Field terrain recognition based on extreme learning theory using wavelet and texture features

Terrain recognition technology plays a key role in enhancing autonomous mobility for Quadruped robot in off-road environments. However, feature extraction and classification algorithm are the key to accuracy and efficiency of the terrain recognition. Regarding the characteristics of different terrain surface properties and structures, it gets low-dimensional and high dimensional characteristics by texture features and wavelet transform and uses them as training features of classifier. Then its efficiency is not high and convergence speed is slow for traditional learning algorithm, which is difficult to meet the requirements. So the extreme learning machine is used to classify the terrain pictures collected by robot in real time. Experimental results show that the accuracy of extreme learning machine terrain classification is higher than the traditional neural network algorithm and the support vector machine, and algorithm efficiency is raised more than several times for the sample size of 6000, which meets the requirements for accuracy, especially for real time.

[1]  Jin Zhong.  Terrain Classification Based on Visible Light and Infrared Data Fusion , 2013 .

[2]  Zhang Su-fang.  Image classification based on wavelet transformation and multi-class Support Vector Machine , 2007 .

[3]  Wu Ju.  Application of Breast Tumor Recognition in Ultrasonic Image based on the Texture Feature of Histogram , 2013 .

[4]  Yaonan Wang,et al.  Bidirectional Extreme Learning Machine for Regression Problem and Its Learning Effectiveness , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Cai Lei.  Comparison of the Extreme Learning Machine with the Support Vector Machine for Reservoir Permeability Prediction , 2010 .

[6]  Li Wang,et al.  Influence of complex topography on global solar radiation in the Yangtze River Basin , 2014, Journal of Geographical Sciences.

[7]  G. Miliaresis,et al.  Segmentation of physiographic features from the global digital elevation model/GTOPO30 , 1999 .

[8]  Hongbin Zha,et al.  Sorted Random Projections for robust texture classification , 2011, 2011 International Conference on Computer Vision.

[9]  Wansoo Kim,et al.  Performance comparison between neural network and SVM for terrain classification of legged robot , 2010, Proceedings of SICE Annual Conference 2010.

[10]  Danny Coomans,et al.  Classification Using Adaptive Wavelets for Feature Extraction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[12]  Xiao Fumin.  Classifying Complication of Seabed Terrain Based on Orthogonal Wavelet Transform , 2008 .

[13]  Richard C. Dubes,et al.  Performance evaluation for four classes of textural features , 1992, Pattern Recognit..

[14]  T. Maneewarn,et al.  Neural networks terrain classification using Inertial Measurement Unit for an autonomous vehicle , 2008, 2008 SICE Annual Conference.

[15]  Sagar V. Kamarthi,et al.  Feature Extraction From Wavelet Coefficients for Pattern Recognition Tasks , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Lian Li,et al.  Identification of fish species based on image processing and statistical analysis research , 2014, 2014 IEEE International Conference on Mechatronics and Automation.

[17]  Tomohiro Yamaguchi,et al.  Free-gait of quadruped robots using neural networks for determining the order of swing leg , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[18]  Do-Jong Kim,et al.  Terrain cover classification based on wavelet feature extraction , 2008, 2008 International Conference on Control, Automation and Systems.