首页 > 论文 > 光子学报 > 47卷 > 11期(pp:1110002--1)

大视场红外空中小目标梯度熵权质心跟踪方法

Gradient Entropy Weighted Centroid Method for Air Target Tracking in Infrared Wide Field

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对大视场红外凝视成像系统中非相似成像对目标形状、运动规律产生畸变影响而造成的跟踪困难, 提出了一种基于梯度熵权的目标质心定位模型, 并结合卡尔曼滤波实现了大视场中多目标跟踪.该模型利用灰度梯度来描述小目标的概率分布, 并求取目标8个方向区域内的梯度熵权, 来表示目标不同位置与质心的相关程度.提出了多方向最大梯度法来提取大视场中的天地分界线, 确定深空背景区域, 通过背景抑制提取航迹起始点.采用线性路径规划方法, 解决了目标相遇时卡尔曼滤波模型之间的互相干扰问题.实验结果表明: 所提方法在视场角为70°和180°的三种背景下, 可准确跟踪多个航模、飞机和导弹目标, 与传统跟踪方法相比, 跟踪中心定位误差低、准确率高, 平均帧速提高了约1.5倍.

Abstract

In order to overcome the tracking difficulty caused by distorted shape and motion law of the target of non-similar imaging in infrared wide-field staring system, a gradient entropy weighted centroid model is proposed. The multi-targets tracking is achieved by combing Kalman filters with this model. The model adopts gray value gradient to describe the probability distribution of dim target. The gradient entropy weights in 8 directions of target are obtained to indicate the correlation between the different regions and centroid of the target. Meanwhile, multi-direction maximum gradient method is proposed to extract the sky-ground line in wide field and obtain the position of the deep space background. Then, the starting point is detected through background suppression. The linear path planning is adopted to solve the mutual interference of Kalman filtering models when the targets meet. The experiment results show that the proposed method can track aeromodellings, airplanes and missiles in three environments in field view of 70° and 180°. Compared with the traditional tracking method, the proposed method has a lower center location error and a high accuracy, and the average frame rate is increased by about 1.5 times.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TN219

DOI:10.3788/gzxb20184711.1110002

基金项目:国家自然科学基金(No. 61801507)资助

收稿日期:2018-05-10

修改稿日期:2018-08-30

网络出版日期:--

作者单位    点击查看

张帅:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003
刘秉琦:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003
黄富瑜:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003
余皓:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003
陈一超:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003
王子昂:陆军工程大学石家庄校区 电子与光学工程系, 石家庄 050003

联系人作者:张帅(zhangshuaioec@163.com)

备注:张帅(1992-), 男, 博士研究生, 主要研究方向为红外目标检测和跟踪、视觉处理.

【1】ZHANG Shuai, LIU Bing-qi, HUANG Fu-yu,et al. Super wide field of view staring infrared imaging technology and its application[J]. Laser and Infrared, 2016, 46(10): 1176-1182.
张帅, 刘秉琦, 黄富瑜, 等. 超大视场红外凝视成像技术及其应用浅析[J]. 激光与红外, 2016, 46(10): 1176-1182.

【2】HUANG Fu-yu, WANG Yong-zhong, SHEN Xue-ju,et al. Analysis of space target detection range based on space-borne fisheye imaging system in deep space background [J]. Infrared Physics & Technology, 2012, 55(6): 475-480.

【3】CHRISTOPHER R B, MARK A M, THOMAS J B. Operational testing and applications of the AIRS FPA with infrared fisheye optics [C]. SPIE, 2003, 4820: 515-524.

【4】LUO Huan, YU Lei, LIAO Jun,et al. Tracking framework for small infrared multi-target in complex background[J]. Acta Optica Sinica, 2009, 29(6): 1536-1541.
罗寰, 于雷, 廖俊, 等. 复杂环境下红外弱小多目标跟踪系统[J]. 光学学报, 2009, 29(6): 1536-1541.

【5】WANG Gang, CHEN Yong-guang, YANG Suo-chang,et al. Robust visual saliency detection method for infrared small target[J]. Journal of Beijing University of Aeronautics and Astronautics, 2015, 41(12): 2309-2318.
王刚, 陈永光, 杨锁昌, 等. 鲁棒的红外小目标视觉显著性检测方法[J]. 北京航空航天大学学报, 2015, 41(12): 2309-2318.

【6】SU Xiu-qin, LIANG Jin-feng, LU Tao, et al. IR target detection & tracking algorithm based on sea-sky background[J]. Acta Photonica Sinica, 2009, 38(5): 1309-1312.
苏秀琴, 梁金峰, 陆陶, 等. 海天复杂背景下红外目标的检测跟踪算法[J]. 光子学报, 2009, 38(5): 1309-1312.

【7】HUANG Fu-yu, SHEN Xue-ju, LIU Xu-min,et al. Detection of super wide-field infrared target based on spatial-temporal fusion processing [J]. Optics and Precision Engineering, 2015, 23(8): 2328-2338.
黄富瑜, 沈学举, 刘旭敏, 等. 基于空时域融合处理检测超大视场红外目标[J]. 光学精密工程, 2015, 23(8): 2309-2318.

【8】BAE T. Spatial and temporal bilateral filter for infrared small target enhancement [J].Infrared Physics & Technology, 2014, 63(2): 42-53.

【9】MIN Chao-bo, ZHANG Jun-ju, CHANG Ben-kang,et al. Spatio-temporal segmentation of moving objects using edge features in infrared videos[J]. Optik, 2014, 125(7): 1809-1815.

【10】ZHANG Shuai, LIU Bing-qi, LI Yong,et al. Rapid detection method for infrared weak and small moving target of super wide-field image [J]. Infrared Technology, 2016, 38(8): 693-698.
张帅, 刘秉琦, 李勇, 等. 一种超大视场中红外弱小运动目标的快速检测方法[J]. 红外技术, 2016, 38(8): 693-698.

【11】DRUMMOND O E. Signal and data processing of small targets[C]. SPIE, 2014, 9092: 909201.

【12】FU Zhao-xia, HAN Yan. Centroid weighted Kalman filter for visual object tracking [J].Measurement, 2012, 45(4): 650-655.

【13】ZHENG Hai-chao, MAO Xia, LIANG Xiao-geng. Gray target tracking algorithm based on edge information[J].Journal of Beijing University of Aeronautics and Astronautics, 2015, 41(12): 2240-2259.
郑海超, 毛峡, 梁晓庚. 基于边缘信息的灰度目标跟踪算法[J]. 北京航空航天大学学报, 2015, 41(12): 2240-2259.

【14】YAN Shi-hua, HE Yong-qiang, ZHOU Yu-long. Maneuvering target model of the infrared fisheye detecting system[J]. Acta Optica Sinica, 2012, 32(9): 0911002.
严世华, 何永强, 周玉龙. 基于红外鱼眼探测系统的运动目标模型[J]. 光学学报, 2012, 32(9): 0911002.

【15】HE Yu-jie, LI Min, ZHANG Jin-li,et al. Infrared target tracking via weighted correlation filter[J]. Infrared Physics & Technology, 2015, 73: 103-114.

【16】HENRIQUES J F, CASEIRO R, MARTINS P,et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]. ECCV, 2012: 702-715.

【17】WEI Kun, ZHAO Yong-qiang, PAN Quan,et al. IR target tracking based on mean shift and particle filter[J]. Journal of Optoelectronics·Lasers, 2008, 19(2): 213-217.
魏坤, 赵永强, 潘泉, 等. 基于均值漂移和粒子滤波的红外目标跟踪[J]. 光电子·激光, 2008, 19(2): 213-217.

引用该论文

ZHANG Shuai,LIU Bing-qi,HUANG Fu-yu,YU Hao,CHEN Yi-chao,WANG Zi-ang. Gradient Entropy Weighted Centroid Method for Air Target Tracking in Infrared Wide Field[J]. ACTA PHOTONICA SINICA, 2018, 47(11): 1110002

张帅,刘秉琦,黄富瑜,余皓,陈一超,王子昂. 大视场红外空中小目标梯度熵权质心跟踪方法[J]. 光子学报, 2018, 47(11): 1110002

被引情况

【1】刘辉,何勇,何博侠,刘志,顾士晨. 基于多特征融合与ROI预测的红外目标跟踪算法. 光子学报, 2019, 48(7): 710004--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF