基于机器视觉的视频SAR运动目标检测方法

doi:10.13229/j.cnki.jdxbgxb.20220772

摘要/Abstract

摘要：

在检测视频SAR运动目标时，无法精确获得动态图像中的运动目标，为解决存在的检测完整度低、有效性差等问题，提出基于机器视觉的视频SAR运动目标检测方法。首先，通过混合高斯模型匹配运动目标像素点，得到视频SAR运动图像的目标区域；其次，利用HSV模型及反射率算法去除运动目标所产生的阴影；最后，将处理后的目标区域输入YOLO算法中完成最终的视频SAR运动目标的检测。实验结果表明：本文算法的检测完整度高、检出率高、误检率低，检测有效性更佳。

关键词: 混合高斯模型, 自适应阈值, HSV模型, 反射率, YOLO算法

Abstract:

In order to solve the problems of low detection integrity and poor detection effectiveness， a moving target detection method for video SAR Based on machine vision is proposed. Firstly， the moving target pixels are matched by Gaussian mixture model to obtain the target region of video SAR moving image. Secondly， the shadow generated by moving target is removed by HSV model and reflectivity algorithm. Finally， the processed target region is input into Yolo algorithm to complete the final video SAR moving target detection. Experimental results show that the proposed algorithm has high detection integrity， high detection rate， low false detection rate and better detection effectiveness.

Key words: Gaussian mixture model, adaptive threshold, HSV model, reflectivity, YOLO algorithm

中图分类号:

TN957.52

武狄,何鸣. 基于机器视觉的视频SAR运动目标检测方法[J]. 吉林大学学报(工学版), 2023, 53(11): 3214-3220.

Di WU,Ming HE. Video SAR moving target detection method based on machine vision[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3214-3220.

图/表 5

图1

图2

图3

图4

图5

参考文献 15

1	潘德伦, 冀隽, 张跃进. 基于运动矢量空间编码的视频监控动态目标检测方法[J]. 吉林大学学报: 工学版, 2021, 51(4): 1370-1374.
	Pan De-lun, Ji Jun, Zhang Yue-jin. Dynamic object detection method of video surveillance based on motion vector space coding[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1370-1374.
2	刘伟, 郝晓丽, 吕进来. 自适应混合高斯建模的高效运动目标检测[J]. 中国图象图形学报, 2020, 25(1): 113-125.
	Liu Wei, Hao Xiao-li, Lv Jin-lai. Efficient moving targets detection based on adaptive Gaussian mixture modelling[J]. Journal of Image and Graphics, 2020, 25(1): 113-125.
3	左军辉, 贾振红, 杨杰, 等. 基于改进背景减法的视频图像运动目标检测[J]. 计算机工程与设计, 2020, 41(5): 1367-1372.
	Zuo Jun-hui, Jia Zhen-hong, Yang Jie, et al. Moving object detection in video image based on improved background subtraction[J]. Computer Engineering and Design, 2020, 41(5): 1367-1372.
4	闫贺, 黄佳, 李睿安. 基于改进快速区域卷积神经网络的视频SAR运动目标检测算法研究[J]. 电子与信息学报, 2021, 43(3): 615-622.
	Yan He, Huang Jia, Li Rui-an. Research on video SAR moving target detection algorithm based on improved faster region-based CNN[J]. Journal of Electronics & Information Technology, 2021, 43(3): 615-622.
5	徐武, 唐文权, 郭兴. 混合高斯模型结合五帧差分的运动目标检测[J]. 小型微型计算机系统, 2021, 42(4): 785-790.
	Xu Wu, Tang Wen-quan, Guo Xing. Moving target detection based on hybrid Gaussian model and five frame difference[J]. Journal of Chinese Computer Systems, 2021, 42(4): 785-790.
6	张小艳, 郭海涛. 基于改进混合高斯模型的井下目标检测算法[J]. 工矿自动化, 2021, 47(4): 67-72.
	Zhang Xiao-yan, Guo Hai-tao. Underground target detection algorithm based on improved Gaussian mixture model[J]. Industry and Mine Automation, 2021, 47(4): 67-72.
7	尹芳, 孟迪, 李骜. 改进ViBe的运动目标检测算法[J]. 哈尔滨理工大学学报, 2022, 27(1): 23-30.
	Yin Fang, Meng Di, Li Ao. Improvement algorithm of ViBe in moving target detection[J]. Journal of Harbin University of Science and Technology, 2022, 27(1): 23-30.
8	曲优, 李文辉. 基于锚框变换的单阶段旋转目标检测方法[J]. 吉林大学学报: 工学版, 2022, 52(1): 162-173.
	Qu You, Li Wen-hui. Single-stage rotated object detection network based on anchor transformation[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 162-173.
9	哈艳, 袁伟珵, 孟翔杰. 基于增强图卷积神经网络的病毒形态识别方法研究[J]. 中国全科医学, 2022, 25(14): 1749-1756.
	Yan Ha, Yuan Wei-cheng, Meng Xiang-jie. Research on virus morphology recognition method based on enhanced graph convolutional network[J]. Chinese General Practice, 2022, 25(14): 1749-1756.
10	李朝献. 基于自适应三维立体图像增强优化处理研究[J]. 计算机仿真, 2020, 37(12): 358-361.
	Li Chao-xian. Research on optimization of 3D image enhancement based on adaptive[J]. Computer Simulation, 2020, 37(12): 358-361.
11	涂继辉, 杜红, 眭海刚. 高分辨率航空影像阴影自动检测和去除[J]. 遥感信息, 2020, 35(2): 38-45.
	Tu Ji-hui, Du Hong, Sui Hai-gang. Automatic shadow detection and removal in high resolution aerial imagery[J]. Remote Sensing Information, 2020, 35(2): 38-45.
12	王文举, 王江薇. 光谱反射率重建技术的研究进展[J]. 包装工程, 2020, 41(11): 254-261.
	Wang Wen-ju, Wang Jiang-wei. Research progress of spectral reflectance reconstruction technology[J]. Packaging Engineering, 2020, 41(11): 254-261.
13	马巧梅, 王明俊, 梁昊然. 复杂场景下基于改进YOLOv3的车牌定位检测算法[J]. 计算机工程与应用, 2021, 57(7): 198-208.
	Ma Qiao-mei, Wang Ming-jun, Liang Hao-ran. License plate location detection algorithm based on improved YOLOv3 in complex scenes[J]. Computer Engineering and Applications, 2021, 57(7): 198-208.
14	彭继慎, 孙礼鑫, 王凯. 基于模型压缩的ED-YOLO电力巡检无人机避障目标检测算法[J]. 仪器仪表学报, 2021, 42(10): 161-170.
	Peng Ji-shen, Sun Li-xin, Wang Kai. ED-YOLO power inspection UAV obstacle avoidance target detection algorithm based on model compression[J]. Chinese Journal of Scientific Instrument, 2021, 42(10): 161-170.
15	宋艳艳, 谭励, 马子豪. 改进YOLOV3算法的视频目标检测[J]. 计算机科学与探索, 2021, 15(1): 163-172.
	Song Yan-yan, Tan Li, Ma Zi-hao. Video target detection based on improved YOLOV3 algorithm[J]. Journal of Frontiers of Computer Science & Technology, 2021, 15(1): 163-172.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	刘海鸥, 张国鑫, 席军强, 张洪彦, 徐宜. 履带车辆传动系统动态载荷谱信号去噪[J]. 吉林大学学报(工学版), 2017, 47(1): 42-49.
[2]	申铉京, 翟玉杰, 卢禹彤, 王玉, 陈海鹏. 基于信道补偿的说话人识别算法[J]. 吉林大学学报(工学版), 2016, 46(3): 870-875.
[3]	王世刚，孙爱朦，赵文婷，惠祥龙. 基于时空兴趣点的单人行为及交互行为识别[J]. 吉林大学学报(工学版), 2015, 45(1): 304-308.
[4]	袁龙涛, 田翔, 陈耀武. 相控阵三维摄像声纳的自适应阈值选取[J]. 吉林大学学报(工学版), 2013, 43(03): 841-848.
[5]	刘敏时, 王晓曼, 景文博. 双波门自适应阈值法对光束质量M²因子测量精度的影响[J]. , 2012, 42(04): 1066-1070.
[6]	李娟,邵春福,杨励雅. 基于混合高斯模型的行人检测方法[J]. 吉林大学学报(工学版), 2011, 41(01): 41-0045.
[7]	冯杰,陈耀武. 基于H.264压缩域的背景建模与前景对象分割[J]. 吉林大学学报(工学版), 2011, 41(01): 239-0243.
[8]	李冬梅, 王延杰, 王长宇, 陈枫, 李德辉. 基于FPGA的高速实时图像采集和自适应阈值算法[J]. 吉林大学学报(工学版), 2010, 40(02): 534-0538.
[9]	于哲舟, 李江春, 周栩, 杨斌, 杨礼,黄岚. 基于视频流的目标检测反馈模型[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 401-0405.
[10]	连静，王珂，吕智莹. 基于B样条小波的自适应阈值多尺度边缘检测[J]. 吉林大学学报(工学版), 2005, 35(05): 542-0546.