Work

Rock Joint Segmentation in Drill Core Images via a Boundary-Aware Token-Mixing Network

Year: 2025

Type: article

Abstract: The precise mapping of rock joint traces is fundamental to the design and safety assessment of foundations, retaining structures, and underground cavities in building and civil engineering. Existing deep learning approaches either impose prohibitive computational demands for on-site deployment or disrupt the topological continuity of subpixel lineaments that govern rock mass behavior. This study presents BATNet-Lite, a lightweight encoder–decoder architecture optimized for joint segmentation on resource-constrained devices. The encoder introduces a Boundary-Aware Token-Mixing (BATM) block that separates feature maps into patch tokens and directionally pooled stripe tokens, and a bidirectional attention mechanism subsequently transfers global context to local descriptors while refining stripe features, thereby capturing long-range connectivity with negligible overhead. A complementary Multi-Scale Line Enhancement (MLE) module combines depth-wise dilated and deformable convolutions to yield scale-invariant responses to joints of varying apertures. In the decoder, a Skeletal-Contrastive Decoder (SCD) employs dual heads to predict segmentation and skeleton maps simultaneously, while an InfoNCE-based contrastive loss enforces their topological consistency without requiring explicit skeleton labels. Training leverages a composite focal Tversky and edge IoU loss under a curriculum-thinning schedule, improving edge adherence and continuity. Ablation experiments confirm that BATM, MLE, and SCD each contribute substantial gains in boundary accuracy and connectivity preservation. By delivering topology-preserving joint maps with small parameters, BATNet-Lite facilitates rapid geological data acquisition for tunnel face mapping, slope inspection, and subsurface digital twin development, thereby supporting safer and more efficient building and underground engineering practice.

Source: Buildings

DOI: 10.3390/buildings15173022

Authors: Seungjoo Lee, Yongjin Kim, Yongseong Kim, Jongseol Park, Bongjun Ji

Institutions: Korea Institute of Civil Engineering and Building Technology, Kangwon National University, Pusan National University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $3,137