Automatic Coal and Gangue Segmentation Using U-Net Based Fully Convolutional Networks

Sorting gangue from raw coal is an essential concern in coal mining engineering. Prior to separation, the location and shape of the gangue should be extracted from the raw coal image. Several approaches regarding automatic detection of gangue have been proposed to date; however, none of them is satisfying. Therefore, this paper aims to conduct gangue segmentation using a U-shape fully convolutional neural network (U-Net). The proposed network is trained to segment gangue from raw coal images collected under complex environmental conditions. The probability map outputted by the network was used to obtain the location and shape information of gangue. The proposed solution was trained on a dataset consisting of 54 shortwave infrared (SWIR) raw coal images collected from Datong Coalfield. The performance of the network was tested with six never seen images, achieving an average area under the receiver operating characteristics (AUROC) value of 0.96. The resulting intersection over union (IoU) was on average equal to 0.86. The results show the potential of using deep learning methods to perform gangue segmentation under various conditions.

[1]  Kai Liu,et al.  Extraction of Coal and Gangue Geometric Features with Multifractal Detrending Fluctuation Analysis , 2018 .

[2]  Johan Spross,et al.  Landslide susceptibility hazard map in southwest Sweden using artificial neural network , 2019 .

[3]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Y Ichioka,et al.  Parallel distributed processing model with local space-invariant interconnections and its optical architecture. , 1990, Applied optics.

[5]  Stefan Larsson,et al.  An artificial neural network based model to predict spatial soil type distribution using piezocone penetration test data (CPTu) , 2018, Bulletin of Engineering Geology and the Environment.

[6]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[7]  Hao Li,et al.  Separation of gangue from coal based on supplementary texture by morphology , 2019, International Journal of Coal Preparation and Utilization.

[8]  Zhenxin Zhang,et al.  An Image-Based Hierarchical Deep Learning Framework for Coal and Gangue Detection , 2019, IEEE Access.

[9]  He Huang,et al.  Lane Detection of Curving Road for Structural Highway With Straight-Curve Model on Vision , 2019, IEEE Transactions on Vehicular Technology.

[10]  Wei Hou,et al.  Identification of Coal and Gangue by Feed-forward Neural Network Based on Data Analysis , 2019 .

[11]  Debi Prasad Tripathy,et al.  Novel Methods for Separation of Gangue from Limestone and Coal using Multispectral and Joint Color-Texture Features , 2017 .

[12]  Anna Fabijanska,et al.  Segmentation of corneal endothelium images using a U-Net-based convolutional neural network , 2018, Artif. Intell. Medicine.