{"success":true,"data":{"author":"Shiwei Luo, Xiongyao Xie, Biao Zhou, Kun Zeng and Jun Guo","bucketAccessType":"public","bucketName":"shiweiluo99/tunnel-crack-segmentation-dataset","bucketPrefix":"","category":"Computer Vision","cloudProvider":"huggingface","createdAt":"2026-11-21T22:15:33.350Z","description":"The Complex Tunnel Crack Dataset (CTCD) is a civil-infrastructure inspection set of 292 tunnel lining images (256x256 pixels) with pixel-level crack segmentation masks, collected from 52 highway tunnels in Yunnan and Zhejiang, China, with a high-speed tunnel inspection vehicle. Crack pixels were annotated by hand in Photoshop with a 1 to 2 pixel brush sized to the crack width. It was introduced in the CraSAM paper, which builds a crack detection network on the Segment Anything visual foundation model, to test how crack segmentation generalizes across scenarios. The repository holds 584 BMP files (images and masks) in one folder, about 80 MB (measured 2026-11-21); load with Hugging Face datasets or PIL. Use it for crack segmentation, tunnel defect inspection and evaluating segmentation models on unseen infrastructure scenes. Images and annotations are by the authors and released under CC-BY-4.0; cite Luo et al., Multiscenario Generalization Crack Detection Network Based on the Visual Foundation Model, Structural Control and Health Monitoring 2025, doi:10.1155/stc/6269747.","displayTitle":"CTCD Complex Tunnel Crack Dataset: 292 Highway Tunnel Lining Images with Pixel-Level Crack Masks (CraSAM)","huggingFaceUrl":"https://huggingface.co/datasets/shiweiluo99/tunnel-crack-segmentation-dataset","id":"d25036b8-144f-5c18-805a-50dd6cc89761","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/shiweiluo99/tunnel-crack-segmentation-dataset","objectCountEstimate":586,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1155/stc/6269747","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"shiweiluo99/tunnel-crack-segmentation-dataset\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"shiweiluo99/tunnel-crack-segmentation-dataset\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=shiweiluo99, license:cc-by-4.0, size_categories:n<1K, format:imagefolder, downloads=2221"],"format":"mixed","generatedAt":"2026-11-21T22:31:36.772Z","layout":{"example":"Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp","truncatedAt":512}],"sampleObjects":["Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp","Complex Tunnel Crack Dataset (CTCD)/train/1005-1.bmp","Complex Tunnel Crack Dataset (CTCD)/train/1011-1.bmp","Complex Tunnel Crack Dataset (CTCD)/train/1011-3.bmp","Complex Tunnel Crack Dataset (CTCD)/train/1013-1.bmp"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n  - image-segmentation\ntags:\n  - crack-detection\n  - crack-segmentation\n  - tunnel-inspection\n  - civil-engineering\n  - foundation-model\npretty_name: Complex Tunnel Crack Dataset (CTCD)\nsize_categories:\n  - n<1K\n---\n\n# Complex Tunnel Crack Dataset (CTCD)\n\n292 tunnel lining images (256 × 256) with pixel-level crack masks, collected from\n**52 highway tunnels** in Yunnan and Zhejiang, China, using a high-speed tunnel\ninspection vehicle. Crack pixels were manually\nannotated in Photoshop with a 1–2 px brush sized by crack width.\n\nThis dataset was introduced in the CraSAM paper (*Structural Control and Health\nMonitoring*, 2025), where it is used to evaluate cross-scenario generalization of\nfoundation-model-based crack segmentation.\n\n📄 **Paper:** https://doi.org/10.1155/stc/6269747\n\n## Usage\n\n```python\nfrom datasets import load_dataset\nds = load_dataset(\"shiweiluo99/tunnel-crack-segmentation-dataset\")\n```\n\n## License\n\nCC-BY-4.0. Images and annotations by the authors.\n\n## Citation\n\n```bibtex\n@article{luo2025crasam,\n  title   = {Multiscenario Generalization Crack Detection Network Based on the Visual Foundation Model},\n  author  = {Luo, Shiwei and Xie, Xiongyao and Zhou, Biao and Zeng, Kun and Guo, Jun},\n  journal = {Structural Control and Health Monitoring},\n  volume  = {2025},\n  number  = {1},\n  pages   = {6269747},\n  year    = {2025},\n  doi     = {10.1155/stc/6269747}\n}\n```","encoding":"utf8","key":"README.md","name":"README.md","size":1436,"truncated":false}],"sourceObjectKey":"Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"shiweiluo99/tunnel-crack-segmentation-dataset\", filename=\"Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"Complex Tunnel Crack Dataset (CTCD)/train/1001-1.bmp","totalObjects":586},"summary":"The Complex Tunnel Crack Dataset (CTCD) is a civil-infrastructure inspection set of 292 tunnel lining images (256x256 pixels) with pixel-level crack segmentation masks, collected…","title":"CTCD Complex Tunnel Crack Dataset: 292 Highway Tunnel Lining Images with Pixel-Level Crack Masks (CraSAM)","updatedAt":"2026-11-22T00:48:22.075Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/shiweiluo99/tunnel-crack-segmentation-dataset"}}