Infrared Target Recognition Based on Multi-Features Fusion

Abstract:

Considering the uncertainty of calculation results by using single feature as measurement of target recognition and identification, this paper discussed the multi-features fusion technology in infrared image recognition classification. The invariant of the singular value and invariant moment feature of infrared target image were used to make fusion. According to Dempster-Shafer Theory, the basic probability assignment was calculated first, and the fusion data was used to make specification decision based on the corresponding rules in the decision-making level. The test result shows that the multi-features fusion method has a better stability, accuracy and reliability in target recognition applications. It can raise the accuracy and fault tolerance ability of infrared image recognition system. So it will have great application value to raise the guidance accuracy of infrared imaging terminal guidance system.

• Periodical: Applied Mechanics and Materials (Volumes 198-199)
• Pages: 249-255
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.198-199.249
• Online since: September 2012
• Authors: Wei Wu
• Keywords: Dempster-Shafer Theory, Infrared Target Image Recognition, Multi-Features Information Fusion

References

[1] Yang Wanhai. Multi-sensor data fusion and applications [M]. Xi'an: Xi'an Electronic Science and Technology University Press, 2004: 17-19.

[2] Nassib Nabaa, Robort H Bishop. solution to a multisensor tracking problem with sensor registration errors[J] . IEEE Trans on AES, 1999, 35(1), 354-363.

DOI: 10.1109/7.745706

[3] F. Russo, G Ramponi. Fuzzy methods for multisensor data fusion IEEE Trans. on IM, 1994, 43(2), 288-293.

DOI: 10.1109/19.293435

[4] Pan Zhenzhong. Dempster-Shafer method in multisensor information [ J] Fire Control Command Control 1994, 19(3), 12-16.

[5] Sun Hongyan, Mao Shiyi. Multisensor data fusion for target identification Chinese Jounal[ J] Electronics, 1995, 4(3), 78-84.

[6] Thierry Denoeux. A Neural Network Classifier Based on Dempster-Shafer Theory IEEE Trans on System, man, and cybemetics- part A: systems and humans 2000, 30(2) 131-150.

DOI: 10.1109/3468.833094

[7] L.A. Klein. Sensor and Data Fusion Concepts and Applications, SPIE. Opt. Engineering Press, Tutorial Texts, 1999 vol. 14.

[8] Hall D. Mathematical techniques in multisensor data fusion, Boston, Artech House, (1992).

[9] Llinas J, Waltz F. Multisensor data fusion, Boston, Arteeh House, (1990).