A 91-Channel Hyperspectral LiDAR for Coal/Rock Classification

During the mining operation, it is a critical task in coal mines to significantly improve the safety by precision coal mining sorting and rock classification from different layers. It implies that a technique for rapidly and accurately classifying coal/rock in-site needs to be investigated and established, which is of significance for improving the coal mining efficiency and safety. In this letter, a 91-channel hyperspectral LiDAR (HSL) using an acousto-optic tunable filter (AOTF) as the spectroscopic device is designed, which operates based on the wide-spectrum emission laser source with a 5-nm spectral resolution to tackle this issue. The spectra of four-type coal/rock specimens collected by HSL are used to classify with three multi-label classifiers: naive Bayes (NB), logistic regression (LR), and support vector machine (SVM). Furthermore, we discuss and explore whether Gaussian fitting (GF) method and calibration with the reference whiteboard (RB) can enhance the classification accuracy. The experimental results show that the GF technique not only improves the accuracy of range measurement but also optimizes the classification performance using the spectra collected by the HSL. In addition, calibration with RB can improve classification accuracy as well. In addition, we also discuss methods to improve the calibration-free classification accuracy preliminarily.

[1]  Simon Lacroix,et al.  Improving LiDAR point cloud classification using intensities and multiple echoes , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  J. Suomalainen,et al.  Full waveform hyperspectral LiDAR for terrestrial laser scanning. , 2012, Optics express.

[3]  Kazhong Deng,et al.  Large-scale deformation monitoring in mining area by D-InSAR and 3D laser scanning technology integration , 2013 .

[4]  Vlastimil Kajzar,et al.  Use of 3D Laser Scanner Technology to Monitor Coal Pillar Deformation , 2016 .

[5]  Xiaowei Yu,et al.  Improving Automation in Map Updating Based on National Laser Scanning, Classification Trees, Object-Based Change Detection and 3D Object Reconstruction , 2007, 2007 Urban Remote Sensing Joint Event.

[6]  Yuwei Chen,et al.  Two-channel Hyperspectral LiDAR with a Supercontinuum Laser Source , 2010, Sensors.

[7]  Hongwei Guo,et al.  A Simple Algorithm for Fitting a Gaussian Function , 2012 .

[8]  Ning Wang,et al.  A 10-nm Spectral Resolution Hyperspectral LiDAR System Based on an Acousto-Optic Tunable Filter , 2019, Sensors.

[9]  Vlastimil Kajzar,et al.  Possibility of convergence measurement of gates in coal mining using terrestrial 3D laser scanner , 2015, Journal of Sustainable Mining.

[10]  Wei Gong,et al.  Application of spectral indices and reflectance spectrum on leaf nitrogen content analysis derived from hyperspectral LiDAR data , 2018, Optics & Laser Technology.

[11]  Azuraliza Abu Bakar,et al.  Naïve bayes variants in classification learning , 2010, 2010 International Conference on Information Retrieval & Knowledge Management (CAMP).

[12]  Christian Böhm,et al.  Supervised machine learning techniques for the classification of metabolic disorders in newborns , 2004, Bioinform..

[13]  W. Wagner,et al.  Gaussian decomposition and calibration of a novel small-footprint full-waveform digitising airborne laser scanner , 2006 .

[14]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[15]  Teemu Hakala,et al.  Artificial target detection with a hyperspectral LiDAR over 26-h measurement , 2015 .

[16]  Hongwei Guo,et al.  A Simple Algorithm for Fitting a Gaussian Function [DSP Tips and Tricks] , 2011, IEEE Signal Processing Magazine.

[17]  Zhijie Wen,et al.  Feasibility Study of Ore Classification Using Active Hyperspectral LiDAR , 2018, IEEE Geoscience and Remote Sensing Letters.

[18]  Hong Chen,et al.  The safety-level gap between China and the US in view of the interaction between coal production and safety management , 2013 .

[19]  P. Litkey,et al.  Tree species classification from fused active hyperspectral reflectance and LIDAR measurements. , 2010 .

[20]  Vlastimil Kajzar,et al.  VERIFYING THE POSSIBILITIES OF USING A 3D LASER SCANNER IN THE MINING UNDERGROUND , 2015 .

[21]  Juha Hyyppä,et al.  Classification of Spruce and Pine Trees Using Active Hyperspectral LiDAR , 2013, IEEE Geoscience and Remote Sensing Letters.

[22]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.