人工神經(jīng)網(wǎng)絡(luò)在航跡關(guān)聯(lián)中的應(yīng)用研究
Application of Artificial Neural Network in Track Correlation
-
摘要: 在分布式多傳感器系統(tǒng)中的多節(jié)點情況下,航跡關(guān)聯(lián)問題可以轉(zhuǎn)化為多維分配問題。而多維分配問題是典型的組合優(yōu)化問題,很難找到問題的最優(yōu)解,而且其計算量隨著問題規(guī)模的增加易出現(xiàn)指數(shù)爆炸現(xiàn)象。該文提出了一種三維神經(jīng)網(wǎng)絡(luò)模型,用以解決三節(jié)點情況下航跡關(guān)聯(lián)的三維分配問題,并進(jìn)行了實驗仿真。仿真結(jié)果表明,三維人工神經(jīng)劂絡(luò)模型能夠有效地求解此三維分配問題,并且具有較高的航跡關(guān)聯(lián)正確率。另外三維神經(jīng)網(wǎng)絡(luò)模型同樣可以推廣到多維,用以解決航跡關(guān)聯(lián)的多維分配問題。Abstract: In a distributed multisensor system, the problem of track correlation can be transformed into the problem of multi-dimension assignment. The problem of multi-dimension assignment is a typical combined optimization problem, it is very hard to find its optimum solution and its computing burden increases heavily with the increase of dimensions and the number of targets. So a new model of three-dimension neural network is proposed in this paper to deal with the problem of three-dimension assignment. The experimental results illustrate that this model can effectively solve the problem of track correlation and have higher correct association percent. And the model of three-dimension neural network proposed in this paper can be generalized to multi-dimension model to solve the problem of multi-dimension assignment.
-
Ditzler W R. A demonstration of multisensor tracking[R]. In Proceedings of the 1987 Tri-Service Data Fusion Symposium,June 1987:303 - 311.[2]Bar-Shalom Y, Fortmann T E. Tracking and Data Association[M],New York: Academic Press, 1988.[3]Kosoka M. A track correlation algorithm for multisensor intergration[R]. Proceeding of the IEEE/AIAA 5th Digital Avionics System Conf., 1983, 10.3:1 - 8.[4]Chang C B, Youens L C. Measurement correlation for multiple sensor tracking in a dense target environment[J]. IEEE Trans. on AC, 1 982,27(6):1250-1252.[5]何友,譚慶海,蔣蓉蓉.多傳感器綜合系統(tǒng)中的航跡相關(guān)算法[J].火力與指揮控制,1989,14(1):1-12.[6]Kenefic R J. Local and remote track file registration using minimum description length[J]. IEEE Trans. on AES; 1993, 29(3):651 - 655.[7]何友,彭應(yīng)寧,陸大繪.多傳感器數(shù)據(jù)融合模型評述[J].清華大學(xué)學(xué)學(xué)報,1996,36(9):14-20.[8]何友,陸大繪彭應(yīng)寧,高志永.多傳感器數(shù)據(jù)融合中兩種航跡相關(guān)算法[J].電子學(xué)報,1997,25(9):10-14.[9]何友,王國宏,陸大繪,彭應(yīng)寧.多傳感器信息融合及應(yīng)用[M].北京:電子工業(yè)出版社,2000:135-136.[10]Pattipati K R, et al.. A new relaxation algorithm and passive sensor data association problem[J]. IEEE Trans. on AC, 1992,37(2): 198 - 213.[11]Deb S, et al.. An S-dimensional assignment algorithm for track initiation[R]. Proc. of the IEEE Int. Conf. Systems Engineering, Kobe, Japan, Sept. 1992:527 - 530. -
計量
- 文章訪問數(shù): 2548
- HTML全文瀏覽量: 161
- PDF下載量: 764
- 被引次數(shù): 0
下載:
