臺灣博碩士論文加值系統

本論文主要考慮在道路環境中之多雷達多目標追蹤問題。在這問題中，目標物數量會隨時間變化且嚴重的雜波存在。另外，一個目標物可能會產生多個反射波，稱為擴展目標問題。為了處理擴展目標問題，我們首先提出使用兩種聚集分類演算法，此兩方法能降低運算時間以及增加追蹤效果。利用多雷達，可以使增加整體視野的範圍且追蹤效果也會提升。我們提出兩種多雷達追蹤的方法。第一種是分散式，第二種為集中式。在分散式方法中，最後結果是結合了來自各個雷達的偵測結果。集中式方法的構想是把一個目標被不同雷達的觀測結果為一個擴展目標問題，並只用一種目標追蹤算法。在此方法中，不需要做資料融合以及各雷達間的關聯。模擬結果顯示，本論文所提出的方法相較於現有的追蹤方法有較好的效能。

In this thesis, we consider multiple-radar multiple-target tracking in on-road environment. In this problem, the number of targets is time-variant and clutters are rich. Also, one target may give multiple reflections, called the extended target problem. To solve the extended target problem. we first propose using two clustering algorithms, that can reduce computational time and enhance the tracking performance. With more radars, the overall field-of-view can be increased and the tracking performance can also be improved. Two methods are proposed. The first is a distributed and the second is a centralized method. In the distributed method, tracking results from multiple radars are fused. The idea of the centralized method is to treat the measurements of a target from multiple radars as an extended target problem, and one tracking algorithm can then be applied. In this method, no fusion and association is required. From simulation results, we see that both proposed method can provide good results.

摘要 i
Abstract ii
Acknowledgement iii
Content iv
List of table vi
List of figure vii
Chapter 1. Introduction 1
1.1 Motivation 1
1.2 Review 2
1.3 Proposed algorithms 3
1.4 Outlines 4
Chapter 2. Multiple target tracking algorithms 5
2.1 Problem statement 5
2.2 Joint probabilistic data association filter 5
2.2.1 Tracking in cluttered environment 5
2.2.2 Joint probabilistic data association 7
2.3 Probability hypothesis density filter 12
2.3.1 Random finite set in multiple target tracking 12
2.3.2 Probability hypothesis density filter 14
2.3.3 PHD filter for extended target tracking 18
2.4 Cardinalized probability hypothesis density filter 22
Chapter 3. Proposed methods 28
3.1 System model 28
3.2 Clustering algorithms 31
3.2.1 Fuzzy adaptive resonance theory 31
3.2.2 Density-based clustering algorithm 34
3.3 Multiple radar tracking: distributed method 38
3.3.1 Track-to-track association 39
3.3.2 Track fusion 40
3.4 Multiple radar tracking: centralized method 42
Chapter 4. Experiments 44
4.1 System overview 44
4.2 Scenarios 45
4.3 Results 46
4.3.1 Single vehicle 46
4.3.2 Multiple vehicles 51
4.3.3 On-road vehicles 53
Chapter 5. Simulations 55
5.1 Setting 55
5.2 Simulation results 56
5.2.1 PHD and CPHD methods 56
5.2.2 Clustering methods for PHD filter 61
5.2.3 Proposed distributed PHD method 64
5.2.4 Proposed centralized PHD method 66
Chapter 6. Conclusions 68
References 70

[1] M. B. Rhudy, R. A. Salguero and K. Holappa, “A Kalman filtering tutorial for undergraduate students,” International Journal of Computer Science & Engineering Survey (IJCSES), vol.8, pp. 1-18, 2017.
[2] Y. Bar-Shalom and T. Fortmann, Tracking and Data Association, Academic Press. 1988.
[3] T. E. Fortmann, Y. Bar-Shalom, M. Scheffe, "Sonar tracking of multiple targets using joint probabilistic data association", IEEE J. Ocean. Eng., vol. OE-8, pp. 173-184, Jul. 1983.
[4] R. Mahler, “Multi-target Bayes filtering via first-order multi-target moments,” IEEE Trans. Aerosp. Electron. Syst., vol. 39, no. 4, pp. 1152–1178, 2003.
[5] B.-N. Vo and W.-K. Ma, “The Gaussian mixture probability hypothesis density filter,” IEEE Trans. Signal Process., vol. 54, no. 11, pp. 4091–4104, Nov. 2006.
[6] B.-T. Vo, B.-N. Vo, and A. Cantoni, “Analytic implementations of the cardinalized Probability Hypothesis Density filter,” IEEE Trans. Signal Process., vol. 55, no. 7, pp. 3553–3567, Jul. 2007
[7] K. Granstrom, C. Lundquist, and U. Orguner, “A Gaussian mixture PHD filter for extended target tracking,” in Proceedings of the 13th International Conference on Information Fusion (Fusion 2010), Edinburgh, Scotland, Jul. 2010
[8] K. Granstrom, C. Lundquist, and U. Orguner, “Extended target tracking using a Gaussian mixture PHD filter,” IEEE Transactions on Aerospace and Electronic Systems, vol. 48, no. 4, pp. 3268–3286, Oct. 2012.
[9] M. Thomas, G. Maignan, and Y. Storey, "Tracking in a multiradar environment," Proc. IEEE, vol. 123, Mar. 1976.
[10] F. Folster and H. Rohling, “Data association and tracking for automotive radar networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 4, pp. 370–377, 2005.
[11] D. Oprisan and H. Rohling, “Tracking systems for automotive radar networks,” in Proc. RADAR, Edinburgh, U.K., 2002, pp. 339–343.
[12] Y. Zhang and H. Ji, “A novel fast partitioning algorithm for extended target tracking using a Gaussian mixture PHD filter,” Signal Processing, vol. 93, no. 11, pp. 2975–2985, 2013.
[13] M. Ester, H. Kriegel, J. Sander, and X. Xu, “A density-based algorithm for discovering clusters in large spatial databases with noise,” in Proc. 2nd Int. Conf. Knowledge Discovery and Data Mining (KDD’96), 1996, pp. 226–231.
[14] K. C. Chang, R. K. Saha, and Y. Bar-Shalom, “On optimal track-to-track fusion,” IEEE Trans. Aerosp. Electron. Syst., vol. 33, pp. 1271–1276, Oct. 1997.
[15] Y. Bar-Shalom, “On the track-to-track correlation problem,” IEEE Trans. Automat. Contr., vol. AC-26, no. 2, pp. 571–572, Apr. 1981.
[16] D. Schuhmacher, B.-T. Vo, and B.-N. Vo, “A consistent metric for performance evaluation of multi-object filters,” IEEE Trans. Signal Process., vol. 56, no. 8, pp. 3447–3457, Aug. 2008.
[17] F. Folster, H. Rohling, and U. Lubbert, “An automotive radar network based on 77 GHz FMCW sensors,” in IEEE Int. Radar Conf., May 2005, pp. 871–876.
[18] F. Folster and H. Rohling, “Data association and tracking for ¨ automotive radar networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 4, pp. 370–377, 2005.