一种自适应红外目标尺寸变化的检测跟踪算法

杨擎宇; 王永让; 李昊; 唐善军; 李芳; 张国华

一种自适应红外目标尺寸变化的检测跟踪算法

1.
上海机电工程研究所, 上海 201109
2.
中国人民解放军 63961 部队, 北京 100012
3.
海军装备部, 北京 100071

详细信息

作者简介:
杨擎宇（1996-），男，工程师，研究方向：探测制导及控制。E-mail: qing_yu_yang@126.com

中图分类号: TN976
计量
- 文章访问数: 164
- HTML全文浏览量: 43
- PDF下载量: 42
出版历程
- 收稿日期: 2022-07-02
- 修回日期: 2022-08-09
- 刊出日期: 2022-11-19

Adaptive Detection and Tracking Algorithm for Infrared Target Size Variation

1.
Shanghai Electro-Mechanical Engineering Institute, Shanghai 201109, China
2.
Unit 63961 of Chinese People's Liberation Army, Beijing 100012, China
3.
Naval Equipment Department, Beijing 100071, China

摘要

摘要: 在实际场景中随着红外探测距离的缩小，红外弱小目标的尺寸等会动态增长，常用的红外弱小目标检测跟踪算法便无法继续稳定检测与跟踪。为解决上述问题，本文提出了一种自适应红外目标尺寸变化的检测跟踪方法，借助低阈值信噪比实现弱小目标的初筛，并通过自适应尺寸分割避免大目标漏检误检，构建备选目标库，最后配合使用卡尔曼算法模型预测运动轨迹，完成小范围波门检测，实现目标跟踪。与传统DBT（Detection Before Track）跟踪检测算法相比，本文算法可同时兼顾弱小目标和大尺寸目标的检测跟踪，在所选目标尺寸动态增长的场景中，本文算法的检测跟踪率提升了约10%。
- 卡尔曼 /
- 尺寸变化 /
- 检测跟踪
Abstract: In an actual scenario, as the detection distance decreases, the size of the infrared weak and small targets increases dynamically. Commonly used infrared weak and small target detection and tracking algorithms cannot continue to detect and track stably. To address these problems, we propose an adaptive infrared target size change detection and tracking method. The initial screening of weak and small targets is realized with the help of a low threshold signal-to-noise ratio and circumvents the missed detection and false detection of large targets via adaptive size segmentation. Subsequently, we built an alternative target library. Finally, the Kalman algorithm model was adopted to predict the motion trajectory, complete the small-scale wave-gate detection, and realize target tracking. Compared with the DBT conventional detection and tracking algorithm, our method considers the detection and tracking of weak and small targets and large-sized targets simultaneously. In the selected scene, where the target size dynamically increases, the detection and tracking rate of the algorithm in this study is improved by approximately 10%.
- Kalman /
- size change /
- detection and tracking

HTML全文

图 1 本文算法流程

Figure 1. Our algorithm flow chart

下载: 全尺寸图片幻灯片

图 2 原始信噪比（上）与分割后的疑似目标（下）

Figure 2. Original SNR(upper) suspected target after segmentation(down)

下载: 全尺寸图片幻灯片

图 3 降采样

Figure 3. Down sampling

下载: 全尺寸图片幻灯片

图 4 海面俯视背景下红外图像（上）疑似目标及提取窗口（下）

Figure 4. Infrared Image in the Sea Surface Top View Background (upper) Suspected target and extraction window (down)

下载: 全尺寸图片幻灯片

图 5 卡尔曼轨迹预测

Figure 5. Kalman trajectory prediction

下载: 全尺寸图片幻灯片

图 6 本文检测结果及目标特性提取

（蓝色为1号轨迹链，红色为2号轨迹链，绿色为3号轨迹链）

Figure 6. Detection results and target characteristics extraction in this paper

(blue is No. 1 track chain, red is No. 2 track chain, and green is No. 3 track chain)

下载: 全尺寸图片幻灯片

图 8 复杂多云背景检测跟踪

Figure 8. Detection and tracking of complex and cloudy background

下载: 全尺寸图片幻灯片

图 9 海面俯视背景检测跟踪

Figure 9. Top view of sea surface background detection and tracking

下载: 全尺寸图片幻灯片

图 10 海天线背景检测跟踪

Figure 10. Detection and tracking under sea antenna background

下载: 全尺寸图片幻灯片

表 1 不同距离成像像素

Table 1 Imaging pixels at different distances

Distance/km	Imaging pixel dimensions	Pixel growth
5	1.76×1.76	-
4.5	1.94×1.94	0.18
4	2.22×2.22	0.28
3.5	2.51×2.51	0.29
3	2.93×2.93	0.42
2.5	3.52×3.52	0.59
2	4.4×4.4	0.88
1.5	5.9×5.9	1.5
1	8.8×8.8	2.1
0.5	17.5×17.5	8.7

下载: 导出CSV

表 2 不同尺寸定义下对应检测波门的实验结果

Table 2 Experimental results of corresponding detection gates under different size definitions

Gate size/1	Complex and cloudy background				Top view background of sea surface				Sea antenna background
Gate size/1	Detection tracking rate/%	Undetected rate/%	False alarm rate/%	Frame rate/Hz	Detection tracking rate/%	Undetected rate/%	False alarm rate/%	Frame rate/Hz	Detection tracking rate/%	Undetected rate/%	False alarm rate/%	Frame rate/Hz
3×3	98	2	7.4	55	90	10	7	51	91.8	8.2	5	56
5×5	98.5	1.5	7	50	94.1	5.9	2	48	93.5	6.5	3	52
8×8	98	2	6	44	95	5	5	43	92	8	3.2	46
12×12	94.4	5.6	15	31	91.2	8.8	12	29	88.6	11.4	4	31

下载: 导出CSV

表 3 不同背景红外数据集下算法表现

Table 3 Algorithm performance under different background infrared data sets

Infrared image	Low SNR target detection algorithm				Our algorithm
Infrared image	Detection tracking rate/%	Undetected rate/%	False alarm rate/%	Frame rate/Hz	Detection tracking rate/%	Undetected rate/%	False alarm rate/%	Frame rate/Hz
Complex and cloudy background	98	2	8	45	98.5	1.5	7	50
Top view background of sea surface	85.8	14.2	3	42	94.1	5.9	2	48
Seaantenna background	82.9	17.1	5	46	93.5	6.5	3	52

下载: 导出CSV

参考文献(15)

[1]	BAI Xiangzhi, ZHANG Shan, DU Binbin, et al. Survey on dim small target detection in clutter background: wavelet, inter-frame and filter based algorithms[J]. Procedia Engineering, 2011, 15: 479-483. DOI: 10.1016/j.proeng.2011.08.091
[2]	MING Z, LI J, ZHANG P. The design of Top-Hat morphological filter and application to infrared target detection[J]. Infrared Physics & Technology, 2006, 48(1): 67-76.
[3]	FAN Q, YANG Y, ZOU E B. A novel infrared target detection and tracking method[C]// Seventh Symposium on Novel Photoelectronic Detection Technology and Application, 2020: 117631L.
[4]	王莹莹, 张永顺, 华永伟. 红外目标检测方法分析[J]. 红外技术, 2011, 33(3): 133-140. DOI: 10.3969/j.issn.1001-8891.2011.03.002 WANG Y Y, ZHANG Y S, HUA Y W. Analysis on infrared target detection methods[J]. Infrared Technology, 2011, 33(3): 133-140. DOI: 10.3969/j.issn.1001-8891.2011.03.002
[5]	王翔. 一种复杂海空背景下的红外小目标检测跟踪算法[J]. 光学与光电技术, 2022, 20(2): 113-119. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD202202014.htm WANG X. A detection and tracking algorithm for infrared small target in complex sea sky background[J]. Optics & Optoelectronic Technology, 2022, 20(2): 113-119. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD202202014.htm
[6]	ZHAO T, WANG T, CAO Y, et al. Infrared dim and small target detection and tracking based on single multi-frame algorithm under sea clutter background[C]// 2019 Chinese Control Conference (CCC), 2019: 402-407.
[7]	郭伟, 赵亦工, 谢振华. 一种改进的红外图像归一化互相关匹配算法[J]. 光子学报, 2009, 38(1): 189-193. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB200901040.htm GUO W, ZHAO Y G, XIE Z H. An Improved normalized cross-correlation for template matching of infrared image[J]. Acta Photonica Sinica, 2009, 38(1): 189-193. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB200901040.htm
[8]	张晋, 王元余, 林丹丹, 等. 基于相关滤波的红外目标跟踪抗遮挡处理[J]. 红外技术, 2022, 44(3): 277-285. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS202203015.htm ZHANG J, WANG Y Y, LIN D D, et al. Anti-occlusion process of infrared target tracking based on correlation filters[J]. Infrared Technology, 2022, 44(3): 277-285. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS202203015.htm
[9]	王曙光, 石胜斌, 胡春生. 一种对空红外弱小目标检测跟踪方法研究[J]. 红外技术, 2020, 42(4): 356-360. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS202004008.htm WANG Y G, SHI S B, HU C S. Detection and tracking method for infrared dim small targets in air[J]. Infrared Technology, 2020, 42(4): 356-360. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS202004008.htm
[10]	杨昳, 徐长彬, 马玉莹, 等. 低信噪比下的红外弱小目标检测算法研究综述[J]. 激光与红外, 2019, 49(6): 643-649. https://www.cnki.com.cn/Article/CJFDTOTAL-JGHW201906002.htm YANG Y, XU C B, MA Y Y, et al. A review of infrared dim small target detection algorithms with low SNR[J]. Laser & Infrared, 2019, 49(6): 643-649. https://www.cnki.com.cn/Article/CJFDTOTAL-JGHW201906002.htm
[11]	宋敏敏, 王爽, 吕弢, 等. 一种天地复杂背景下的红外弱小目标检测方法[J]. 红外技术, 2018, 40(10): 996-1001. http://hwjs.nvir.cn/article/id/hwjs201810011 SONG M M, WANG S, LYU T, et al. A method for infrared dim target detection in complex scenes of sky and ground[J]. . Infrared Technology, 2018, 40(10): 996-1001 http://hwjs.nvir.cn/article/id/hwjs201810011
[12]	施元斌, 张晓杰, 王兴. 基于梯度和各向异性扩散的红外双波段目标检测方法[J]. 空天防御, 2021, 4(4): 95-100. https://www.cnki.com.cn/Article/CJFDTOTAL-KTFY202104014.htm SHI Y B, ZHANG X J, WANG X. Infrared dual-band target detection method based on gradient and anisotropic diffusion[J]. Air & Space Defense, 2021, 4(4): 95-100. https://www.cnki.com.cn/Article/CJFDTOTAL-KTFY202104014.htm
[13]	LI Z M, MEI L F, SONG M. A survey on infrared weak small target detection method[J]. Advanced Materials Research, 2014, 945-949: 1558-1560.
[14]	施天俊, 鲍广震, 王福海, 等. 一种适用于多场景的红外弱小目标检测跟踪算法[J]. 航空兵器, 2019, 26(6): 35-42. https://www.cnki.com.cn/Article/CJFDTOTAL-HKBQ201906007.htm SHI T J, BAO G Z, WANG F H, et al. An infrared small target detection and tracking algorithm applying for multiple scenarios[J]. Aero Weaponry, 2019, 26(6): 35-42. https://www.cnki.com.cn/Article/CJFDTOTAL-HKBQ201906007.htm
[15]	李静. 基于区域生长和背景配准的低信噪比红外目标检测算法[J]. 红外技术, 2014, 36(11): 909-913. http://hwjs.nvir.cn/article/id/hwjs201411011 LI J. Detection method of moving infrared target integrating based on region growing and background[J]. Infrared Technology, 2014, 36(11): 909-913. http://hwjs.nvir.cn/article/id/hwjs201411011

施引文献(27)

期刊类型引用(12)

1.	刘和，宋璎珞，胡龙湘，刘国辉，王侃，王爱丽. 基于空间金字塔注意力机制残差网络的高光谱图像分类. 液晶与显示. 2024(06): 833-843 . 百度学术
2.	吴庆岗，刘中驰，贺梦坤. 融合MS3D-CNN和注意力机制的高光谱图像分类. 重庆理工大学学报(自然科学). 2023(02): 173-182 . 百度学术
3.	张云龙，齐国红，许新华. 基于模式识别技术的高光谱图像分类研究. 激光杂志. 2023(07): 95-99 . 百度学术
4.	贺敏慧，何敬，刘刚. 改进的混合2D-3D卷积神经网络高光谱图像分类研究. 时空信息学报. 2023(02): 184-192 . 百度学术
5.	张晓瑞. 基于卷积神经网络的多标签图像分类识别算法研究. 通化师范学院学报. 2022(02): 75-82 . 百度学术
6.	王欣，樊彦国. 基于改进DenseNet和空谱注意力机制的高光谱图像分类. 激光与光电子学进展. 2022(02): 211-222 . 百度学术
7.	孔祥魁，樊翠红. 多特征融合和最小二乘支持向量机的运动视频图像分类研究. 南京理工大学学报. 2022(02): 164-169+176 . 百度学术
8.	郑爽，梁云浩，武俊峰，乔壮，刘付刚. 基于AlexNet-SN网络的煤与煤矸石分类方法. 中国矿业. 2022(06): 79-85 . 百度学术
9.	王晨海，陈澳，王康乐. 虚拟现实环境下基于红外光谱的多特征纹理图像视觉传达方法研究. 激光杂志. 2022(11): 154-158 . 百度学术
10.	吴鸿昊，王立国，石瑶. 高光谱图像小样本分类的卷积神经网络方法. 中国图象图形学报. 2021(08): 2009-2020 . 百度学术
11.	吴涛. 基于特征提取和半监督学习的图像分类算法. 粘接. 2021(11): 92-97 . 百度学术
12.	杨远陶，刘瑞，曹礼刚，杨梅，陈景珏. 基于随机森林算法的珠海一号高光谱影像土地利用信息提取. 物探化探计算技术. 2021(06): 818-824 . 百度学术