Application of multi-scale fusion super-resolution algorithm in UAV detection

LI Zhipeng; ZHAO Changming; ZHANG Haiyang; ZHANG Zilong; WU Xuan

doi:10.5768/JAO202142.0302003

Journal of Applied Optics > 2021 > 42(3): 462-473. > DOI: 10.5768/JAO202142.0302003

LI Zhipeng, ZHAO Changming, ZHANG Haiyang, ZHANG Zilong, WU Xuan. Application of multi-scale fusion super-resolution algorithm in UAV detection[J]. Journal of Applied Optics, 2021, 42(3): 462-473. DOI: 10.5768/JAO202142.0302003

Citation:

PDF (1454 KB)

Application of multi-scale fusion super-resolution algorithm in UAV detection

LI Zhipeng^{1, 2,},
ZHAO Changming^{1, 2},
ZHANG Haiyang^{1, 2, ,},
ZHANG Zilong^{1, 2},
WU Xuan^{1, 2}

1.
Key Laboratory of Optoelectronic Imaging Technology and System (Ministry of Education), Beijing 100081, China
2.
School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China

More Information

Received Date: November 10, 2020
Revised Date: December 06, 2020
Available Online: May 09, 2021

Graphical Abstract

Abstract

Abstract

The low-speed and small unmanned aerial vehicle (UAV) detection system based on photoelectric sensors can quickly and accurately find and identify the UAV targets. However, the proportion of pixels in the images of long-distance non-cooperative UAV targets is too small, and the degradation of characteristics is obvious, which greatly reduce the recognition rate. The image super-resolution technology can obtain the high-resolution images from low-resolution target image regions and restore the more detailed features. The existing super-resolution technology is difficult to be compatible with the high and low frequency characteristics of images while ensuring the inference speed. In order to meet the requirements of detection system, based on the feature extraction and nonlinear mapping network structure of fast super-resolution convolutional neural network (FSRCNN), and combined with the multi-scale fusion, a lightweight multi-scale fusion super-resolution network with 4 branches was proposed, which could be compatible with the high and low frequency image information in super-resolution graphics and with low parameter quantity and high real-time performance. The experimental results show that the UAV contours and details with high resolution can be reconstructed more quickly and efficiently by this algorithm. In the experiment of YOLOV3 detection effect, the confidence degree of the UAV detection can be increased by 6.72% by this algorithm, which has high practical application values.
- unmanned aerial vehicle detection system,
- lightweight,
- multi-scale fusion,
- super-resolution

FullText(HTML)

References (22)

References

[1]	胡文娟, 张毅. 反无人机系统的研究与实现[J]. 中国民航飞行学院学报,2020,31(2):30-34. doi: 10.3969/j.issn.1009-4288.2020.02.007 HU Wenjuan, ZHANG Yi. Research and implementation of anti-UAV system[J]. Journal of Civil Aviation Flight University of China,2020,31(2):30-34. doi: 10.3969/j.issn.1009-4288.2020.02.007
[2]	PIERACCINI M, MICCINESI L, ROJHANI N. RCS measurements and ISAR images of small UAVs[J]. IEEE Aerospace and Electronic Systems Magazine,2017,32(9):28-32. doi: 10.1109/MAES.2017.160167
[3]	向凡夫, 郝冬青, 吴鹏. 针对低慢小目标的雷达信号处理算法[J]. 指挥控制与仿真,2019,41(4):40-46. doi: 10.3969/j.issn.1673-3819.2019.04.009 XIANG Fanfu, HAO Dongqing, WU Peng. A radar signal processing algorithm for low, slow and small targets[J]. Command Control and Simulation,2019,41(4):40-46. doi: 10.3969/j.issn.1673-3819.2019.04.009
[4]	EL J S, FIORANELLI F, ANDERSON D. Review of radar classification & RCS characterisation techniques for small UAVs or drones[J]. IET Radar Sonar? Navigation,2018,12(9):911-919. doi: 10.1049/iet-rsn.2018.0020
[5]	OPROMOLLA R, FASANO G, ACCARDO D. A vision-based approach to UAV detection and tracking in cooperative applications[J]. Sensors,2018,18(10):3391. doi: 10.3390/s18103391
[6]	ANDRAŠI P, RADIŠIĆ T, MUŠTRA M, et al. Night-time detection of UAVs using thermal infrared camera[J]. Transportation Research Procedia,2017,28:183-190. doi: 10.1016/j.trpro.2017.12.184
[7]	SHOUFAN A, AL-ANGARI H M, SHEIKH M, et al. Drone pilot identification by classifying radio-control signals[J]. IEEE Transactions on Information Forensics & Security,2018:2439-2447.
[8]	HARVEY B, O’YOUNG S. Acoustic detection of a fixed-wing UAV[J]. Drones,2018,2(1):4. doi: 10.3390/drones2010004
[9]	任永平. 反无人机系统中目标探测跟踪技术研究[D]. 西安: 西安工业大学, 2019. REN Yongping. Research on target detection and tracking technology in anti-UAV system[D]. Xi’an: Xi’an Technological University, 2019.
[10]	李有为. 基于小目标检测的自然场景交通标志识别[D]. 成都: 电子科技大学, 2020. LI Youwei. Natural scene traffic sign recognition based on small target detection[D]. Chengdu: University of Electronic Science and Technology of China, 2020.
[11]	黄露. 压缩监控视频中车牌超分辨率和识别算法研究[D]. 杭州: 浙江大学, 2017. HUANG Lu. Research on license plate super-resolution and recognition algorithm in compressed surveillance video[D]. Hangzhou: Zhejiang University, 2017.
[12]	DONG C, LOY C C, HE K, et al. Learning a deep convolutional network for image super-resolution[C]// European Conference on Computer Vision. Cham, Switzerland: Springer, 2014.
[13]	DONG C, LOY C C, TANG X. Accelerating the super-resolution convolutional neural network[C]// European Conference on Computer Vision. Cham, Switzerland: Springer, 2016.
[14]	LEDIG C, THEIS L, HUSZAR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). USA: IEEE, 2016.
[15]	WANG X, YU K, WU S, et al. ESRGAN: enhanced super-resolution generative adversarial networks[C]// European Conference on Computer Vision. Cham, Switzerland: Springer, 2018.
[16]	CHE K, CHEN Y, XIANG Z, et al. Research of infrared image super-resolution reconstruction based on improved FSRCNN[C]//Proceedings of the Conference on Research in Adaptive and Convergent Systems. [S.l.]: ACM, 2019.
[17]	曲海成, 唐博文, 袁贵森. 一种改进的SRCNN超分辨率图像重建算法[J]. 激光与光电子学进展,2021,58(2):18. QU Haicheng, TANG Bowen, YUAN Guisen. An improved SRCNN super-resolution image reconstruction algorithm[J]. Laser and Optoelectronics Progress,2021,58(2):18.
[18]	SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). USA: IEEE, 2020.
[19]	MONTSERRAT D M, LIN Q, ALLEBACH J, et al. Training object detection and recognition cnn models using data augmentation[J]. Electronic Imaging,2017,2017(10):27-36. doi: 10.2352/ISSN.2470-1173.2017.10.IMAWM-163
[20]	EDUARDO R, ANDREAS U, GEORG W, et al. Exploring deep learning and transfer learning for colonic polyp classification[J]. Computational and Mathematical Methods in Medicine,2016(6584725):1-16.
[21]	JOHNSON J, ALAHI A, LI F. Perceptual losses for real-time style transfer and super-resolution[C]// European Conference on Computer Vision. Cham, Switzerland: Springer, 2016.
[22]	HU Y, WU X, ZHENG G, et al. Object Detection of UAV for anti-UAV based on improved YOLO v3[C]// 2019 Chinese Control Conference (CCC). USA: IEEE, 2019.

[1]	DING Wei, YANG Jiegen, HU Feng, ZOU Liner. Design of ultra-short focal miniature projection lens based on DMD[J]. Journal of Applied Optics, 2023, 44(6): 1294-1299. DOI: 10.5768/JAO202344.0601002
[2]	LIU Xiaochan, CHEN Chen, SONG Tao, LI Weishan, ZHANG Xin, GAO Song, YANG Bo. Optical design of spherical zone projection lens for small and medium-sized flight simulator[J]. Journal of Applied Optics, 2023, 44(1): 30-36. DOI: 10.5768/JAO202344.0101005
[3]	LUO Rui, LIANG Xiuling. Design of large-aperture and wide-spectrum zoom lens[J]. Journal of Applied Optics, 2022, 43(5): 839-845. DOI: 10.5768/JAO202243.0501002
[4]	WANG Kang, DUAN Jie, ZHOU Jianhong, WANG Chen, FU Yuegang. Design on projection objective of portable projector[J]. Journal of Applied Optics, 2019, 40(2): 316-322. DOI: 10.5768/JAO201940.0205003
[5]	Huang Yaolin, Wang Min, Lin Zheng. Design of zoom projection lens with large aperture and wild view[J]. Journal of Applied Optics, 2018, 39(3): 412-417. DOI: 10.5768/JAO201839.0305002
[6]	Hou Guozhu, Lyu Lijun. Design of large aperture zoom projection lens[J]. Journal of Applied Optics, 2018, 39(3): 405-411. DOI: 10.5768/JAO201839.0305001
[7]	Ju Rongbing, Kang Lianjie, Han Min, Liu Yan. Design of miniprojection wideangle lens[J]. Journal of Applied Optics, 2016, 37(4): 527-531. DOI: 10.5768/JAO201637.0401006
[8]	LI Wei-shan, CHEN Chen, ZHANG Yu, LIU Xiao-chan. Digital light processing mini-projection lens based on ZEMAX[J]. Journal of Applied Optics, 2011, 32(6): 1121-1125.
[9]	LI Wei-shan, CHEN Chen, ZHANG Yu, LIU Xiao-chan. Design of short focal digital projection lens based on ZEMAX[J]. Journal of Applied Optics, 2010, 31(5): 714-717.
[10]	SONG Dong-fan, ZHANG Ping, WANG Cheng, ZHANG Ren-jian, REN Zhao-yu, BAI Jin-tao. Design of mobile phone camera lens based on ZEMAX[J]. Journal of Applied Optics, 2010, 31(1): 34-38.

Cited By

Cited by

Periodical cited type(3)

1.	刘尊辈，蔡毅，刘福平，马俊卉，张猛蛟，王岭雪. 分孔径紫外多波段成像光学系统设计. 中国光学. 2021(06): 1476-1485 .
2.	李西杰，刘钧，邹纯博，杨佳婷. 双波段共口径同时偏振光学系统设计. 西安工业大学学报. 2020(01): 25-31 .
3.	陈旭，吴智勇，赵新潮，周兴雷，王丁. 中红外双通道滤波器的研制. 光学仪器. 2020(01): 32-39 .

Other cited types(3)

Get Citation

PDF

XML

Article views (1217) PDF downloads (95) Cited by(6)

Turn off MathJax

Article Contents

Abstract

References

Application of multi-scale fusion super-resolution algorithm in UAV detection