A method of using geomagnetic anomaly to recognize objects based on HOG and 2D-AVMD

In order to identify the shape of underground small magnetic anomaly objects, we use Support Vector Machines (SVM) to identify the underground magnetic anomaly targets. Firstly, as the SVM needs a lot of training data, and we also need to make full use of the magnetic field signal, nine component signals including total magnetic intensity (TMI) and five independent components of tensor are calculated from the original detected magnetic signal. Secondly, the nine component signals are subjected respectively to two-dimensional adaptively variational mode decomposition (2D-AVMD), which is advanced based on the two indicators, namely Mutual information (MI) and empirical entropy (EE), and we can get the nine primary signals from the decomposition results of nine component signals called the Intrinsic Mode Function (IMF). Then, the Histogram of Oriented Gradients (HOG) of the nine primary signals is extracted, and the feature data would be constructed into feature vectors. In the end, Support Vector Machines (SVM) are adopted to process these feature vectors. The output of the SVM can indicate the result of small objects’ shape recognition under the ground. Experiments prove that the shape recognition accuracy of underground small magnetic anomaly object recognition reaches 90%.In order to identify the shape of underground small magnetic anomaly objects, we use Support Vector Machines (SVM) to identify the underground magnetic anomaly targets. Firstly, as the SVM needs a lot of training data, and we also need to make full use of the magnetic field signal, nine component signals including total magnetic intensity (TMI) and five independent components of tensor are calculated from the original detected magnetic signal. Secondly, the nine component signals are subjected respectively to two-dimensional adaptively variational mode decomposition (2D-AVMD), which is advanced based on the two indicators, namely Mutual information (MI) and empirical entropy (EE), and we can get the nine primary signals from the decomposition results of nine component signals called the Intrinsic Mode Function (IMF). Then, the Histogram of Oriented Gradients (HOG) of the nine primary signals is extracted, and the feature data would be constructed into feature vectors. In the end, Support Vector Machines (...

[1]  Q. Cheng.  A New Model for Quantifying Anisotropic Scale Invariance and for Decomposition of Mixing Patterns , 2004 .

[2]  Wencai Yang,et al.  Multi-scale inversion of density structure from gravity anomalies in Tarim Basin , 2011 .

[3]  Asadollah Shahbahrami,et al.  Evaluation of Adaptive Boosting and Neural Network in Earthquake Damage Levels Detection , 2014 .

[4]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[5]  Maurizio Fedi,et al.  On the application of Euler deconvolution to the analytic signal , 2005 .

[6]  Subhadeep Mukhopadhyay,et al.  LPiTrack: Eye movement pattern recognition algorithm and application to biometric identification , 2018, Machine Learning.

[7]  Houkuan Huang,et al.  Feature selection for text classification with Naïve Bayes , 2009, Expert Syst. Appl..

[8]  B. Ehret.  Pattern recognition of geophysical data , 2010 .

[9]  Huaguang Zhang,et al.  A fuzzy support vector machine algorithm for classification based on a novel PIM fuzzy clustering method , 2014, Neurocomputing.

[10]  David A. Clark,et al.  Estimating source location using normalized magnetic source strength calculated from magnetic gradient tensor data , 2012 .

[11]  Algebraic reconstruction combined with the signal space separation method for the inverse magnetoencephalography problem with a dipole-quadrupole source , 2014 .

[12]  S. Ando,et al.  A Closed-Form Formula for Magnetic Dipole Localization by Measurement of Its Magnetic Field and Spatial Gradients , 2006, IEEE Transactions on Magnetics.

[13]  Tao Liu,et al.  Multiscale Fractures Characterization Based on Ant Colony Optimization and Two-Dimensional Variational Mode Decomposition , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Fernando De la Torre,et al.  Optimal feature selection for support vector machines , 2010, Pattern Recognit..

[15]  Hyoungrea Rim,et al.  Interpretation of magnetic gradient tensor for automatic locating a dipole source , 2012 .

[16]  David A. Clark,et al.  New methods for interpretation of magnetic vector and gradient tensor data I: eigenvector analysis and the normalised source strength , 2012 .

[17]  B. Oruç.  Depth Estimation of Simple Causative Sources from Gravity Gradient Tensor Invariants and Vertical Component , 2010 .

[18]  A. Chwala,et al.  Magnetic full-tensor SQUID gradiometer system for geophysical applications , 2006 .

[19]  L. Pedersen,et al.  Comment on “Depth Estimation of Simple Causative Sources from Gravity Gradient Tensor Invariants and Vertical Component” by B. Oruç in Pure Appl. Geophys. 167 (2010), 1259–1272 , 2011, Pure and Applied Geophysics.

[20]  Ping Wang,et al.  Full magnetic gradient tensor from triaxial aeromagnetic gradient measurements: Calculation and application , 2015, Applied Geophysics.

[21]  Dominique Zosso,et al.  Two-Dimensional Variational Mode Decomposition , 2015, EMMCVPR.

[22]  Navneet Dalal,et al.  Finding People in Images and Videos , 2006 .

[23]  Ettore Cardarelli,et al.  Statistical pattern recognition technique to enhance anomalies in magnetic surveys , 1997 .

[24]  Lianghui Guo,et al.  Preferential filtering for gravity anomaly separation , 2013, Comput. Geosci..

[25]  W. E. Glenn,et al.  Image processing of aeromagnetic data and integration with Landsat images for improved structural interpretation , 1987 .

[26]  Yih Jeng,et al.  Two-dimensional nonlinear geophysical data filtering using the multidimensional EEMD method , 2014 .

[27]  Q. Cheng,et al.  Identification of REE mineralization-related geochemical anomalies using fractal/multifractal methods in the Nanling belt, South China , 2014, Environmental Earth Sciences.

[28]  Leslie S. Smith,et al.  Feature subset selection in large dimensionality domains , 2010, Pattern Recognit..