Maritime automatic target recognition for ground-based scanning radars by using sequential range profiles

Classification of marine targets using radar data products has become an important area for modern research society. However, due to several reasons such as the similarity between ship structures and spatial specifications, classification of marine targets constitutes a challenging problem. In almost all of the studies, this problem has been handled by focusing on a single instance of range profiles or synthetic aperture radar data. However, this approach is seen to achieve only a particular success. This study introduces a novel classification approach that is shown to provide additional classification enhancements by exploiting the extra information extracted from sequential range profiles generated by ground-based marine surveillance radars. With this purpose, both synthetic and measuremental range profiles are taken into consideration. Synthetic profile data are generated for seven marine targets by using an electromagnetic scattering simulation tool (RASES)1. On the other hand, a total of 2387 range profile data of 171 different target tracks are collected for five different marine target class types by using an X-band marine surveillance radar. Each target tracked for a long period of time to gather sequential HRRP data subsets. HRRP data subsets are used to generate HMM based transition matrix probabilities and sequential classification results by evaluating proposed method. Probabilistic neural network (PNN) and convolutional neural network (CNN) classification algorithms applied to gather classification results. The proposed method results are compared with both single value classification and majority voting rule (MVR) method results. According to the examination results, the proposed classification approach provides remarkable enhancements in the correct classification rates when compared to the case of single profile data approach.

PDF

___

1] Jun L, WenXian Y, GuiRong G. Feature extraction for radar ship target recognition using compactly supported wavelets. In: Proceedings of National Aerospace and Electronics Conference (NAECON’94); Dayton, OH, USA; 1994. pp. 66-73.
[2] Jasinski T, Antipov I, Monteiro ST, Brooker G. W-band maritime target classification using high resolution range profiles. In: 2013 International Conference on Radar; Adelaide, Australia; 2013. pp. 356-361.
[3] Klepko R. Classification of SAR ship images with the aid of a syntactic pattern recognition algorithm. Defence Research Establishment Technical Note, No. DREO-TN-91-10. Ottawa, Canada; Department of National Defence, 1991.
[4] Pastina D, Spina C. Multi-feature based automatic recognition of ship targets in ISAR. IET Radar, Sonar and Navigation 2009; 3 (4):406-423. doi: 10.1049/iet-rsn.2008.0172
5] Nilubol C, Pham QH, Mersereau RM, Smisth MJT, Clements MA. Hidden Markov modelling for SAR automatic target recognition. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing; Seattle, WA, USA; 1998. pp.1061-1064.
[6] Laterveer R, Hughes D, Dugelay S. Markov random fields for target classification in low frequency radar. In: IEEE Oceanic Engineering Society (OCEANS’98); Nice, France; 1998. pp. 1274-1278.
[7] Runkle PR, Bharadwaj PK, Couchman L, Carin L. Hidden Markov models for multiaspect target classification. IEEE Transactions on Signal Processing 1999; 47 (7): 2035-2040. doi: 10.1109/OCEANS.1998.726273
[8] Vespe M, Baker CJ, Griﬀiths HD. Radar target classification using multiple perspectives. IET Radar, Sonar and Navigation 2007; 1 (4):300-307. doi: 10.1049/iet-rsn:20060049 [9] Theodoridis S, Koutroumbas K. Pattern Recognition. 2nd. ed. Cambridge, MA, USA: Elsevier Acedemic Press, 2003.
[10] Ji S, Liao X, Carin L. Adaptive multi-aspect target classification and detection with hidden Markov models. IEEE Sensors Journal 2005; 5 (5): 1035-1042. doi: 10.1109/JSEN.2005.847936
[11] Pei B, Bao Z. Multi-aspect radar target recognition method based on scattering centers and HMMs classifiers. IEEE Transactions on Aerospace and Electronic Systems 2005; 41 (3): 1067-1074. doi: 10.1109/TAES.2005.1541451
[12] Kahler B, Blasch E. Robust multi-look HRR ATR investigation through decision-level fusion evaluation. In: 11th International Conference on Information Fusion; Cologne, Germany; 2008. pp. 1-8.
[13] Cho H, Chun J, Lee T, Lee S, Chae D. Spatiotemporal radar target identification using radar cross-section modeling and hidden Markov models. IEEE Transactions on Aerospace and Electronic Systems 2016; 52 (3): 1284-1295. doi: 10.1109/TAES.2016.140908
[14] Huan RH, Pan Y. Target recognition for multi-aspect SAR images with fusion strategies. Progress In Electromag- netics Research 2013; 134: 267-288. doi: 10.2528/PIER12100304
[15] Rizvi SA, Nasrabadi NM. Fusion of automatic target recognition algorithms. Information Fusion 2002; 4 (4): 247- 258. doi: 10.1016/S1566-2535(03)00043-5
[16] Liu J, Fang N, Xie YJ, Wang BF. Multi-scale feature-based fuzzy-support vector machine classification using radar range profiles. IET Radar, Sonar And Navigation 2016; 10 (2): 370-378. doi: 10.1049/iet-rsn.2015.0244
[17] Jiang Y, Li Y, Cai J, Wang Y, Xu J. Robust automatic target recognition via HRRP Sequence based on scatterer matching. Sensors 2018; 18 (593). doi: 10.3390/s18020593
[18] Wang H, Li S, Zhou Y, Chen S. SAR automatic target recognition using a roto-translational invariant wavelet- scattering convolution network. Remote Sensing 2018; 10 (4): 501. doi: 10.3390/rs10040501
[19] Xie D, Zhang X, Hu Y, Radar target recognition using LVQ Network and Majority Voting. In: 2008 Congress on Image and Signal Processing; Hainan, China; 2008, pp. 184-187.
[20] Liu B, Liu J. Overview of image noise reduction based on non-local mean algorithm. In: MATEC Web of Conferences; 2018. pp. 03029.
[21] Buades A, Coll B, Morel JM. A non-local algorithm for image denoising. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition; California, USA; 2005. pp. 60-65.
[22] Goh TC. Probabilistic neural network for evaluating seismic liquefaction potential. In: IEEE International Sympo- sium On Intelligent Systems; Varna, Bulgaria; 2002, pp. 16-20.
[23] Liao X, Runkle P, Carin L. Identification of ground targets from sequential high-range-resolution radar signatures. IEEE Transactions on Aerospace and Electronic Systems 2002; 38 (4): 1230-1242. doi: 10.1109/TAES.2002.1145746