Multi-target detection via sparse recovery of least absolute shrinkage and selection operator model

doi:10.11772/j.issn.1001-9081.2017.08.2184

Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (8): 2184-2188.DOI: 10.11772/j.issn.1001-9081.2017.08.2184

Previous Articles Next Articles

Multi-target detection via sparse recovery of least absolute shrinkage and selection operator model

HONG Liugen^1,2, ZHENG Lin^1,2, YANG Chao^1,2

1. Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, Guilin University of Electronic Technology, Guilin Guangxi 541004, China;
2. College of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China

Received:2017-02-24 Revised:2017-03-28 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61362006,61371107),the Natural Science Foundation of Guangxi Zhuang Autonomous Region (2014GXNSFBA118288),the Foundation of Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing (GXKL061501).

基于最小绝对收缩与选择算子模型稀疏恢复的多目标检测

洪刘根^1,2, 郑霖^1,2, 杨超^1,2

1. 桂林电子科技大学广西无线宽带通信与信号处理重点实验室, 广西桂林 541004;
2. 桂林电子科技大学信息与通信学院, 广西桂林 541004

通讯作者: 郑霖
作者简介:洪刘根(1991-),男,江苏南通人,硕士研究生,主要研究方向:多径环境下目标检测;郑霖(1973-),男,安徽祁门人,教授,博士,主要研究方向:无线传感器网络、雷达信号处理;杨超(1988-),男,陕西西安人,博士研究生,主要研究方向:移动通信、雷达通信一体化。
基金资助:
国家自然科学基金资助项目（61362006，61371107）；广西壮族自治区自然科学基金资助项目（2014GXNSFBA118288）；广西无线宽带通信与信号处理重点实验室基金资助项目（GXKL061501）。

Abstract

Abstract: Focusing on the issue that the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm may introduce some false targets in moving target detection with the presence of multipath reflections, a descending dimension method for designed matrix based on LASSO was proposed. Firstly, the multipath propagation increases the spatial diversity and provides different Doppler shifts over different paths. In addition, the application of broadband OFDM signal provides frequency diversity. The introduction of spatial diversity and frequency diversity to the system causes target space sparseness. Sparseness of multiple paths and environment knowledge were applied to estimate paths along the receiving target responses. Simulation results show that the improved LASSO algorithm based on the descending dimension method for designed matrix has better detection performance than the traditional algorithms such as Basis Pursuit (BP), Dantzig Selector (DS) and LASSO at the Signal-to-Noise Ratio (SNR) of -5 dB, and the target detection probability of the improved LASSO algorithm was 30% higher than that of LASSO at the false alarm rate of 0.1. The proposed algorithm can effectively filter the false targets and improve the radar target detection probability.

Key words: multipath effect, sparse vector recovery, multi-target detection, Least Absolute Shrinkage and Selection Operator (LASSO), Orthogonal Frequency Division Multiplexing (OFDM) signal radar

摘要： 针对地面多径环境下运动目标检测，使用最小绝对收缩与选择算子（LASSO）算法在参数估计时会出现伪目标的问题，提出一种基于LASSO模型框架的设计矩阵降维构造方法。首先，信号的多径传播能够带来目标检测的空间分集，信号在不同的多径上有不同的多普勒频移；此外，使用宽带正交频分复用（OFDM）信号能够带来频率分集。由于空间分集和频率分集的引入造成目标的稀疏特性。利用多径的稀疏性和对环境的先验知识，去估计稀疏向量。仿真结果表明，在一定信噪比（SNR，-5dB）下，基于设计矩阵降维构造方法的改进的LASSO算法比基追踪算法（BP）、DS（Dantzig Selector）、LASSO等传统算法的检测性能有明显提高；在一定虚警率（0.1）条件下，改进的LASSO算法比原LASSO算法检测概率提高了30%。所提算法能够有效去除伪目标，提高雷达目标检测概率。

关键词: 多径效应, 稀疏向量恢复, 多目标检测, 最小绝对收缩与选择算子, 正交频分复用信号雷达

CLC Number:

TN91

HONG Liugen, ZHENG Lin, YANG Chao. Multi-target detection via sparse recovery of least absolute shrinkage and selection operator model[J]. Journal of Computer Applications, 2017, 37(8): 2184-2188.

洪刘根, 郑霖, 杨超. 基于最小绝对收缩与选择算子模型稀疏恢复的多目标检测[J]. 计算机应用, 2017, 37(8): 2184-2188.

References

[1] SEN S, HURTADO M, NEHORAI A. Adaptive OFDM radar for detecting a moving target in urban scenarios[C]//Proceedings of the 2009 International Waveform Diversity and Design Conference. Piscataway, NJ:IEEE, 2009:268-272.
[2] SEN S, NEHORAI A. Adaptive OFDM radar for target detection in multipath scenarios[J]. IEEE Transactions on Signal Processing, 2011, 59(1):78-90.
[3] LE FLOCH B, HALBERT-LASSALLE R, CASTELAIN D. Digital sound broadcasting to mobile receivers[J]. IEEE Transactions on Consumer Electronics, 1989, 35(3):493-503.
[4] FRANKEN G E A, NIKOOKAR H, VAN GENDEREN P. Doppler tolerance of OFDM-coded radar signals[C]//EuRAD 2006:Proceedings of the 3rd European Radar Conference. Piscataway, NJ:IEEE, 2006:108-111.
[5] STRALKA J P. Applications of orthogonal frequency division multiplexing (OFDM) to radar[D]. Baltimore, Maryland:The Johns Hopkins University, 2008:1-40.
[6] CHEN S S, DONOHO D L, SAUNDERS M A. Atomic decomposition by basis pursuit[J]. SIAM Journal on Scientific Computing, 2006, 43(1):33-61.
[7] CANDÈS E, TAO T. Rejoinder:the Dantzig selector:statistical estimation when p is much larger than n[J]. The Annals of Statistics, 2008, 35(6):2392-2404.
[8] TIBSHIRANI R. Regression shrinkage and selection via the LASSO[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2011, 73(3):273-282.
[9] SEN S, TANG G, NEHORAI A. Multi-objective optimized OFDM radar waveform for target detection in multipath scenarios[C]//Proceedings of the 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers. Piscataway, NJ:IEEE, 2010:618-622.
[10] EFRON B, HASTIE T, JOHNSTONE I, et al. Least angle regression (with discussion)[J]. The Annals of Statistics, 2004, 32(2):407-451.
[11] HASTIE T, TAYLOR J, TIBSHIRANI R, et al. Forward stage wise regression and the monotone LASSO[J]. Electronic Journal of Statistics, 2007, 1:1-29.
[12] 张秀秀,王慧,田双双,等.高维数据回归分析中基于LASSO的自变量选择[J].中国卫生统计,2013,30(6):922-926. (ZHANG X X, WANG H, TIAN S S, et al. Selection of independent variables based on LASSO in high dimensional data regression analysis[J]. China Health Statistics, 2013, 30(6):922-926.)
[13] TANG G, NEHORAI A. Computable performance bounds on sparse recovery[J]. IEEE Transactions on Signal Processing, 2015, 63(1):132-141.
[14] 方明,戴奉周,刘宏伟,等.基于联合稀疏恢复的宽带雷达动目标检测方法[J].电子与信息学报,2015,37(12):2977-2983. (FANG M, DAI F Z, LIU H W, et al. Detection of moving targets for wideband radar based on joint-sparse recovery[J]. Journal of Electronics & Information Technology, 2015, 37(12):2977-2983.)
[15] XIA Y, SONG Z, LU Z, et al. Target detection in low grazing angle with adaptive OFDM radar[J]. International Journal of Antennas & Propagation, 2015, 2015(6):1-12.

Multi-target detection via sparse recovery of least absolute shrinkage and selection operator model

基于最小绝对收缩与选择算子模型稀疏恢复的多目标检测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 4

Recommended Articles

Metrics

[1]	CHEN Shanxiong, LIU Xiaojuan, CHEN Chunrong, ZHENG fangyuan. Method for solving Lasso problem by utilizing multi-dimensional weight [J]. Journal of Computer Applications, 2017, 37(6): 1674-1679.
[2]	GUO Yecai, ZHAO Weijuan, ZHANG Xiuzai. Design and simulation of satellite channel three-state Markov model [J]. Journal of Computer Applications, 2016, 36(1): 91-95.
[3]	GUO Yecai YUAN Tao ZHANG Tao. Simulator design and its simulation of meteorological satellite channel [J]. Journal of Computer Applications, 2013, 33(09): 2650-2652.
[4]	LI Zhean CHEN Jianping ZHANG Yajuan ZHAO Weihua. Robust feature selection method in high-dimensional data mining [J]. Journal of Computer Applications, 2013, 33(08): 2194-2197.