Datasets › York Urban Line Segment Database

York Urban Line Segment Database

archive 2025-07-28

The York Urban Line Segment Database is a compilation of 102 images (45 indoor, 57 outdoor) of urban environments consisting mostly of scenes from the campus of York University and downtown Toronto, Canada. The images are 640 x 480 in size and have been taken with a calibrated Panasonic Lumix DMC-LC80 digital camera.

Each image in the database has been hand-labelled to identify the set of line segments satisfying the “Manhattan assumption” (Coughlan & Yuille 2003), i.e., the set of line segments that conform to the 3D orthogonal frame of the urban environment.

These hand-labelled data have been used to identify the three Manhattan vanishing points in each image and from these to identify the Euler angles relating the camera frame to the Manhattan frame of the scene.

The database provides the original images, camera calibration parameters, ground truth line segments, and estimated Manhattan frame relative to the camera for each image.

Source: York Urban Line Segment Database

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Line Segment Detection York Urban Dataset LINEA-L sAP5 30.9 LINEA: Fast and Accurate Line Detection Using Scalable... SebastianJanampa/LINEA 16 Compare
Horizon Line Estimation York Urban Dataset V AUC (horizon error) 95.35 A-Contrario Horizon-First Vanishing Point Detection... alexvonduar/V 4 Compare

Papers archive 2025-07-28

17 shown of 17 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 17. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
LINEA: Fast and Accurate Line Detection Using Scalable Transformers 1 4 22 May 2025 not harvested
DT-LSD: Deformable Transformer-based Line Segment Detection 1 1 20 Nov 2024 not harvested
LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection 1 1 10 Sep 2022 not harvested
Towards Light-weight and Real-time Line Segment Detection 2 1 1 Jun 2021 not harvested
ELSD: Efficient Line Segment Detector and Descriptor 0 1 29 Apr 2021 not harvested
Fully Convolutional Line Parsing 2 1 22 Apr 2021 ran 2 of 19 samples (17 unverified)
Line Segment Detection Using Transformers without Edges 2 1 6 Jan 2021 ran 1 of 1 samples (0 unverified)
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras 2 1 6 Nov 2020 not harvested
TP-LSD: Tri-Points Based Line Segment Detector 2 1 11 Sep 2020 not harvested
Deep Hough-Transform Line Priors 1 1 18 Jul 2020 not harvested
Holistically-Attracted Wireframe Parsing 1 1 3 Mar 2020 not harvested
End-to-End Wireframe Parsing 1 1 8 May 2019 ran 1 of 14 samples (13 unverified)
A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws 1 1 1 Sep 2018 not harvested
Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection 2 1 8 Jul 2017 not harvested
MCMLSD: A Dynamic Programming Approach to Line Segment Detection 0 1 1 Jul 2017 not harvested
Detecting Vanishing Points using Global Image Context in a Non-Manhattan World 1 1 19 Aug 2016 not harvested
Horizon Lines in the Wild 1 1 7 Apr 2016 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • York Urban Dataset
  • York Urban Line Segment Database

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections