引入显著特征空间的抗遮挡红外目标跟踪

马天义; 张会香; 宋敏敏; 钮赛赛

doi:10.3788/IRLA201746.0304002

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

引入显著特征空间的抗遮挡红外目标跟踪

马天义, 张会香, 宋敏敏, 钮赛赛

文章导航 > 红外与激光工程 > 2017 > 46(3): 304002-0304002(7)

马天义, 张会香, 宋敏敏, 钮赛赛. 引入显著特征空间的抗遮挡红外目标跟踪[J]. 红外与激光工程, 2017, 46(3): 304002-0304002(7). doi: 10.3788/IRLA201746.0304002

引用本文:

马天义, 张会香, 宋敏敏, 钮赛赛. 引入显著特征空间的抗遮挡红外目标跟踪[J]. 红外与激光工程, 2017, 46(3): 304002-0304002(7). doi: 10.3788/IRLA201746.0304002

Ma Tianyi, Zhang Huixiang, Song Minmin, Niu Saisai. Anti-occluded infrared target tracking with salient feature space[J]. Infrared and Laser Engineering, 2017, 46(3): 304002-0304002(7). doi: 10.3788/IRLA201746.0304002

Citation:

Ma Tianyi, Zhang Huixiang, Song Minmin, Niu Saisai. Anti-occluded infrared target tracking with salient feature space[J]. Infrared and Laser Engineering, 2017, 46(3): 304002-0304002(7). doi: 10.3788/IRLA201746.0304002

引入显著特征空间的抗遮挡红外目标跟踪

doi: 10.3788/IRLA201746.0304002

1.
上海航天控制技术研究所,上海 201109

基金项目:

上海航天科技创新基金（SAST2016073）

详细信息

作者简介:
马天义(1976-),男,高级工程师,主要从事光电探测制导技术方面的研究。Email:458508175@qq.com

中图分类号: TP391

Anti-occluded infrared target tracking with salient feature space

1.
Shanghai Institute of Spaceflight Control Technology,Shanghai 201109,China

摘要: 针对红外目标跟踪过程中目标纹理信息缺乏，与背景灰度呈现强耦合性，特别是在遮挡情况下目标特征信息链断裂，特征信息无法延续的实际跟踪问题，提出了基于显著特征空间的抗遮挡跟踪算法。首先通过分析红外目标特性，利用多尺度显著性、对比度和信息熵等信息生成显著特征向量空间，结合超像素特征距离和空间距离对区域进行聚类融合，突出目标区域，生成显著图。然后融合显著区域和原图，生成多个目标候选区作为跟踪算法输入。最后通过目标的空间分布场矩阵对全局的候选区域进行匹配，同时建立遮挡检测机制，基于显著区连通区变化和特征相似度变化曲线对遮挡的起始进行判断，结合遮挡判定设置模型更新策略。在不同红外测试集上的实验结果表明：所提算法在遮挡情况下也能达到较好的跟踪效果，有效增强了跟踪算法的鲁棒性。
- 红外目标跟踪 /
- 显著特征 /
- 分布场
Abstract: Aiming at the lack of target texture information in infrared target tracking, strong coupling between the target and the background, and the case of occlusion causing that the characteristic information cannot be extended, the anti-occlusion algorithm for infrared target tracking with salient feature space was proposed. Firstly, by analyzing the characteristics of the infrared target, the salient feature space was generated by using multi-scale saliency, contrast and information entropy, and the regions were clustered with the super-pixel feature distance and spatial distance to highlight the infrared target area. By quantifying the different regions of the infrared image, the saliency map was generated. Based on the saliency map and the original image, a plurality of target candidate regions was generated as the tracking algorithms input. Finally, the spatial distribution field matrices of the infrared target were matched by way of the global candidate regions. At the same time, the occlusion detection mechanism on account of the change of the salience regions and the inter-frame variation curve of feature similarity was established. Experimental results on different IR test sets show that the proposed infrared target algorithm can achieve better tracking performance under the occlusion condition, which effectively enhances the robustness of the tracking algorithm.
- infrared target tracking /
- saliency feature /
- distribution fields

[1]	Qiao Liyong, Xu Lixin, Gao Min. Infrared target tracking using bandwidth adaptive mean shift[J]. Infrared and Laser Engineering, 2015, 44(1):354-362. (in Chinese)乔立永, 徐立新, 高敏. 带宽自适应均值偏移红外目标跟踪[J]. 红外与激光工程, 2015, 44(1):354-362.
[2]	Liu Hongbin, Chang Faliang. Moving object detection by optical flow method based on adaptive weight coefficient[J]. Optics and Precision Engineering, 2016, 24(2):460-468. (in Chinese)刘洪彬, 常发亮. 权重系数自适应光流法运动目标检测[J]. 光学精密工程, 2016, 24(2):460-468.
[3]	Yang Mingdong, Wang Jianyu, Jia Jianjun, et al. Research on technologies of space area targets high-precision tracking based on SWAD algorithm[J]. Infrared and Laser Engineering, 2016, 45(2):228002. (in Chinese)杨明冬, 王建宇, 贾建军, 等. 基于SWAD算法的空间面目标高精度跟踪技术研究[J]. 红外与激光工程, 2016, 45(2):228002.
[4]	Yang Dedong, Cai Yuzhu, Mao Ning, et al. Long-term object tracking based on kernelized correlation filters[J]. Optics and Precision Engineering, 2016, 24(8):2037-2049. (in Chinese)杨德东, 蔡玉柱, 毛宁, 等. 采用核相关滤波器的长期目标跟踪[J]. 光学精密工程, 2016, 24(8):2037-2049.
[5]	Gao Wen, Zhu Ming, He Baigen, et al. Overview of target tracking technology[J]. Chinese Optics, 2014, 7(3):365-375. (in Chinese)高文, 朱明, 贺柏根, 等. 目标跟踪技术综述[J]. 中国光学, 2014, 7(3):365-375.
[6]	Kalal Z, Mikolajczyk K, Matas J. Tracking-learning-detection[J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7):1409-1422.
[7]	Hare S, Golodetz S, Saffari A, et al. Struck:structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(10):2096-2109.
[8]	Cheng Peirui, Wang Jianli, Wang Bin, et al. Salient object detection based on multi-scale region contrast[J]. Chinese Optics, 2016, 9(1):97-105. (in Chinese)成培瑞, 王建立, 王斌, 等. 基于多尺度区域对比的显著目标识别[J]. 中国光学, 2016, 9(1):97-105.
[9]	Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2189-2202.
[10]	Rodriguez A, Laio A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191):1492-1496.
[11]	Sevilla-Lara L, Learned-Miller E. Distribution fields for tracking[C]//Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference, 2012:1910-1917.
[12]	Wu Y, Lim J, Yang M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1834-1848.

[1]	王向军, 李名洋, 王霖, 刘峰, 王玮. 边缘信息引导多级尺度特征融合的显著性目标检测方法 . 红外与激光工程, 2023, 52(1): 20220344-1-20220344-10. doi: 10.3788/IRLA20220344
[2]	陈世琼. 基于非线性抗噪声估计的视觉显著性弱小目标检测 . 红外与激光工程, 2022, 51(9): 20210939-1-20210939-6. doi: 10.3788/IRLA20210939
[3]	李博, 张心宇. 复杂场景下基于自适应特征融合的目标跟踪算法 . 红外与激光工程, 2022, 51(10): 20220013-1-20220013-11. doi: 10.3788/IRLA20220013
[4]	蒋国清, 万烂军. 基于最恰对比度显著性分析的红外弱小目标检测方法 . 红外与激光工程, 2021, 50(4): 20200377-1-20200377-8. doi: 10.3788/IRLA20200377
[5]	南天章, 耿建君, 陈旭, 陈颖. 基于邻域特征的红外低慢小目标检测 . 红外与激光工程, 2019, 48(S1): 174-180. doi: 10.3788/IRLA201948.S128002
[6]	房胜男, 谷小婧, 顾幸生. 基于自适应响应融合的相关滤波红外目标跟踪 . 红外与激光工程, 2019, 48(6): 626003-0626003(8). doi: 10.3788/IRLA201948.0626003
[7]	齐楠楠, 姜鹏飞, 李彦胜, 谭毅华. 基于视觉显著性和目标置信度的红外车辆检测技术 . 红外与激光工程, 2017, 46(6): 604005-0604005(9). doi: 10.3788/IRLA201746.0604005
[8]	楚天鹏. 多光电跟踪设备异步序贯分布式目标跟踪算法 . 红外与激光工程, 2017, 46(9): 926002-0926002(7). doi: 10.3788/IRLA201746.0926002
[9]	万一龙, 柏连发, 韩静, 张毅. 低照度双目立体显著目标距离测定方法与实现 . 红外与激光工程, 2015, 44(3): 1053-1060.
[10]	张士成, 杨立, 石恒. 基于射线跟踪算法的舰船尾迹波红外特征与探测 . 红外与激光工程, 2015, 44(5): 1450-1455.
[11]	张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法 . 红外与激光工程, 2015, 44(S1): 29-34.
[12]	孙照蕾, 惠斌, 秦莫凡, 常铮, 罗海波, 夏仁波. 红外图像显著目标检测算法 . 红外与激光工程, 2015, 44(9): 2633-2637.
[13]	吕相银, 金伟, 杨莉. 地面目标红外立体特征 . 红外与激光工程, 2014, 43(9): 2810-2814.
[14]	彭志勇, 王向军, 卢进. 窗口热辐射下基于视觉显著性的红外目标检测方法 . 红外与激光工程, 2014, 43(6): 1772-1776.
[15]	任利锋, 张靖周, 单勇, 刘喜岳. 旋翼气动加热对直升机红外特征分布的影响 . 红外与激光工程, 2014, 43(1): 53-60.
[16]	吕俊伟, 郭宁, 潘爽. 时滞和相关性观测条件下的红外目标状态估计方法 . 红外与激光工程, 2014, 43(10): 3238-3243.
[17]	苏娟, 杨小冈, 卢俊. 鲁棒的前视红外目标多核跟踪算法 . 红外与激光工程, 2013, 42(2): 543-548.
[18]	刘莹奇. 空间目标红外多波段温度分布反演 . 红外与激光工程, 2013, 42(3): 556-561.
[19]	耿利祥, 陈钱, 钱惟贤. 改进的联合概率数据关联算法（JPDA）对红外目标与诱饵的辨别 . 红外与激光工程, 2013, 42(2): 305-310.
[20]	王江涛, 陈得宝, 李素文, 杨一军, 杨静宇. 在线自适应选择子空间的红外目标跟踪方法 . 红外与激光工程, 2013, 42(9): 2579-2583.

点击查看大图

计量

文章访问数: 646
HTML全文浏览量: 130
PDF下载量: 171
被引次数: 0

引入显著特征空间的抗遮挡红外目标跟踪

doi: 10.3788/IRLA201746.0304002

1. 上海航天控制技术研究所,上海 201109

作者简介:
马天义(1976-),男,高级工程师,主要从事光电探测制导技术方面的研究。Email:458508175@qq.com

收稿日期: 2016-07-10
修回日期: 2016-08-20
刊出日期: 2017-03-25

基金项目:

上海航天科技创新基金（SAST2016073）

中图分类号: TP391

关键词:

摘要: 针对红外目标跟踪过程中目标纹理信息缺乏，与背景灰度呈现强耦合性，特别是在遮挡情况下目标特征信息链断裂，特征信息无法延续的实际跟踪问题，提出了基于显著特征空间的抗遮挡跟踪算法。首先通过分析红外目标特性，利用多尺度显著性、对比度和信息熵等信息生成显著特征向量空间，结合超像素特征距离和空间距离对区域进行聚类融合，突出目标区域，生成显著图。然后融合显著区域和原图，生成多个目标候选区作为跟踪算法输入。最后通过目标的空间分布场矩阵对全局的候选区域进行匹配，同时建立遮挡检测机制，基于显著区连通区变化和特征相似度变化曲线对遮挡的起始进行判断，结合遮挡判定设置模型更新策略。在不同红外测试集上的实验结果表明：所提算法在遮挡情况下也能达到较好的跟踪效果，有效增强了跟踪算法的鲁棒性。

English Abstract

Anti-occluded infrared target tracking with salient feature space

1. Shanghai Institute of Spaceflight Control Technology,Shanghai 201109,China

Received Date: 2016-07-10
Rev Recd Date: 2016-08-20
Publish Date: 2017-03-25

Keywords:

Abstract: Aiming at the lack of target texture information in infrared target tracking, strong coupling between the target and the background, and the case of occlusion causing that the characteristic information cannot be extended, the anti-occlusion algorithm for infrared target tracking with salient feature space was proposed. Firstly, by analyzing the characteristics of the infrared target, the salient feature space was generated by using multi-scale saliency, contrast and information entropy, and the regions were clustered with the super-pixel feature distance and spatial distance to highlight the infrared target area. By quantifying the different regions of the infrared image, the saliency map was generated. Based on the saliency map and the original image, a plurality of target candidate regions was generated as the tracking algorithms input. Finally, the spatial distribution field matrices of the infrared target were matched by way of the global candidate regions. At the same time, the occlusion detection mechanism on account of the change of the salience regions and the inter-frame variation curve of feature similarity was established. Experimental results on different IR test sets show that the proposed infrared target algorithm can achieve better tracking performance under the occlusion condition, which effectively enhances the robustness of the tracking algorithm.