The Application of Neural Network Approach to Radar Systems 蘇進東、鍾翼能
E-mail: 9507639@mail.dyu.edu.tw
ABSTRACT
Multiple target tracking algorithm plays an important role in radar systems. It will obtain the relations between radar measurements and existing tracks after applying the tracking algorithm. A new approach to multiple target tracking algorithm based on the Neural Network approach is investigated. Moreover, it applys an adaptive tracking procedure in order to solve both the data association and the target tracking problems simultaneously. With this approach, the matching between radar measurements and existing target tracks can achieve a global consideration. Computer simulation results indicate that this approach successfully solves the problem of tracking multiple maneuvering targets.
Keywords : Multiple target tracking algorithm ; Data association ; Competitive Hopfield Neural Network Table of Contents
目錄 封面內頁 簽名頁 授權書.........................iii 中文摘要..........
..............iv 英文摘要........................v 誌謝.......
................... vi 目錄..........................vii 圖目錄
.........................ix 表目錄........................
.xi 第一章 緒論 1.1研究動機...................1 1.2研究背景及目的............
..1 1.3論文章節.................2 第二章 雷達系統介紹 2.1前言..............
.......3 2.2雷達基本架構.................3 2.3雷達基本方塊圖............
....5 ………2.3.1雷達天線.................7 2.4現代雷達技術..............
...9 2.5雷達原理與演進 ...............11 2.6拋物面雷達於平面陣列雷達之比較 .......13 第三章 卡門濾波器 3.1目標動態系統 ................16 3.2卡門濾波器數學架構 .........
....17 3.3擴展式卡門濾波器 ..............19 第四章 類神經網路追蹤程序 4.1數學模型 .....
.............21 4.2類神經網路模型 ...............21 4.3適應程序 ........
..........26 第五章 電腦模擬分析與討論 5.1單目標追蹤模擬分析 .............31 5.2雙目標 追蹤模擬分析 .............40 第六章 結論......................50 參考文獻
........................51 圖目錄 圖2.1 雷達系統方塊圖 ...............
...4 圖2.2 資料處理方塊圖 ..................5 圖2.3雷達基本方塊圖 ...........
.......6 圖4.1目標物及量測值之關係圖..............22 圖4.2 標題8×3之目標與量測值之關係 圖..........26 圖5.1 方法一之定速度單目標追蹤軌跡...........33 圖5.2 方法二之定速度單目 標追蹤軌跡...........33 圖5.3 方法三之定速度單目標追蹤軌跡...........34 圖5.4 方法一之 定速度單目標追蹤的誤差..........34 圖5.5 方法二之定速度單目標追蹤的誤差..........35 圖5.6 方法三之定速度單目標追蹤的誤差..........35 圖5.7 方法一之變速度單目標追蹤軌跡..........
.37 圖5.8 方法二之變速度單目標追蹤軌跡...........37 圖5.9 方法三之變速度單目標追蹤軌跡.....
......38 圖5.10 方法一之變速度單目標追蹤的誤差.........38 圖5.11 方法二之變速度單目標追蹤的誤 差.........39 圖5.12 方法三之變速度單目標追蹤的誤差.........39 圖5.13 方法一之定速度雙目標 追蹤軌跡..........42 圖5.14 方法二之定速度雙目標追蹤軌跡..........42 圖5.15 方法三之定速 度雙目標追蹤軌跡..........43 圖5.16 方法一之定速度雙目標追蹤的誤差.........43 圖5.17 方法 二之定速度雙目標追蹤的誤差.........44 圖5.18 方法三之定速度雙目標追蹤的誤差.........44 圖5.19 方法一之變速度雙目標交叉運動追蹤軌跡......47 圖5.20 方法二之變速度雙目標交叉運動追蹤軌跡....
..47 圖5.21 方法三之變速度雙目標交叉運動追蹤軌跡......48 圖5.22 方法一之變速度雙目標追蹤的誤差...
......48 圖5.23 方法二之變速度雙目標追蹤的誤差.........49 圖5.24 方法三之變速度雙目標追蹤的誤 差.........49 表目錄 表5.1 標題單目標之初始狀態 ..............31 表5.2 標題單目標追蹤的 模擬結果 ............32 表5.3 標題單目標之變速度區間設定 ...........36 表5.4 標題單目標 追蹤的模擬結果.............36 表5.5 標題雙目標之初始狀態...............40 表5.6 標題雙目標追蹤的模擬結果.............41 表5.7 標題雙目標之初始狀態..............
.45 表5.8 標題雙目標之變速度區間設定............45 表5.9 標題雙目標追蹤的模擬結果.......
......46 REFERENCES
參考文獻 1. P.C. Chung, C.T. Tsai, E.L. Chen and Y.N. Sun, "Polygonal Approximation Using A Competitive Hopfield Neural Network,"
Pattern Recognition, Vol. 27, No. 11, pp.1505-1512, 1994. 2. Chein-Chen Lee, Pau-Choo Chung, H.M Tsai, "Identifying Multiple Abdominal Organs from CT Image Series Using a Multimodule Contextual Neural Network and Spatial Fuzzy Rules," IEEE Trans. on Information Technology in BioMedicine, Vol. 7, No.8, pp.208-217, Sept.2003. 3. Chuan-Yu Chang and Pau-Choo Chung, "Medical Image Segmentation Using a Contextual-Constraint Based Hopfield Neural Cube," Image and Vision Computing, Vol. 19, pp.669-678, 2001. 4. Y. Bar-Shalom, and T.E. Formann, “Tracking and Data Association,” Artech House,1988. 5. K.C. Chang, C.Y. Chong, andY. Bar-Shalom,“Joint Probabilistic Dataand Association Distributed Sensor Networks” IEEE Trans. Automa. Contr., Vol. AC-31, P.p.889- 897, 1986. 6. Y. Bar-Shalom and T.
Edsion, “Sonar Tracking of Multiple Targets Using Joint Probabilistic Data Association,” IEEE Journal of Oceaning Engineering, Vol. OE-8, No.3, 1983. 7. Y. Bar-Shalom and T.E. Fortmann," Tracking and Data Association," Academic Press ,Inc., 1989. 8. Y.N. Chung and D.L.
Gustafson , and E. Emre, “Extended Solution to Multiple Maneuvering Target Tracking,” IEEE Trans. Aerosp Electron. Syst.Vol AES-25, P.p.876-887, 1990. 9. E. Emre, and J. Seo," A Unifying Approach to Multi-Target Tracking," IEEE Trans. Aerosp. Electron. Syst., Vol. AES-25, pp.520-528, 1989. 10. Y.N. Chung and Joy Chen, “Applying Both Kinematic and Attribute Information for A Target Tracking Algorithm,” J. of Control Syst. And Technology, Vol.5, No.3, P.p.203-209, 1997. 11. P.Swerling ," Radar Probability of Detection for Some Additional Fluctuating Target Cases ,"IEEE Trans. Aerosp. Electron. Syst. Vol AES-33,pp.698-709,1997. 12. P. D. Hanlon and P. S. Maybeck,”Interrelation Ship of Single-Filter and Multiple-Model Adaptive Algorithms ”,IEEE Trans. Aerosp. Electron. Syst. Vol. AES-34,PP.934-946,1998. 13. E. Conte, M.
Lops, and G. Ricci, "Adaptive Detection Schemes in Compound-Gaussian Clutter," IEEE Trans. Aerosp. Electron. Syst., Vol. AES-34 , pp.1058-1069, 1998. 14. R.L.Popp,K.R.Pattipati,Y.Bar-Shalom&M.Ysddanapudi ,"Parallelization of a Multiple Tracking Algorithm with Superlinear Speedups,"IEEE Trans. Aerosp. Electron. Syst. Vol AES-33 , pp.281-290,1997.3 15. D.J. Kershaw and R.J. Evans, "Waveform Selective Probabilistic Data Association," IEEE Trans. Aerosp. Electron. Syst., Vol. AES-33, pp.1180-1189,1997. 16. P. D. Hanlon & P. S.
Maybeck, ”Interrelationship of Single-Filter and Multiple-Model Adaptive Algorithms ”,IEEE Trans. Aerosp. Electron. Syst. Vol
AES-34,pp.934-947,1998. 17. S-T.Park&J.G.Lee,”Design of a Practical Tracking Algorithm with Radar Measurements,” IEEE Trans. Aerosp.
Electron. Syst. Vol AES-34,pp.1337-1345,1998. 18. E.Mazor,J Dayan,A.Averbuch &Y.Bar-Shalom,”Interacting Multiple Model Methods in Target Tracking: A Survey,” IEEE Trans.Aerosp.Electron. Syst. Vol AES-34,pp.103-124,1998. 19. H.Lee and I-J Tahk, “Generalized Input-Estimation Technique for Tracking Maneuvering Targets,” IEEE Trans. Aerosp. 20. Electron. Syst. Vol AES-35, P.p.1388-1403, 1999.K.A. Fisher and P.S. Maybeck, "Multiple Adaptive Estimation with Filter Spawning," IEEE Trans. Aerosp. Electron. Syst., Vol.38, No. 3, pp.755-768, 2002. 21. N. Okello and B. Ristic, "Maximum Likelihood Registration for Multiple Dissimilar Sensors," IEEE Trans. Aerosp.
Electron. Syst., Vol. 39, No.3, pp.1074-1083, 2003. 22. M. Efe and D.P. Atherton, “Maneuvering Targets Tracking Using Adaptive Turn Rate Models in The Interacting Multiple Model,” 35th IEEE Conf. on Decision and Control, P.p.3151- 3156, 1996. 23. K. Mehrotra and P.R.
Mahapatra, “A Jerk Model for Tracking Highly Maneuvering Targets,” IEEE Trans. Aerosp. Electron. Syst. Vol. AES-33, P.p.1094-1106, 1997.