LightECA-UNet: a lightweight model for segmentation of coal fracture CT images

TL;DR

LightECA-UNet is a lightweight model that improves coal fracture segmentation in CT images, offering better accuracy and efficiency for mine-site use.

Contribution

Introduces LightECA-UNet, a novel lightweight model combining DSC, ECA, and adaptive pruning for efficient coal fracture segmentation.

Findings

LightECA-UNet achieves 1.6% higher mIoU and 2.5% higher fracture IoU than popular models.

It reduces computational load by 87.1% and parameter count by 86.9% compared to lightweight models.

The model enables deployment on mine-used edge equipment without sacrificing accuracy.

Abstract

Coal fracture segmentation in CT images is critical for coal structure analysis, coalbed methane extraction, and mine safety, but it is challenged by complex fracture features and limited computing resources for mine-site deployment. Basic UNet exhibits redundancy, sensitivity to image noise, and high overfitting risk. This study proposes LightECA-UNet, integrating depthwise separable convolution (DSC), efficient channel attention (ECA), and adaptive channel pruning. Experiments show LightECA-UNet achieves 1.6% higher mean Intersection over Union (mIoU) and 2.5% higher fracture IoU than currently popular models. Compared to lightweight counterparts, it reduces computational load by 87.1% and parameter count by 86.9%, enabling deployment on mine-used edge equipment while maintaining segmentation accuracy.

Figures