Fusion of the Targets of AIS and Radar Based on a Stacked Auto-Encoder

被引：3

作者：

Cao Xiufeng ^{[1
]}

Gao Shu ^{[1
,2
]}

Jiang Zilong ^{[1
]}

Chen Liangchen ^{[1
,3
]}

Wang Yan ^{[4
]}

机构：

[1] Wuhan Univ Technol, Sch Comp Sci & Technol, Wuhan, Hubei, Peoples R China

[2] Wuhan Univ Technol, Hubei Key Lab Transportat Internet Things, Wuhan, Hubei, Peoples R China

[3] China Inst Ind Relat, Dept Comp Applicat, Beijing, Peoples R China

[4] Guizhou Univ Engn Sci, Sch Informat Engn, Bijie, Peoples R China

来源：

INDIAN JOURNAL OF GEO-MARINE SCIENCES | 2018年 / 47卷 / 11期

基金：

中国国家自然科学基金;

关键词：

track association; track Fusion; SAE; BP; Soft max;

D O I：

暂无

中图分类号：

P7 [海洋学];

学科分类号：

0707 ;

摘要：

Automatic identification system(AIS) and radar have its own advantages and disadvantages and employ track association and fusion to complement each other. This study proposes a new model of target track association and fusion based on deep learning to overcome the drawbacks of AIS and radar target traces. First, the features of fusion data are selected; then, the standard deviation is employed to normalize the pre-selected data. Next, an algorithm and regression are added to the top layer of the stacked auto-encoder(SAE), and a back propagation (BP) algorithm is used to adjust the weights and thresholds of the cost function for track association. Finally, rule items are added to the softmax regression to conduct track fusion. Experimental results demonstrate that the proposed model improves the accuracy of AIS and radar tracking.

引用

页码：2186 / 2197

页数：12

共 27 条

[1] Vessel Tracking and Anomaly Detection Using Level 0/1 and High-Level Information Fusion Techniques
Abielmona, R.
Falcon, R.
Vachon, P. W.
Groza, V. Z.
[J]. SOFT COMPUTING APPLICATIONS, (SOFA 2014), VOL 2, 2016, 357 : 769 - 780
[2] AChevere D. G, 2015, SPIE DEFENSE SECURIT, P9461
[3] [Anonymous], 2008, ICML 08, DOI 10.1145/1390156.1390294
[4] [Anonymous], 2011, Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP '11
[5] [Anonymous], Proceedings of ICML Workshop on Unsupervised and Transfer Learning
[6] Bengio Y., 2006, ADV NEURAL INFORM PR, V19
[7] Learning Deep Architectures for AI
Bengio, Yoshua
[J]. FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01): : 1 - 127
[8] Chang L, 2013, THESIS, P85
[9] Danu D, 2007, 10 INT C INF FUS JUL, P1
[10] Gao J, 2015, INDIAN J GEO-MAR SCI, V44, P1669

← 1 2 3 →