cs.CVNov 14, 2026

FDAM: A Frequency-Direction-Aware Multi-Task Framework for Pavement Crack Grid Localization

Authors: Haiyang Xu, Bin Pan, Mengze Wang, Qiaoying Qu, Zhenwei Shi

Organizations: School of Statistics and Data Science, LEBPS, KLMDASR, LPMC, AAIS, NITFID, Nankai University · Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University

Abstract

Pavement crack grid localization remains challenging for thin and tiny cracks due to weak visual cues and background interference. Box detection often misses these cracks, while supervised semantic segmentation faces limited pixel-wise annotations and high labeling costs. In this paper, we propose a Frequency-Direction-Aware Multi-Task framework (FDAM) with box detection and grid classification branches. The core grid classification branch comprises Frequency-Domain Enhancement (FDE) and Directional Feature Refinement (DFR). FDE adaptively weights spectral bands and fuses reconstructed features with spatial features. DFR captures thin crack patterns through multi-scale strip convolutions, direction-sensitive modulation, and feature recalibration. Sparse positive cells and ambiguous local predictions motivate adaptive grid supervision. Adaptive Importance Reweighting emphasizes uncertain predictions and local label transitions, with focal supervision for all cells. Our contribution is to couple the box detection and grid classification branches through shared feature learning for pavement crack grid localization. We validate FDAM on our RoadDistress2026 dataset of thin and tiny cracks and further evaluate it on public datasets Crack500 and DeepCrack. The code is available at https://github.com/Lab-PANbin/FDAM

Explore similar work

May 25, 2026

Pixel-Level Pavement Distress Assessment Using Instance Segmentation

Automated pavement distress assessment requires more than image-level classification or coarse bounding box detection, demanding precise localization of thin, branching, and irregular cracks to achieve the geometric precision necessary for maintenance-relevant quantification. This paper presents a vision-based pavement distress analysis system based on Mask R-CNN instance segmentation and evaluates it on UWGB-StreetCrack, a custom field-collected roadway image dataset acquired with a vehicle-mounted smartphone and manually annotated with polygon labels for longitudinal cracks, transverse cracks, alligator cracks, and potholes. Five Detectron2-based Mask R-CNN backbone variants were considered under a consistent fine-tuning protocol. The best-performing model, Mask R-CNN with a ResNet-101 FPN backbone, achieved 84.23% precision, 90.04% recall, and an F1 score of 87.04% under the project-specific bounding-box matching protocol. The same model produced an aggregate predicted crack-area fraction of 2.164%, closely matching the 2.170% ground-truth crack-area fraction. To contextualize the segmentation system against a detector-oriented alternative, a CSPDarknet53-based YOLO detector was also adapted and retrained on the dataset, reaching 27.5% precision and 20.7% recall on the validation protocol. The results show that instance segmentation is a practical direction for field pavement imagery and aggregate crack-area estimation, while also exposing open challenges in annotation consistency, class imbalance, confounder rejection, and mask-level benchmarking.
Jun 4, 2026

Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure

Reliable crack assessment requires not only accurate pixel-level masks but also connected crack geometry and confidence estimates that remain stable under domain shift. However, existing segmentation models can achieve high overlap scores while fragmenting cracks, missing fine branches, and providing no calibrated uncertainty. To address this gap, this paper proposes CrackGeoFM, a multi-task framework that combines a frozen visual foundation backbone with crack-specific adaptation for mask prediction, skeleton reconstruction, and uncertainty estimation. The framework integrates a Frequency-Guided Crack Enhancement Module (FCEM) to enhance high-frequency crack cues, a Crack-Domain Feature Adaptation Module (CFAM) to adapt frozen backbone features to crack-domain patterns, and a Structure-Aware Multi-Task Decoder (SMTD) to jointly decode masks, skeletons, and uncertainty. Across 20 crack datasets, CrackGeoFM achieves state-of-the-art segmentation, improved topology preservation, calibrated uncertainty, and effective few-shot adaptation with only five labeled images. These results support reliable, generalizable, and engineering-oriented crack analysis for infrastructure assessment.
Oct 24, 2026

DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions

Pavement crack segmentation under low light is degraded by reduced contrast, shadows, headlight glare, joints, stains, and wet seams. Existing crack segmentation methods mostly assume good illumination. Low-light enhancement methods improve visual quality, but they do not explicitly preserve crack topology. To address these limitations, we formulate low-light crack segmentation as a degradation-aware, prompt-grounded structural defect segmentation problem and propose DROA-CLIPSeg, a parameter-efficient framework that adapts a frozen CLIPSeg vision language backbone using two lightweight modules. QKV Low-Rank Adaptation is injected into the Q/K/V projections of the vision and text encoders to improve crack-specific image text alignment without backbone fine-tuning. The proposed Domain Residual Orthogonal Adapter (DROA) decomposes intermediate features into a dominant crack-domain branch, which captures recurring low-light crack patterns, and an orthogonal residual branch, which preserves faint, thin, and fragmented evidence usually suppressed by noise, shadow, or over-smoothing. We also introduce CrackLingo-9K and CrackLingo-12K, text augmented versions of Crack9k and Crack12k with crack-aware prompts. Training only approximately 1.93 M parameters, corresponding to 1.3% of the full model, DROA-CLIPSeg outperforms 9 zero-shot and 4 fine-tuned vision language baselines on both splits, generalises zero-shot to MVTec AD across textures and defect morphologies, and is supported by extensive ablations. Our source code is publicly available at https://github.com/VShuklacode/DROA-CLIPSeg