计算机科学 ›› 2022, Vol. 49 ›› Issue (8): 150-156.doi: 10.11896/jsjkx.210700135

• 计算机图形学& 多媒体 • 上一篇    下一篇

基于局部梯度强度图的动态规划检测前跟踪算法

陈莹, 郝应光, 王洪玉, 王坤   

  1. 大连理工大学信息与通信工程学院 辽宁 大连 116024
  • 收稿日期:2021-07-13 修回日期:2021-12-30 发布日期:2022-08-02
  • 通讯作者: 郝应光(yghao@dlut.edu.cn)
  • 作者简介:(chendaxian@mail.dlut.edu.com)
  • 基金资助:
    中央高校基本科研业务费专项基金(DUT21GF204)

Dynamic Programming Track-Before-Detect Algorithm Based on Local Gradient and Intensity Map

CHEN Ying, HAO Ying-guang, WANG Hong-yu, WANG Kun   

  1. College of Information and Communication,Dalian University of Technology,Dalian,Liaoning 116024,China
  • Received:2021-07-13 Revised:2021-12-30 Published:2022-08-02
  • About author:CHEN Ying,born in 1996,postgra-duate.Her main research interests include track-before-detect algorithm for weak targets in infrared images and so on.
    HAO Ying-guang,born in 1968,asso-ciate professor.His main research in-terests include modeling complex time-varying systems and image processing algorithm.
  • Supported by:
    Fundamental Research Funds for the Central Universities of Ministry of Education of China(DUT21GF204).

摘要: 针对传统动态规划检测前跟踪(DP-TBD)算法在背景复杂度高且信噪比低的红外弱小目标图像中检测概率低的问题,提出了一种基于局部梯度强度图的动态规划检测前跟踪(LIG-DP-TBD)算法。该算法首先采用局部梯度强度算法(LIG)对帧序列图像进行预处理,从而得到一个新的量测模型;再根据相邻帧值函数的相关性,构造一种全新的值函数;利用动态规划检测前跟踪算法(DP-TBD)对新的值函数进行多帧积累,从而实现对弱小目标的检测前跟踪。蒙特卡洛仿真实验结果表明,在信噪比低于4dB的情况下,该算法的检测概率较传统DP-TBD算法和DBT算法相比提高了约10%。同时,在背景复杂的真实红外弱小目标序列图像中,该算法可以在恒定虚警率条件下有效地进行弱小目标的检测前跟踪,提高了目标的检测概率。

关键词: 动态规划, 红外弱小目标, 检测前跟踪, 局部梯度强度, 帧间相关性

Abstract: Aiming at the low detection probability of traditional DP-TBD algorithm in the infrared weak and small targets images with high background complexity and low SNR,a dynamic programming track-before-detect algorithm based on local gradient and intensity map is proposed.Firstly,the algorithm uses the local gradient and intensity algorithm (LIG) to preprocess the frame sequence images to obtain a new measurement model.Then,a new value function is constructed according to the correlation of the value function of adjacent frames.Finally,the DP-TBD is used to accumulate the new value function in multiple frames,so as to realize the track-before-detect of small and weak targets.Monte Carlo simulation experiment results show that when the signal-to-noise ratio is lower than 4dB,the detection probability of this algorithm is about 10% higher than that of the traditional DP-TBD algorithm and DBT algorithm.At the same time,in the real infrared weak and small target sequence image with complex background,the algorithm can also effectively track the target before detection under the condition of a constant false alarm rate,which improves the detection probability of the target.

Key words: Dynamic programming, Infrared weak and small target, Inter-frame correlation, Local gradient and intensity, Track-before-detect

中图分类号: 

  • TP751
[1]BAI X Z,ZHOU F G,XIE Y C,et al.New Top-Hat Transformation and Application on Infrared Small Target Detection [J].Journal of Data Acquisition & Processing,2009,24(5):643-649.
[2]SUN Y Q,TIAN J W,LIU J.Background Suppression Based-onWavelet Transformation to Detect Infrared Target [C]//2005 International Conference on Machine Learning and Cybernetics Guangzhou.2005:4611-4615.
[3]XIONG W,XU Y L,YAO L B,et al.A new ship target detection algorithm based on visual salience calculation of spectral residuals in high-resolution SAR images[J].Electronics Optics and Control,2018,25(4):7-11,49.
[4]CHEN X P,WANG Z C,TIAN J W.Fusion Detection of Small Infrared Target Based on Local Entropy and Local Gradient Strength[J].Computer and Digital Engineering,2006,34(10):1-3,19.
[5]YI W,KONG L,YANG J,et al.Student highlight:Dynamic programming-based on track-before-detect approach to multitarget tracking[J].IEEE Aerospace and Electronic Systems Magazine,2012,27(12):31-33.
[6]RUTTEN M G,GORDON N J.Recursive track-before-detectwith target amplitude fluctuations[J].Radar,Sonar and Navigation,IEEE Proceedings,2005,152(5):345-352.
[7]BOER S,DRIESSEN J N.Multitarget particle filter track before detect application[J].Radar Sonar & Navigation IEE Procee-dings,2004,151(6):351-357.
[8]BARNIV Y,KELLA O.Dynamic Programming Solution for Detecting Dim Moving Targets Part II:Analysis[J].IEEE Tran-sactions on Aerospace & Electronic Systems,1985,21(1):144-156.
[9]JOHNSTON L A,KRISHNAMUTHY V.Performance of a dynamic programming track before detect algorithm[J].IEEETransactions on Aerospace & Electronic Systems,2002,38(1):228-242.
[10]WANG J,YI W,KIRUBARAJAN T,et al.An Efficient Recursive Multi-frame Track-before-Detect Algorithm[J].IEEETransactions on Aerospace & Electronic Systems,2018,54(1):190-204.
[11]ROTH M W.Neural networks for extraction of weak targets in high clutter environments[J].IEEE Transactions on Systems,Man,and Cybernetics,1989,19(5):1210-1217.
[12]REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:to-wards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[13]LI J H,ZHANG P,WANG X W,et al.Overviews of the small and dim target detection algorithms in infrared images[J].Journal of Image and Graphics,2020,25(9):1739-1753.
[14]WANG X L,LI X.Target Tracking Algorithm Based on Correlated Filters and Convolutional Neural Network[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2020,37(1):19-24.
[15]ZHANG H,ZHANG L,YUAN D,et al.Infrared small target detection based on local intensity and gradient properties[J].Infrared Physics & Technology,2018,89:88-96.
[16]GAO C Q,MENG D Y,YANG Y,et al.Infrared Patch-ImageModel for Small Target Detection in a Single Image[J].IEEE Transactions on Image Processing,2013,22(12):4996-5009.
[17]CHEN C P,LI H,WEI Y T,et al.A local Contrast Method for Small Infrared Target Detection[J].IEEE Transaction on Geoscience and Remote Sensing,2014,52(1):574-581.
[18]ACITO N,CORSINI G,DIANI M,et al.Experimental perfor-mance analysis of clutter removal techniques in IR images[C]//IEEE International Conference on Image Processing.2005:3(III):561-564.
[1] 李双刚, 张爽, 王兴伟.
基于自适应虚拟机迁移的云资源调度机制
Cloud Resource Scheduling Mechanism Based on Adaptive Virtual Machine Migration
计算机科学, 2020, 47(9): 238-245. https://doi.org/10.11896/jsjkx.190900189
[2] 简琤峰, 平靖, 张美玉.
面向边缘计算的Storm边缘节点调度优化方法
Edge Computing-oriented Storm Edge Node Scheduling Optimization Method
计算机科学, 2020, 47(5): 277-283. https://doi.org/10.11896/jsjkx.190600048
[3] 王正理,谢添,何琨,金燕.
考虑时间因素的0-1背包调度问题
0-1 Knapsack Variant with Time Scheduling
计算机科学, 2018, 45(4): 53-59. https://doi.org/10.11896/j.issn.1002-137X.2018.04.007
[4] 张勋,顾春华,罗飞,常耀辉,文赓.
基于动态规划的虚拟机放置策略
Virtual Machine Placement Strategy Based on Dynamic Programming
计算机科学, 2017, 44(8): 54-59. https://doi.org/10.11896/j.issn.1002-137X.2017.08.010
[5] 刘学军,陈玉凤,李斌.
基于不可信环境的移动位置隐私保护
Mobile Location Privacy Protection Based on Untrusted Environment
计算机科学, 2015, 42(2): 108-113. https://doi.org/10.11896/j.issn.1002-137X.2015.02.023
[6] 孙焘,夏 斐,刘洪波.
基于动态规划求解时间序列DTW中心
Calculating DTW Center of Time Series Using Dynamic Planning
计算机科学, 2015, 42(12): 278-282.
[7] 周欢欢,姜瑛.
一种基于动态规划的云环境测试配置方法
Test Configuration Method Based on Dynamic Programming under Cloud Environment
计算机科学, 2014, 41(9): 215-219. https://doi.org/10.11896/j.issn.1002-137X.2014.09.040
[8] 刘坤良,张大坤,武继刚.
基于权重约束的最大密度路径改进算法
Improved Algorithm for Finding Weight-constrained Maximum-density Path
计算机科学, 2014, 41(8): 122-124. https://doi.org/10.11896/j.issn.1002-137X.2014.08.027
[9] 贺毅朝,田海燕,张新禄,王志威,高锁刚.
基于动态规划法求解动态o-1背包问题
Solving Dynamic 0-1 Knapsack Problems Based on Dynamic Programming Algorithm
计算机科学, 2012, 39(7): 237-241.
[10] 刘铭,徐杨,陈峥,梁瀚,孙婷婷.
基于Multi-Agent系统的多飞行器协同路径规划方法的研究
Decentralized Multi-Agent Based Cooperative Path Planning for Multi-UAVs
计算机科学, 2012, 39(1): 219-222.
[11] 杨卫波,王万良,介靖,赵燕伟.
优化皮革裁剪加工空行程路径的混合算法
Hybrid Algorithm for Tool-path Airtime Optimization during Multi-contour Processing in Leather Cutting
计算机科学, 2011, 38(3): 254-256.
[12] 束鑫,唐楠,邱源.
基于距离比上下文的形状描述与识别方法
Shape Description and Recognition Approach Based on Distance Ratio Context
计算机科学, 2011, 38(11): 264-266.
[13] 李曙光,周彤.
限制树宽图上的有界聚类
Bounded Clustering on Bounded Tree-width Graphs
计算机科学, 2011, 38(11): 241-244.
[14] 于美娟,马希荣.
基于HMM方法的动态手势识别技术的改进
Improvement of Dynamic Hand Gesture Recognition Technology Based on HMM Method
计算机科学, 2011, 38(1): 251-252.
[15] 任永功 林楠.
DPFS:一种基于动态规划的文本特征选择算法

计算机科学, 2009, 36(6): 188-191.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!