Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 10, 2025SensorsOpen Access

CONTI-CrackNet: A Continuity-Aware State-Space Network for Crack Segmentation

View Full Paper
Ask AI
Bookmark
Share

Authors

WSWenjie SongMZMin ZhaoXXXunqian Xu

Discussion

Loading...

Member takes

Overview

Experimental evaluation shows F1 score of 0.8332 in public benchmarks, indicating CONTI-CrackNet enhances crack detection with low computational cost.

Key Points

  • Crack segmentation accuracy improves, showing an F1 score of 0.8332 and mIoU of 0.8436 on the TUT dataset.
  • The approach combines a Multi-Directional Selective Scanning Strategy, enhancing detail preservation and global continuity.
  • Using 512 × 512 inputs, the model processes with 24.22 G floating point operations and operates at 42 frames per second.
  • Results suggest CONTI-CrackNet offers a favorable trade-off in crack detection performance and computational efficiency.

Cite This Study

Song et al. (2025) studied this question.

synapsesocial.com/papers/69253a16c0ce034ddc356e17https://doi.org/10.3390/s25226865
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1CrackNet: A novel multi-scale architecture for crack segmentation2026 · 1 citations
  2. 2TriCrackNet: Trilateral Segmentation Network for Real‐Time Crack Segmentation2026
  3. 3Enhanced Crack Segmentation via Dual-Branch CNN-Transformer Architecture with Linear Perception and Multi-Scale Refinement2025
  4. 4CMD-CrackNet: A Modular, Interpretable, and Lightweight Approach to Crack Segmentation under Data Scarcity2026
  5. 5LiteCrackSeg: A lightweight hybrid CNN-transformer for efficient crack segmentation.2026 · 2 citations