Saved in:
Bibliographic Details
Main Authors: Bätz, Annika, Klasek, Pavel, Ham, Seo-Young, Neumaier, Philipp, Köppel, Martin, Lauer, Martin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908991053889536
author Bätz, Annika
Klasek, Pavel
Ham, Seo-Young
Neumaier, Philipp
Köppel, Martin
Lauer, Martin
author_facet Bätz, Annika
Klasek, Pavel
Ham, Seo-Young
Neumaier, Philipp
Köppel, Martin
Lauer, Martin
contents Automated train operation on existing railway infrastructure requires robust camera-based perception, yet the railway domain lacks public benchmark suites with standardized evaluation protocols that would enable reproducible comparison of approaches. We present RAIL-BENCH, the first perception benchmark suite for the railway domain. It comprises five challenges - rail track detection, object detection, vegetation segmentation, multi-object tracking, and monocular visual odometry - each tailored to the specific characteristics of railway environments. RAIL-BENCH provides curated training and test datasets drawn from diverse real-world scenarios, evaluation metrics, and public scoreboards (https://www.mrt.kit.edu/railbench). For the rail track detection challenge we introduce LineAP, a novel segment-based average precision metric that evaluates the geometric accuracy of polyline predictions independently of instance-level grouping, addressing key limitations of existing line detection metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22507
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain
Bätz, Annika
Klasek, Pavel
Ham, Seo-Young
Neumaier, Philipp
Köppel, Martin
Lauer, Martin
Computer Vision and Pattern Recognition
Automated train operation on existing railway infrastructure requires robust camera-based perception, yet the railway domain lacks public benchmark suites with standardized evaluation protocols that would enable reproducible comparison of approaches. We present RAIL-BENCH, the first perception benchmark suite for the railway domain. It comprises five challenges - rail track detection, object detection, vegetation segmentation, multi-object tracking, and monocular visual odometry - each tailored to the specific characteristics of railway environments. RAIL-BENCH provides curated training and test datasets drawn from diverse real-world scenarios, evaluation metrics, and public scoreboards (https://www.mrt.kit.edu/railbench). For the rail track detection challenge we introduce LineAP, a novel segment-based average precision metric that evaluates the geometric accuracy of polyline predictions independently of instance-level grouping, addressing key limitations of existing line detection metrics.
title Railway Artificial Intelligence Learning Benchmark (RAIL-BENCH): A Benchmark Suite for Perception in the Railway Domain
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.22507