CONTI-CrackNet: A Continuity-Aware State-Space Network for Crack Segmentation
Sensors · 10.11.2025 · 25 (22) · 6865
DOI: 10.3390/s25226865 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.11.2025. Verfasst von Wenjie Song und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Nantong University, Nantong 226019, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nantong Natural Science Foundation of China.
Abstract (Originalsprache)
Crack segmentation in cluttered scenes with slender and irregular patterns remains difficult, and practical systems must balance accuracy and efficiency. We present CONTI-CrackNet, which is a lightweight visual state-space network that integrates a Multi-Directional Selective Scanning Strategy (MD3S). MD3S performs bidirectional scanning along the horizontal, vertical, and diagonal directions, and it fuses the complementary paths with a Bidirectional Gated Fusion (BiGF) module to strengthen global continuity. To preserve fine details while completing global texture, we propose a Dual-Branch Pixel-Level Global–Local Fusion (DBPGL) module that incorporates a Pixel-Adaptive Pooling (PAP) mechanism to dynamically weight max-pooled responses and average-pooled responses. Evaluated on two public benchmarks, the proposed method achieves an F1 score (F1) of 0.8332 and a mean Intersection over Union (mIoU) of 0.8436 on the TUT dataset, and it achieves an mIoU of 0.7760 on the CRACK500 dataset, surpassing competitive Convolutional Neural Network (CNN), Transformer, and Mamba baselines. With 512 × 512 input, the model requires 24.22 G floating point operations (GFLOPs), 6.01 M parameters (Params), and operates at 42 frames per second (FPS) on an RTX 3090 GPU, delivering a favorable accuracy–efficiency balance. These results show that CONTI-CrackNet improves continuity and edge recovery for thin cracks while keeping computational cost low, and it is lightweight in terms of parameter count and computational cost.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Science and Technology, Nantong University, Nantong 226019, China.
- School of Artificial Intelligence and Computer Science, Nantong University, Nantong 226019, China.
- School of Transportation and Civil Engineering, Nantong University, Nantong 226019, China.
Förderung
- Nantong Natural Science Foundation of China
Zitieren
APA
Song, W., Zhao, M., & Xu, X. (2025). CONTI-CrackNet: A Continuity-Aware State-Space Network for Crack Segmentation. Sensors, 25(22), 6865. https://doi.org/10.3390/s25226865
Vancouver
Song W, Zhao M, Xu X. CONTI-CrackNet: A Continuity-Aware State-Space Network for Crack Segmentation. Sensors. 2025;25(22):6865. doi:10.3390/s25226865
BibTeX
@article{Song2025,
author = {Song, Wenjie and Zhao, Min and Xu, Xunqian},
title = {CONTI-CrackNet: A Continuity-Aware State-Space Network for Crack Segmentation},
journal = {Sensors},
year = {2025},
volume = {25},
number = {22},
pages = {6865},
doi = {10.3390/s25226865}
}
EUVIMED