Abstract
This paper discusses arithmetic of inversible neural network. Condensation algorithm is based on the sampling factor for conditional density propagation method, combined with the dynamic model of learning, can complete robust motion tracking. This technology was first widely used in military guidance, introduced into the monitoring system, tracking objects in particular to people or other relatively slow speed of the target, thus tracking method is more simple than the former. Current tracking methods can generally be divided into match tracking and motion tracking. Based on match of track algorithm main has regional match track, and profile match track and the features match track, regional match track of basic thought is put advance extraction of movement regional as match template, set a match metric, and in stay match figure as move template search target. Although the amount of calculation is decreased, but cannot solve the inherent defects profiles matching the basic idea is to extract the contour of objects and to track profile properties. Region matching pursuit algorithm by contour matching benefits can be achieved at a very good match, and the complexity is not high, is a focus of current research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dai, X., Zhang, K., Zhang, T.: ANN generalized inversion control of turbo-generator governor. IEEE Proc. Gener. Transm. Distrib. 151(3), 327–333 (2004)
Birol, G., Undey, C., Cinar, A.: A modular simulation package for fed-batch fermentation: penicillin production. Comput. Chem. Eng. 26, 1553–1565 (2002)
Dai, X., Zhang, K., Lu, X.: An improved ANN-inversion TCSC controller based on local measurements. IEEE Power Eng. Soc. 4, 2555–2560 (2003)
Wang, W., Dai, X.: An Interactor algorithm for invertibility in general nonlinear system. In: Proceedings of the 5th IEEE World Congress on Intelligent Control and Automation, Hangzhou, China, vol. 1, pp. 59–63, June 2004
Nasaroui, O., Gonzdez, F., Dasgupta, D.: The fuzzy artificial immune svstem: motivations, basic concepts and application to clustering and web profiling. Fuzzy Syst. 1(2), 711–716 (2002)
De Castro, L.N., Timmis, J.: Artificial Immune System: A Novel Computational Intelligence Approach. Springer, New York (2012)
Jiao, L., Wang, L.: A novel genetic algorithm based on immunity. IEEE Trans. Syst. May Cybern. Part A Syst. Hum. 30(5), 552 (2010)
Wu, X., Chen, Z.: Chaos Study Introductory Remarks. Shanghai Science and technology Publishing House, Shanghai (2012)
Jin, G., Zhang, L., Hu, F.-S.: Investigation on space optical system of high F number and high resolution. Opt. Precis. Eng. 15(2), 155–159 (2007)
Ken, F., Sugie, T.: Freedom in coordinate transformation for exact linearization and its application to transient behavior improvement. Automatica 37(2), 137–144 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Jian, C., Gang, L., Sen, Z., Cong, Y. (2018). Image Fusion Study by Inversible System of Neural Network. In: Qiao, F., Patnaik, S., Wang, J. (eds) Recent Developments in Mechatronics and Intelligent Robotics. ICMIR 2017. Advances in Intelligent Systems and Computing, vol 691. Springer, Cham. https://doi.org/10.1007/978-3-319-70990-1_68
Download citation
DOI: https://doi.org/10.1007/978-3-319-70990-1_68
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70989-5
Online ISBN: 978-3-319-70990-1
eBook Packages: EngineeringEngineering (R0)