Adaptive Multi-Scale Feature Fusion Based Residual U-net for Fracture Segmentation in Coal Rock Images

Abstract

<jats:title>Abstract</jats:title> <jats:p>Accurate segmentation of fractures in coal rock CT images is important for safe production and the development of coalbed methane. However, the coal rock fractures formed through natural geological evolution, which are complex, low contrast and different scales. Furthermore, there is no published data set of coal rock. In this paper, we proposed adaptive multi-scale feature fusion based residual U-uet (AMSFFR-U-uet) for fracture segmentation in coal rock CT images. The dilated residual blocks (DResBlock) with dilated ratio (1,2,3) are embedded into encoding branch of the U-uet structure, which can improve the ability of extract feature of network and capture different scales fractures. Furthermore, feature maps of different sizes in the encoding branch are concatenated by adaptive multi-scale feature fusion (AMSFF) module. And AMSFF can not only capture different scales fractures but also improve the restoration of spatial information. To alleviate the lack of coal rock fractures training data, we applied a set of comprehensive data augmentation operations to increase the diversity of training samples. Our network, U-net and Res-U-net are tested on our test set of coal rock CT images with five different region coal rock samples. The experimental results show that our proposed approach improve the average Dice coefficient by 2.9%, the average precision by 7.2% and the average Recall by 9.1% , respectively. Therefore, AMSFFR-U-net can achieve better segmentation results of coal rock fractures, and has stronger generalization ability and robustness.</jats:p>

Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks

“…As an alternative approach, various supervised (Karimpouli et al 2020;Lu et al 2020;Lee et al 2021) and unsupervised (Taibi et al 2019;Zhang et al 2021) machine learning techniques were implemented for fracture identification and segmenting porous samples (Chauhan et al 2016). Among the unsupervised approaches, encoder-decoder networks in the form of CNNs received much attention during fracture identification in the DRP workflow (Varfolomeev et al 2019;Hong & Liu 2020;Karimpouli et al 2020;Kim et al 2020;Lu et al 2020;Lee et al 2021). Studies showed the capabilities of CNNs compared to other segmentation methods (Lu et al 2021;Lee et al 2021).…”