AutomatumPaul commited on
Commit
618f7b5
·
verified ·
1 Parent(s): 63d60d9

House format 2026-11: rendering video, research-data section, compressed images

Browse files
.gitattributes CHANGED
@@ -38,3 +38,10 @@ images/icon_tcrossing.jpg filter=lfs diff=lfs merge=lfs -text
38
  images/icon_roundabout.jpg filter=lfs diff=lfs merge=lfs -text
39
  images/dataset_ramps.jpg filter=lfs diff=lfs merge=lfs -text
40
  images/dataset_open.jpg filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
38
  images/icon_roundabout.jpg filter=lfs diff=lfs merge=lfs -text
39
  images/dataset_ramps.jpg filter=lfs diff=lfs merge=lfs -text
40
  images/dataset_open.jpg filter=lfs diff=lfs merge=lfs -text
41
+ media/area_pools_hero.jpg filter=lfs diff=lfs merge=lfs -text
42
+ media/automatum_reel.mp4 filter=lfs diff=lfs merge=lfs -text
43
+ media/automatum_reel_poster.jpg filter=lfs diff=lfs merge=lfs -text
44
+ media/crossing_hero.jpg filter=lfs diff=lfs merge=lfs -text
45
+ media/full_highway_hero.jpg filter=lfs diff=lfs merge=lfs -text
46
+ media/highway_with_ramps_hero.jpg filter=lfs diff=lfs merge=lfs -text
47
+ media/roundabout_hero.jpg filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -7,4 +7,78 @@ sdk: static
7
  pinned: false
8
  ---
9
 
10
- Automatum Data provides high-precision drone-based traffic datasets for autonomous driving research.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  pinned: false
8
  ---
9
 
10
+ <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/automatum_logo.png" alt="Automatum Data" width="220">
11
+
12
+ **Drone-based trajectory data of real traffic — bird's-eye view, all tracked road users, OpenDRIVE road models.**
13
+ Automatum Data GmbH, Ingolstadt, Germany · method published at IEEE IV 2021 · in operation since 2021
14
+
15
+ <video src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/automatum_reel.mp4" poster="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/automatum_reel_poster.jpg" controls autoplay muted loop playsinline width="100%"></video>
16
+
17
+ <sub>Rendering videos of the five datasets (3D digital twins rendered from our trajectories; last clip: pipeline video of the IEEE IV 2021 paper). Datenquelle: Bayerische Vermessungsverwaltung – www.geodaten.bayern.de, Daten verändert (CC BY 4.0).</sub>
18
+
19
+ ## Open datasets
20
+
21
+ Free excerpts from the Automatum data pool for research and teaching. Every dataset card follows the same structure: rendering video, key figures, recordings, data format, quick start, example scripts.
22
+
23
+ | | Dataset | Content | License |
24
+ |---|---|---|---|
25
+ | <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/crossing_hero.jpg" width="200"> | [**T-Crossing**](https://huggingface.co/datasets/AutomatumData/automatum-data-crossing) | 2 recordings · 683 vehicles · urban/rural T-junctions | CC BY-ND 4.0 |
26
+ | <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/roundabout_hero.jpg" width="200"> | [**Roundabout**](https://huggingface.co/datasets/AutomatumData/automatum-data-roundabout) | 2 recordings · 212 vehicles · single-lane roundabouts | CC BY-ND 4.0 |
27
+ | <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/highway_with_ramps_hero.jpg" width="200"> | [**Highway with Ramps**](https://huggingface.co/datasets/AutomatumData/automatum-data-highway-with-ramps) | 4 recordings · 7,178 vehicles · on-/off-ramps, merging | CC BY-ND 4.0 |
28
+ | <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/full_highway_hero.jpg" width="200"> | [**Full Highway**](https://huggingface.co/datasets/AutomatumData/automatum-data-full-highway) | 114 recordings · ~200,000 vehicles · 30 h of A9 motorway (IEEE IV 2021) | CC BY-ND 4.0 |
29
+ | <img src="https://huggingface.co/spaces/AutomatumData/README/resolve/main/media/area_pools_hero.jpg" width="200"> | [**Highway Area Pools**](https://huggingface.co/datasets/AutomatumData/automatum-data-highway-area-pools) | 3 multi-drone pools · 3,951 vehicles · ~1.2 km per scene, Parquet viewer | CC BY-NC 4.0 |
30
+
31
+ > Custom drone recordings for research projects — your site, your time window: [how it works](#data-for-your-own-research-question) · [info@automatum-data.com](mailto:info@automatum-data.com?subject=Research%20data%20request%20%28HF%20organisation%20page%29)
32
+
33
+ ## Data for your own research question
34
+
35
+ The public datasets are excerpts. The same validated pipeline has produced 1,670 recordings (368 hours) at 128 sites as of November 2026, and it records and processes new data on request:
36
+
37
+ - **Your site, your time window.** Junctions, roundabouts, motorway sections, construction-site layouts, service areas — recorded where your research question lives.
38
+ - **All tracked road users, full area.** Cars, vans, trucks, buses, motorcycles and vehicles with trailers in one consistent trajectory set with an OpenDRIVE road model. Several drones (up to 18 so far) can be fused in time and space into continuous trajectories over more than one kilometre.
39
+ - **Timing.** Recording and processing can be scheduled for the start of your project, so the first project phase can be spent on analysis rather than on data collection.
40
+ - **For proposals.** Feasibility note, cost estimate and, if required, a letter of intent as subcontractor or partner for your funding application. Several groups can share one recording campaign.
41
+ - **For theses and publications.** Student theses and joint method papers are welcome.
42
+
43
+ Write to [info@automatum-data.com](mailto:info@automatum-data.com?subject=Research%20data%20request%20%28HF%20organisation%20page%29) with a short description of your research question and site, or use the contact form on [automatum-data.com](https://automatum-data.com?utm_source=huggingface&utm_medium=org_card&utm_campaign=research_data). Please include the site, the time window, the road users of interest and whether the data are for a proposal or a running project. We reply with a feasibility note and a cost estimate.
44
+
45
+ ## What the data contain
46
+
47
+ - **Kinematics for every vehicle:** position (UTM), velocity, acceleration, jerk, heading, size and class, at 29.97 Hz.
48
+ - **Road model:** OpenDRIVE (XODR) per site; lane assignment, neighbour relations, TTC/THW and lane-marking distances in most releases; OpenSCENARIO exports on request.
49
+ - **Validated processing:** < 0.2 % velocity error; every processing step is versioned and recorded in each file (`CalculationStepVersions`), so results stay traceable and reproducible.
50
+ - **Python access:** `pip install openautomatumdronedata` — one loader for all datasets.
51
+
52
+ Typical uses: traffic engineering and traffic surveys, ADAS/AD scenario extraction and validation, behaviour and interaction modelling, trajectory prediction.
53
+
54
+ ## Quick start
55
+
56
+ ```python
57
+ from openautomatumdronedata.dataset import droneDataset
58
+
59
+ dataset = droneDataset("path/to/recording") # a folder from Sample_Data/ or the archive
60
+ for obj in dataset.dynWorld.get_list_of_dynamic_objects()[:5]:
61
+ speed = (obj.vx_vec[0]**2 + obj.vy_vec[0]**2) ** 0.5 * 3.6
62
+ print(obj.UUID, obj.type, f"{speed:.1f} km/h")
63
+ ```
64
+
65
+ ## Citation
66
+
67
+ ```bibtex
68
+ @inproceedings{spannaus2021automatum,
69
+ title = {AUTOMATUM DATA: Drone-based highway dataset for development and validation of automated driving software},
70
+ author = {Spannaus, Paul and Zechel, Peter and Lenz, Kilian},
71
+ booktitle = {IEEE Intelligent Vehicles Symposium (IV)},
72
+ year = {2021}
73
+ }
74
+ ```
75
+
76
+ ## Contact
77
+
78
+ [automatum-data.com](https://automatum-data.com) · [info@automatum-data.com](mailto:info@automatum-data.com) · [Documentation](https://openautomatumdronedata.readthedocs.io) · [PyPI](https://pypi.org/project/openautomatumdronedata/)
79
+
80
+ ## Geodata attribution
81
+
82
+ The 3D renderings (video and preview images) use official open geodata (DOP20, DGM1, LoD2, airborne laser data): **Datenquelle: Bayerische Vermessungsverwaltung – www.geodaten.bayern.de, Daten verändert** (CC BY 4.0, https://creativecommons.org/licenses/by/4.0/).
83
+
84
+ <sub>Automatum Data GmbH · Ingolstadt, Germany</sub>
media/area_pools_hero.jpg ADDED

Git LFS Details

  • SHA256: 4c5c1bd0216caea80be7ec8a16d0a1f375abd75ad278ac73692983543f3a4268
  • Pointer size: 131 Bytes
  • Size of remote file: 239 kB
media/automatum_logo.png ADDED
media/automatum_reel.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5e47bc58a5099794fa82972d9d78f5d14f3670d9b5b381fbac4e536b7d4c37
3
+ size 3445013
media/automatum_reel_poster.jpg ADDED

Git LFS Details

  • SHA256: 2a58d15ce8af1f0a46a1502acc77126fb0e9dee3c0f91206d90406e0a25ae599
  • Pointer size: 131 Bytes
  • Size of remote file: 131 kB
media/crossing_hero.jpg ADDED

Git LFS Details

  • SHA256: a4bd176656b5205f7e9ab51c60535734fade58c220d376ed4ee25abd78adabbf
  • Pointer size: 131 Bytes
  • Size of remote file: 154 kB
media/full_highway_hero.jpg ADDED

Git LFS Details

  • SHA256: 6d37e1f44d1076e77eeeba7d468e79f1ecd42996d391bf5a7d8f79847bcc2225
  • Pointer size: 131 Bytes
  • Size of remote file: 177 kB
media/highway_with_ramps_hero.jpg ADDED

Git LFS Details

  • SHA256: a7cc8760c2d42773d978e6a631851a25c7007053b55182c3f4b39350c5bbc1db
  • Pointer size: 131 Bytes
  • Size of remote file: 171 kB
media/roundabout_hero.jpg ADDED

Git LFS Details

  • SHA256: 4a13e84fe00536cdad39ac5827da9258a01d39eee94a12106445c8f5cea8780b
  • Pointer size: 131 Bytes
  • Size of remote file: 178 kB