CERBERUS: Crack Evaluation & Recognition Benchmark for Engineering Reliability & Urban Stability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Reinman, Justin, Choi, Sunwoong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915361356513280
author Reinman, Justin
Choi, Sunwoong
author_facet Reinman, Justin
Choi, Sunwoong
contents CERBERUS is a synthetic benchmark designed to help train and evaluate AI models for detecting cracks and other defects in infrastructure. It includes a crack image generator and realistic 3D inspection scenarios built in Unity. The benchmark features two types of setups: a simple Fly-By wall inspection and a more complex Underpass scene with lighting and geometry challenges. We tested a popular object detection model (YOLO) using different combinations of synthetic and real crack data. Results show that combining synthetic and real data improves performance on real-world images. CERBERUS provides a flexible, repeatable way to test defect detection systems and supports future research in automated infrastructure inspection. CERBERUS is publicly available at https://github.com/justinreinman/Cerberus-Defect-Generator.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21909
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CERBERUS: Crack Evaluation & Recognition Benchmark for Engineering Reliability & Urban Stability
Reinman, Justin
Choi, Sunwoong
Computer Vision and Pattern Recognition
CERBERUS is a synthetic benchmark designed to help train and evaluate AI models for detecting cracks and other defects in infrastructure. It includes a crack image generator and realistic 3D inspection scenarios built in Unity. The benchmark features two types of setups: a simple Fly-By wall inspection and a more complex Underpass scene with lighting and geometry challenges. We tested a popular object detection model (YOLO) using different combinations of synthetic and real crack data. Results show that combining synthetic and real data improves performance on real-world images. CERBERUS provides a flexible, repeatable way to test defect detection systems and supports future research in automated infrastructure inspection. CERBERUS is publicly available at https://github.com/justinreinman/Cerberus-Defect-Generator.
title CERBERUS: Crack Evaluation & Recognition Benchmark for Engineering Reliability & Urban Stability
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21909