pith:FLFOQOLV
Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection
Lightweight CNN with attention and focal loss detects bridge cracks at 825 FPS for UAV inspections.
arxiv:2604.27617 v2 · 2026-04-30 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{FLFOQOLVC7PEHBFAZCCQ7X7IJB}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on the SDNET2018 bridge deck dataset show that the proposed method achieves an inference speed of 825 FPS with only 11.21M parameters and 1.82G FLOPs. Compared with the baseline model, the complete framework improves the F1-score by 2.51% and recall by 3.95%.
That the directed robust augmentation strategy based on inspection-scene priors, when combined with CBAM and Focal Loss, will produce robust performance gains that generalize from the SDNET2018 dataset to varied real-world UAV flight conditions, lighting, and bridge types not represented in the test set.
A lightweight CNN framework with CBAM, targeted augmentation, and focal loss runs at 825 FPS on the SDNET2018 dataset while improving F1-score by 2.51% and recall by 3.95% over baseline for bridge crack detection.
Receipt and verification
| First computed | 2026-06-01T01:02:40.937274Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
2acae8397517de4384a0c8850fdfe8484b53d98ba14673d7a2309175af3ae0ba
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/FLFOQOLVC7PEHBFAZCCQ7X7IJB \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 2acae8397517de4384a0c8850fdfe8484b53d98ba14673d7a2309175af3ae0ba
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "259fb75bfd695badf4071735ad3ff35e902462b5163125ff863b251557a161bc",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-30T09:08:41Z",
"title_canon_sha256": "c26977d1713e6fdc85dbae7996a8fad5b3a3b59630f2d91c98ffc2c85eaca0b3"
},
"schema_version": "1.0",
"source": {
"id": "2604.27617",
"kind": "arxiv",
"version": 2
}
}