An accurate detection algorithm for time backtracked projectile-induced water columns based on the improved YOLO network

doi:10.23919/JSEE.2023.000106

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (4): 981-991.doi: 10.23919/JSEE.2023.000106

• • 上一篇

收稿日期:2022-02-21 出版日期:2023-08-18 发布日期:2023-08-28

An accurate detection algorithm for time backtracked projectile-induced water columns based on the improved YOLO network

Yasong LUO¹(), Jianghu XU¹^,*(), Chengxu FENG¹(), Kun ZHANG²()

¹ College of Weapon Engineering, Naval University of Engineering, Wuhan 430033, China
² Unit 91115 of the PLA, Zhoushan 316000, China

Received:2022-02-21 Online:2023-08-18 Published:2023-08-28
Contact: Jianghu XU E-mail:yours_baggio@sina.com;xujianghu123@sina.com;kerryfengcx@126.com;zhangkun_547@sina.com
About author:
LUO Yasong was born in 1982. He received his B.S., M.S., and Ph.D. degrees from Naval University of Engineering in 2004, 2007, and 2010. Currently he is an associate professor in Naval University of Engineering. His research interests are intelligent identification and unmanned system. E-mail: yours_baggio@sina.com

XU Jianghu was born in 1975. He received his B.S. and M.S. degrees from Dalian Naval Academy, and Ph.D. degree from Naval University of Engineering in 2008. Currently he is a lecturer in Naval University of Engineering. His research interests are electronic countermeasure and signal processing. E-mail: xujianghu123@sina.com

FENG Chengxu was born in 1986. He received his B.S. and M.S. degrees from Huazhong University of Science and Technology, and Ph.D. degree from Naval University of Engineering in 2014. Currently he is a lecturer in Naval University of Engineering. His research interests are system engineering and data fusion. E-mail: kerryfengcx@126.com

ZHANG Kun was born in 1993. He received his B.S. and M.S. degrees from Naval University of Engineering. Currently he is an engineer in Unit 91115 of the PLA. His research interests include unmanned combat system and adaptive target detection. E-mail: zhangkun_547@sina.com
Supported by:
This work was supported by the National Natural Science Foundation of China (51679247)

摘要/Abstract

Abstract:

During a sea firing training, the intelligent detection of projectile-induced water column targets in a firing video is the prerequisite for and critical to the automatic calculation of miss distance, while the correct and precise calculation of miss distance is directly affected by the accuracy, false alarm rate and time delay of detection. After analyzing the characteristics of projectile-induced water columns, an accurate detection algorithm for time backtracked projectile-induced water columns based on the improved you only look once (YOLO) network is put forward. The capability and accuracy of detecting projectile-induced water column targets with the conventional YOLO network are improved by optimizing the anchor box through K-means clustering and embedding the squeeze and excitation (SE) attention module. The detection area is limited by adopting a sea-sky line detection algorithm based on gray level co-occurrence matrix (GLCM), so as to effectively eliminate such disturbances as ocean waves and ship wakes, and lower the false alarm rate of projectile-induced water column detection. The improved algorithm increases the mAP₅₀ of water column detection by 30.3%. On the basis of correct detection, a time backtracking algorithm is designed with mean shift to track images containing projectile-induced water column in reverse time sequence. It accurately detects a projectile-induced water column at the time of its initial appearance as well as its pixel position in images, and considerably reduces detection delay, so as to provide the support for the automatic, accurate, and real-time calculation of miss distance.

Key words: object recognition, projectile-induced water column, you only look once (YOLO), K-means, squeeze and excitation (SE), mean shift

. [J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 981-991.

Yasong LUO, Jianghu XU, Chengxu FENG, Kun ZHANG. An accurate detection algorithm for time backtracked projectile-induced water columns based on the improved YOLO network[J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 981-991.

图/表 11

参考文献 17

18	FAHIM A K and starting means for k-means algorithm. Journal of Computational Science, 2021, 55, 101445.
19	LIU S X, LIU X D. Research on density-based k-means clustering algorithm. Proc. of the 5th International Conference on Electrical, Mechanical and Computer Engineering, 2021: 29−31.
20	HUANG S Y. Research and implementation of convolution k-means algorithm based on unsupervised learning. Proc. of the 2nd International Conference on Computer Information and Big Data Applications, 2021: 26−28.
21	HU J, SHEN L, SUN G. Squeeze-and-excitation networks. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132−7141.
22	ZHENG Y Y, XU S W, XU X L Facial expression recognition method based on squeeze and excitation module. International Core Journal of Engineering, 2021, 7 (3): 433- 439.
23	ROY A G, NAVAB N, WACHINGER C Recalibrating fully convolutional networks with spatial and channel “squeeze and excitation” blocks. IEEE Trans. on Medical Imaging, 2019, 38 (2): 540- 549.
24	LIANG D, LIANG Y. Horizon detection from electro-optical sensors under maritime environment. IEEE Trans. on Instrumentation and Measurement, 2020, 69(1): 45−53.
25	BAI Y M, LEI S D, LIU L C. The ship target detection based on sea-sky-line. Proc. of the 6th International Conference on Automation, Control and Robotics Engineering, 2021: 474−478.
26	FENG T W, LIU J Q, XIAO J C, et al Sea-sky line detection methods: an overview. Laser and Optoelectronics Progress, 2020, 57, 160002. doi: 10.3788/LOP57.160002
27	LIANG D, ZHANG W G, HUANG Q Z, et al. Robust sea-sky-line detection for complex sea background. Proc. of the IEEE International Conference on Progress in Informatics and Computing, 2015: 348−352.
28	JING H L, NIE J Efficient integral image calculation based on gray level co-occurrence matrix. Journal of Jilin Normal University (Natural Science Edition), 2014, 35 (4): 136- 138.
29	MWHAK N S A comparison of k-means and mean shift algorithms. International Journal of Theoretical and Applied Mathematics, 2021, 7 (5): 76- 84.
30	FENG Z W. High speed moving target tracking algorithm based on mean shift for video human motion. Proc. of the International Conference on Mechanical Automation and Computer Engineering, 2020: 28−30.
1	ZHANG X B, YING W W, YANG P X, et al Parameter estimation of impulsive noise with Class B model. IET Radar, Sonar and Navigation, 2020, 14 (7): 1055- 1060. doi: 10.1049/iet-rsn.2019.0477
2	ZHANG X B, WU H R, SUN H X, et al Multireceiver SAS imagery based on monostatic conversion. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14, 10835- 10853. doi: 10.1109/JSTARS.2021.3121405
3	GUO H Y, YANG X, WANG N N, et al A CenterNet++ model for ship detection in SAR images. Pattern Recognition, 2021, 112, 107787. doi: 10.1016/j.patcog.2020.107787
4	WANG Z Q, ZHOU Y, WANG F T, et al SDGH-Net: ship detection in optical remote sensing images based on Gaussian heatmap regression. Remote Sensing, 2021, 13 (3): 499. doi: 10.3390/rs13030499
5	ZHONG Y F, HAN X B, ZHANG L P Multi-class geospatial object detection based on a position-sensitive balancing framework for high spatial resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 138, 281- 294. doi: 10.1016/j.isprsjprs.2018.02.014
6	HUANG F Q, CHEN M, FENG G F Improved yolo object detection algorithm based on deformable convolution. Computer Engineering, 2021, 47 (10): 269- 275, 282.
7	ZHU M M, HU G P, ZHOU H, et al. Rapid ship detection in SAR images based on YOLOv3. Proc. of the 5th International Conference on Communication, Image and Signal Processing, 2020: 13−15.
8	CHEN L Q, SHI W X, DENG D X Improved YOLOv3 based on attention mechanism for fast and accurate ship detection in optical remote sensing images. Remote Sensing, 2021, 13 (4): 660. doi: 10.3390/rs13040660
9	LI Q Z, XU X Y Fast detection of surface ship targets based on improved YOLOV3-Tiny. Computer Engineering, 2020, 47 (10): 283- 297.
10	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 27−30.
11	REDMON J, FARHADI A. YOLO9000: better, faster, stronger. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6517−6525.
12	REDMON J, FARHADI A. YOLOv3: an incremental improvement. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 2767−2773.
13	XIE B H, YUAN S, GONG D L. Detection of blocked pedestrians based on RDB-YOLOv4 in the mine. Computer Engineering and Applications, 2021, 58(5): 200−207. (in Chinese)
14	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection. https://doi.org/10.48550/arXiv.2004.10934.
15	YUAN M X, ZHANG L M, ZHU Y S, et al Ship target detection based on deep learning method. Ship Science and Technology, 2019, 41 (1): 111- 115, 124.
16	LI J W, QU C W, SHAO J Q. Ship detection in SAR images based on an improved faster R-CNN. Proc. of the SAR in Big Data Era: Models, Methods and Applications, 2017: 17413068.
17	YANG J C, ZHAO C Survey on k-means clustering algorithm. Computer Engineering and Applications, 2019, 55 (23): 7- 14, 63.

Mode	K-means	SE	Sea-sky line	P/%	R/%	mAP₅₀/%	FPS
YOLOv4_0				76.2	56.2	53.5	42
YOLOv4_1	√			88.3	66.0	66.3	42
YOLOv4_2		√		88.7	78.7	75.6	38
YOLOv4_3			√	90.0	67.7	67.0	26
YOLOv4_4	√	√		90.3	80.0	79.4	28
YOLOv4_5	√	√	√	94.5	83.0	83.8	21

An accurate detection algorithm for time backtracked projectile-induced water columns based on the improved YOLO network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 17

相关文章 0

编辑推荐

Metrics

本文评价