SPARSE TIME-FREQUENCY REPRESENTATION BASED FEATURE EXTRACTION METHOD FOR LANDMINE DISCRIMINATION

被引：7

作者：

Wang, Y. ^{[1
]}

Song, Q. ^{[1
]}

Jin, T. ^{[1
]}

Shi, Y. ^{[1
]}

Huang, X. ^{[1
]}

机构：

[1] Natl Univ Def Technol, Sch Elect Sci & Engn, Changsha 410073, Hunan, Peoples R China

来源：

PROGRESS IN ELECTROMAGNETICS RESEARCH-PIER | 2012年 / 133卷

基金：

中国国家自然科学基金;

关键词：

GROUND-PENETRATING RADAR; SYNTHETIC-APERTURE RADAR; MINE DETECTION; TARGET RECOGNITION; SAR; SYSTEM; PERFORMANCE; SIMULATION; CLUTTER; MODEL;

D O I：

10.2528/PIER12082104

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Low-frequency ultra-wideband synthetic aperture radar is a promising technology for landmine detection. According to the scattering characteristics of body-of-revolution (BOR) along with azimuth angles, a discriminator based on Bayesian decision rule is proposed, which uses sequential features, i.e., double-hump distance. First, the algorithm estimates the target scatterings in all azimuth angles based on regions of interest. Second, sequential aspect features are extracted by sparse time-frequency representation. Third, the distributions of features are obtained by training samples, and then the posterior probability of landmine class is computed as an input to the classifier adopting Mahalanobis distance. The experimental results indicate that the proposed algorithm is effective in BOR target discrimination.

引用

页码：459 / 475

页数：17

共 50 条

[1] Time-frequency audio feature extraction based on tensor representation of sparse coding
Zhang, Xue-Yuan
He, Qian-Hua
ELECTRONICS LETTERS, 2015, 51 (02) : 131 - U20
[2] Landmine Feature Extraction in UWB SAR Based on Sparse Representation
Lou, Jun
Jin, Tian
Zhou, Zhimin
PROCEEDINGS OF 2012 INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND SIGNAL PROCESSING, 2012, : 132 - 135
[3] EXTRACTION OF INTRAWAVE SIGNALS USING THE SPARSE TIME-FREQUENCY REPRESENTATION METHOD
Tavallali, Peyman
Hou, Thomas Y.
Shi, Zuoqiang
MULTISCALE MODELING & SIMULATION, 2014, 12 (04): : 1458 - 1493
[4] RETRACTED: Feature Extraction and Selection for Landmine Detection using Textures of Time-Frequency Representation (Retracted Article)
Gao, Xiang
Ji, Guangrong
Wang, Chunhe
Ji, Guangyu
PROCEEDINGS 2010 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, (ICCSIT 2010), VOL 1, 2010, : 516 - 520
[5] Sparse representation based on local time-frequency template matching for bearing transient fault feature extraction
He, Qingbo
Ding, Xiaoxi
JOURNAL OF SOUND AND VIBRATION, 2016, 370 : 424 - 443
[6] Investigation of time-frequency features for GPR landmine discrimination
Savelyev, Timofey Grigorlevich
van Kempen, Luc
Sahli, Hichem
Sachs, Juergen
Sato, Motoyuki
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (01): : 118 - 129
[7] Time-frequency manifold sparse reconstruction: A novel method for bearing fault feature extraction
Ding, Xiaoxi
He, Qingbo
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 80 : 392 - 413
[8] Optimal GPR bandwidth for time-frequency landmine discrimination
Savelyev, TG
Sato, M
DETECTION AND REMEDIATION TECHNOLOGIES FOR MINES AND MINELIKE TARGETS X, PTS 1 AND 2, 2005, 5794 : 435 - 446
[9] A SPECIFIC EMITTER IDENTIFICATION METHOD BASED ON TIME-FREQUENCY FEATURE EXTRACTION
Dong, Wenlong
Wang, Yuqi
Sun, Guangcai
Xing, Mengdao
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 6302 - 6305
[10] Time-frequency feature extraction method based on CSLBP for bearing signals
Zhang Y.
Zhang P.
Wu D.
Li B.
1600, Nanjing University of Aeronautics an Astronautics (36): : 22 - 27

← 1 2 3 4 5 →