for salient object detection in optical remote sensing images[J]. IEEE Transactions on Image Processing, 2020, 30: 1305-1317.

[9]	ZHENG J, QUAN Y, ZHENG H, et al. ORSI salient object detection via cross-scale interaction and enlarged receptive field[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 1-5.

[10]	宋晓茹, 刘康, 高嵩, 等. 基于深度学习的军事目标识别算法综述[J]. 科学技术与工程, 2022, 22(22): 9466-9475. SONG X R, LIU K, GAO S, et al. Overview of military target recognition algorithms based on deep learning[J]. Science Technology and Engineering, 2022, 22(22): 9466-9475.

[11]	TU Z Z, WANG C, LI C L, et al. ORSI salient object detection via multiscale joint region and boundary model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5607913.

[12]	周秦汉, 王振. 基于多尺度特征增强卷积神经网络遥感目标检测算法[J]. 电光与控制, 2022, 29(11): 78-81. ZHOU Q H, WANG Z. A remote sensing target detection algorithm based on multi-scale feature enhancement CNNs[J]. Electronics Optics & Control, 2022, 29(11) : 74-81.

[13]	ZHENG Z, ZHANG T, LIU Z, et al. Arbitrarily oriented object detection in remote sensing images based on improved YOLOv4-CSP[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 9355-9368.

[14]	SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(4): 640-651.

[15]	张翠军, 安冉, 马丽. 改进U-Net的遥感图像中建筑物变化检测[J]. 计算机工程与应用, 2021, 57(3): 239-246. DOI ZHANG C J, AN R, MA L. Building change detection in remote sensing image based on improved U-Net[J]. Computer Engineering and Applications, 2021, 57(3): 239-246. DOI

[16]	张善文, 齐国红, 徐新华. 基于轻量级多尺度注意力U-Net的遥感图像飞机检测方法[J]. 弹箭与制导学报, 2022, 42(5): 108-112. ZHANG S W, QI G H, XU X H. Lightweight multi-scale attention U-Net for aircraft detection in remote sensing image[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2022, 42(5): 108-112.

[17]	MU Y, LI J, LUO T Y, et al. A lightweight model of VGG-U-Net for remote sensing image classification[J]. Computers, Materials, & Continua, 2022(12): 6195-6205.

[18]	AHMED K R. Smart pothole detection using deep learning based on dilated convolution[J]. Sensors, 2021, 21(24), 8406.

[19]	LIAN X H, PANG Y W, HAN J G, et al. Semantic segmentation with hybrid pyramid pooling and stacked pyramid structure[J]. Neurocomputing, 2020, 410: 454-467.

Options

Outlines