Lune

ACM MM2022Top-tier venue

Rail Detection: An Efficient Row-based Network and a New Benchmark

Xinpeng Li, Xiaojiang Peng

Abstract

Rail detection, essential for railroad anomaly detection, aims to identify the railroad region in video frames. Although various studies on rail detection exist, neither an open benchmark nor a high-speed network is available in the community, making al- gorithm comparison and development difficult. Inspired by the growth of lane detection, we propose a rail database and a row- based rail detection method. In detail, we make several contribu- tions: (i) We present a real-world railway dataset, Rail-DB, with 7432 pairs of images and annotations. The images are collected from different situations in lighting, road structures, and views. The rails are labeled with polylines, and the images are catego- rized into nine scenes. The Rail-DB is expected to facilitate the improvement of rail detection algorithms. (ii) We present an ef- ficient row-based rail detection method, Rail-Net, containing a lightweight convolutional backbone and an anchor classifier. Specif- ically, we formulate the process of rail detection as a row-based selecting problem. This strategy reduces the computational cost compared to alternative segmentation methods. (iii) We evaluate the Rail-Net on Rail-DB with extensive experiments, including cross-scene settings and network backbones ranging from ResNet to Vision Transformers. Our method achieves promising perfor- mance in terms of both speed and accuracy. Notably, a lightweight version could achieve 92.77% accuracy and 312 frames per second. The Rail-Net outperforms the traditional method by 50.65% and the segmentation one by 5.86%. The database and code are available at: https://github.com/Sampson-Lee/Rail-Detection.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection cites Learning Lightweight Lane Detection CNNs by Self Attention Distillation
  • Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane Detection cites Inter-Region Affinity Distillation for Road Marking Segmentation
  • Inter-Region Affinity Distillation for Road Marking Segmentation cites Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  2. Learning Lightweight Lane Detection CNNs by Self Attention DistillationYuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change LoyICCV 2019 · 666 citations
  3. Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane DetectionLucas Tabelini Torres, Rodrigo Ferreira Berriel, Thiago M. Paixão, Claudine Badue et al.CVPR 2021
  4. Inter-Region Affinity Distillation for Road Marking SegmentationYuenan Hou, Zheng Ma, Chunxiao Liu, Tak-Wai Hui et al.CVPR 2020

Related papers

  1. Improving Transformer Based Line Segment Detection with Matched Predicting and Re-rankingXin Tong, Shi Peng, Baojie Tian, Yufei Guo et al.AAAI 2025 · 3 citations
  2. RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object DetectionPei Sun, Weiyue Wang, Yuning Chai, Gamaleldin Elsayed et al.CVPR 2021
  3. Video Instance Lane Detection via Deep Temporal and Geometry Consistency ConstraintsMingqian Wang, Yujun Zhang, Wei Feng, Lei Zhu et al.ACM MM 2022 · 10 citations
  4. AKCMamba-YOLO: Selective State Space Models For Real-Time Object DetectionLong Chen, Hui Wang, Man Xu, Zexuan Li et al.CVPR 2026
  5. From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain RemovalYun Guo, Xueyao Xiao, Yi Chang, Shumin Deng et al.ICCV 2023 · 51 citations
Dusk over the sea between two cliffs drawn in fine vertical lines