Abstract
This paper proposes an improved Gaussian mixture model (GMM) for outdoor scene classification. The GMM is usually solved by the expectation-maximization (EM) algorithm, but the EM algorithm may easily lead to local optima with the convergence speed of this method unstable and different initial values also leading to fluctuations in the algorithm’s performance. As a result, a hybrid particle swarm optimization (PSO) algorithm is introduced to replace the EM algorithm for solving the aforementioned problems with a series of improvements also proposed when the hybrid PSO algorithm is used to solve the GMM. Experimental results with outdoor scene classification show that the proposed algorithm, compared to other algorithms, can enhance global search capabilities and convergence speed; in addition, the accuracy of parameter estimation is high, and classification performance is excellent.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Christopher AB, Karl I. Self-supervised terrain classification for planetary surface exploration rovers. J Field Rob. 2012;29(3):445–68.
Marcel H, et al. Probabilistic terrain classification in unstructured environments. Robot Auton Syst. 2013;61(10):1051–9.
Thomas JP, et al. An improved simple morphological filter for the terrain classification of airborne LIDAR data. ISPRS J Photogramm Remote Sens. 2013;77(3):21–30.
Li W, Prasad S, Fowler JE. Hyperspectral image classification using Gaussian mixture models and Markov random fields. IEEE Geosci Remote Sens Lett. 2014;11(1):153–7.
Han G. Algorithmic research for unstructured scene image interpretation. Nanjing: Nanjing University of Science and Technology; 2010 (in Chinese).
Chen YJ, et al. Brain MRIS segmentation using the active contours based on Gaussian mixture. J Comput Res Dev. 2007;44(9):1595–603 (in Chinese).
Eberhart RC, Shi Y. Particle swarm optimization: developments, applications and resources. In: The 2001 Congress on Evolutionary Computation, vol. 1. Seoul, Korea: IEEE Press; 2001. p. 81–6.
Gao S, et al. Solving traveling salesman problem by hybrid particle swarm optimization algorithm. Control Decis. 2004;19(11):1286–9 (in Chinese).
Castano R, Manduchi R, Fox J. Classification experiments on real-world texture. In: Proceedings of the Third Workshop on Empirical Evaluation Methods in Computer Vision. Pasadena: Jet Propulsion Laboratory; 2001. p. 3–20.
Fan SK, Lin Y. A multi-level thresholding approach using a hybrid optimal estimation algorithm. Pattern Recogn Lett. 2007;28(5):662–9.
Acknowledgments
This work is supported by China National Natural Science Foundation (61302156) and the University Natural Science Research Project of Jiangsu Province (13KJB510021).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Han, G. (2015). An Improved Gaussian Mixture Model and Its Application. In: Wong, W. (eds) Proceedings of the 4th International Conference on Computer Engineering and Networks. Lecture Notes in Electrical Engineering, vol 355. Springer, Cham. https://doi.org/10.1007/978-3-319-11104-9_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-11104-9_14
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11103-2
Online ISBN: 978-3-319-11104-9
eBook Packages: EngineeringEngineering (R0)