Abstract
This paper addresses the problem of joint tracking and classification (JTC) of a single extended target with a complex shape. To describe this complex shape, the spatial extent state is first modeled by star-convex shape via a random hypersurface model (RHM), and then used as feature information for target classification. The target state is modeled by two vectors to alleviate the influence of the high-dimensional state space and the severely nonlinear observation model on target state estimation, while the Euclidean distance metric of the normalized Fourier descriptors is applied to obtain the analytical solution of the updated class probability. Consequently, the resulting method is called the “JTC-RHM method.” Besides, the proposed JTC-RHM is integrated into a Bernoulli filter framework to solve the JTC of a single extended target in the presence of detection uncertainty and clutter, resulting in a JTC-RHM-Ber filter. Specifically, the recursive expressions of this filter are derived. Simulations indicate that: (1) the proposed JTC-RHM method can classify the targets with complex shapes and similar sizes more correctly, compared with the JTC method based on the random matrix model; (2) the proposed method performs better in target state estimation than the star-convex RHM based extended target tracking method; (3) the proposed JTC-RHM-Ber filter has a promising performance in state detection and estimation, and can achieve target classification correctly.
摘要
本文解决具有复杂形状的单扩展目标联合跟踪与分类 (joint tracking and classification, JTC) 问题. 为描述复杂形状, 首先利用随机超曲面模型 (random hypersurface model, RHM) 将空间扩展状态建模为星凸形状, 并将其作为目标分类的特征信息. 利用两个向量对目标状态建模, 以减轻高维状态空间和严重非线性观测模型对目标状态估计的影响, 并利用归一化傅立叶描述子的欧氏距离度量获得类别概率更新的解析解. 因此, 该方法被称为“JTC-RHM方法”. 此外, 为解决检测不确定和杂波情况下的单扩展目标JTC问题, 将所提JTC-RHM方法整合到Bernoulli滤波框架中, 提出JTC-RHM-Ber滤波算法. 特别地, 推导了该滤波算法的递推表达式. 仿真结果表明: (1) 与基于随机矩阵模型的JTC算法相比, 所提JTC-RHM方法能更准确地对不同形状、 相似大小的目标进行分类; (2) 与基于星凸RHM的扩展目标跟踪算法相比, 所提算法对目标状态性能估计更优; (3) 所提JTC-RHM-Ber滤波算法在状态检测和估计方面具有良好性能, 能够正确地实现目标分类.
Similar content being viewed by others
References
Angelova D, Mihaylova L, 2006. Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information. Dig Signal Process, 16(2):180–204. https://doi.org/10.1016/j.dsp.2005.04.007
Angelova D, Mihaylova L, Petrov N, et al., 2013. A convolution particle filtering approach for tracking elliptical extended objects. Proc 16th Int Conf on Information Fusion, p.1542–1549.
Baum M, Hanebeck UD, 2014. Extended object tracking with random hypersurface models. IEEE Trans Aerosp Electron Syst, 50(1):149–159. https://doi.org/10.1109/taes.2013.120107
Baum M, Klumpp V, Hanebeck UD, 2010. A novel Bayesian method for fitting a circle to noisy points. Proc 13th Int Conf on Information Fusion, p.1–6. https://doi.org/10.1109/ICIF.2010.5711884
Baum M, Faion F, Hanebeck UD, 2012. Modeling the target extent with multiplicative noise. Proc 15th Int Conf on Information Fusion, p.2406–2412.
Beard M, Reuter S, Granström K, et al., 2016. Multiple extended target tracking with labeled random finite sets. IEEE Trans Signal Process, 64(7):1638–1653. https://doi.org/10.1109/tsp.2015.2505683
Cao W, Lan J, Li XR, 2016. Conditional joint decision and estimation with application to joint tracking and classification. IEEE Trans Syst Man Cybern Syst, 46(4):459–471. https://doi.org/10.1109/tsmc.2015.2442219
Cao W, Lan J, Li XR, 2018. Extended object tracking and classification using radar and ESM sensor data. IEEE Signal Process Lett, 25(1): 90–94. https://doi.org/10.1109/lsp.2017.2757920
de Freitas A, Mihaylova L, Gning A, et al., 2019. A box particle filter method for tracking multiple extended objects. IEEE Trans Aerosp Electron Syst, 55(4):1640–1655. https://doi.org/10.1109/taes.2018.2874147
Eryildirim A, Guldogan MB, 2016. A Bernoulli filter for extended target tracking using random matrices in a UWB sensor network. IEEE Sens J, 16(11):4362–4373. https://doi.org/10.1109/jsen.2016.2544807
Feldmann M, Fränken D, Koch W, 2011. Tracking of extended objects and group targets using random matrices. IEEE Trans Signal Process, 59(4): 1409–1420. https://doi.org/10.1109/tsp.2010.2101064
Gilholm K, Salmond D, 2005. Spatial distribution model for tracking extended objects. IEE Proc Radar Sonar Navig, 152(5):364–371. https://doi.org/10.1049/ip-rsn:20045114
Granström K, Lundquist C, Orguner O, 2012. Extended target tracking using a Gaussian-mixture PHD filter. IEEE Trans Aerosp Electron Syst, 48(4):3268–3286. https://doi.org/10.1109/taes.2012.6324703
Granström K, Reuter S, Meissner D, et al., 2014. A multiple model PHD approach to tracking of cars under an assumed rectangular shape. Proc 17th Int Conf on Information Fusion, p.1–8.
Granström K, Willett P, Bar-Shalom Y, 2015. An extended target tracking model with multiple random matrices and unified kinematics. Proc 18th Int Conf on Information Fusion, p.1007–1014.
Granström K, Baum M, Reuter S, 2017. Extended object tracking: introduction, overview, and applications. J Adv Inform Fus, 12(2):139–174.
Hirscher T, Scheel A, Reuter S, et al., 2016. Multiple extended object tracking using Gaussian processes. Proc 19th Int Conf on Information Fusion, p.1–8.
Hu Q, Ji HB, Zhang YQ, 2018. A standard PHD filter for joint tracking and classification of maneuvering extended targets using random matrix. Signal Process, 144:352–363. https://doi.org/10.1016/j.sigpro.2017.10.026
Jiang H, Zhan K, Xu L, 2015. Joint tracking and classification with constraints and reassignment by radar and ESM. Dig Signal Process, 40:213–223. https://doi.org/10.1016/j.dsp.2015.01.004
Knill C, Scheel A, Dietmayer K, 2016. A direct scattering model for tracking vehicles with high-resolution radars. Proc IEEE Intelligent Vehicles Symp, p.298–303. https://doi.org/10.1109/IVS.2016.7535401
Koch JW, 2008. Bayesian approach to extended object and cluster tracking using random matrices. IEEE Trans Aerosp Electron Syst, 44(3):1042–1059. https://doi.org/10.1109/taes.2008.4655362
Lan J, Li XR, 2013. Joint tracking and classification of extended object using random matrix. Proc 16th Int Conf on Information Fusion, p.1550–1557.
Lan J, Li XR, 2014. Tracking of maneuvering non-ellipsoidal extended object or target group using random matrix. IEEE Trans Signal Process, 62(9):2450–2463. https://doi.org/10.1109/tsp.2014.2309561
Lan J, Li XR, 2016. Tracking of extended object or target group using random matrix: new model and approach. IEEE Trans Aerosp Electron Syst, 52(6):2973–2989. https://doi.org/10.1109/taes.2016.130346
Magnant C, Kemkemian S, Zimmer L, 2018. Joint tracking fand classification for extended targets in maritime surveillance. Proc IEEE Radar Conf, p.1117–1122. https://doi.org/10.1109/RADAR.2018.8378718
Mahler RPS, 2007. Statistical Multisource-Multitarget Information Fusion. Artech House, Boston, USA.
Mahler RPS, 2014. Advances in Statistical Multisource-Multitarget Information Fusion. Artech House, Boston, USA.
Mihaylova L, Carmi AY, Septier F, et al., 2014. Overview of Bayesian sequential Monte Carlo methods for group and extended object tracking. Dig Signal Process, 25:1–16. https://doi.org/10.1016/j.dsp.2013.11.006
Ristic B, Gordon N, Bessell A, 2004. On target classification using kinematic data. Inform Fus, 5(1):15–21. https://doi.org/10.1016/j.inffus.2003.08.002
Ristic B, Vo BT, Vo BN, et al., 2013. A tutorial on Bernoulli filters: theory, implementation and applications. IEEE Trans Signal Process, 61(13):3406–3430. https://doi.org/10.1109/tsp.2013.2257765
Schuhmacher D, Vo BT, Vo BN, 2008. A consistent metric for performance evaluation of multi-object filters. IEEE Trans Signal Process, 56(8):3447–3457. https://doi.org/10.1109/tsp.2008.920469
Sun LF, Lan J, Li XR, 2018. Joint tracking and classification of extended object based on support functions. IET Radar Sonar Navig, 12(7):685–693. https://doi.org/10.1049/iet-rsn.2017.0499
Wahlström N, Özkan E, 2015. Extended target tracking using Gaussian processes. IEEE Trans Signal Process, 63(16): 4165–4178. https://doi.org/10.1109/tsp.2015.2424194
Yang SS, Baum M, 2016. Second-order extended Kalman filter for extended object and group tracking. Proc 19th Int Conf on Information Fusion, p.1–7.
Yang SS, Baum M, 2017. Extended Kalman filter for extended object tracking. Proc IEEE Int Conf on Acoustics, Speech and Signal Processing, p.4386–4390. https://doi.org/10.1109/ICASSP.2017.7952985
Zhao YJ, Belkasim S, 2012. Multiresolution Fourier descriptors for multiresolution shape analysis. IEEE Signal Process Lett, 19(10):692–695. https://doi.org/10.1109/lsp.2012.2210040
Author information
Authors and Affiliations
Contributions
Liping WANG designed the research and drafted the manucript. Ronghui ZHAN helped organize the manuscript. Yuan HUANG, Jun ZHANG, and Zhaowen ZHUANG revised and finalized the paper.
Corresponding author
Ethics declarations
Liping WANG, Ronghui ZHAN, Yuan HUANG, Jun ZHANG, and Zhaowen ZHUANG declare that they have no conflict of interest.
Additional information
Project supported by the National Natural Science Foundation of China (No. 61471370)
Rights and permissions
About this article
Cite this article
Wang, L., Zhan, R., Huang, Y. et al. Joint tracking and classification of extended targets with complex shapes. Front Inform Technol Electron Eng 22, 839–861 (2021). https://doi.org/10.1631/FITEE.2000061
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2000061
Key words
- Extended target
- Fourier descriptors
- Joint tracking and classification
- Random hypersurface model
- Bernoulli filter