ListDB RepTwo: 3 months (Jun'22-Aug'22) of drone videos and trajectories at a 4-way intersection
Subtitle: Dresden (Germany): Kohlenstrasse / Dorfhainer Strasse
Metadata
Additional title | Subtitle: Dresden (Germany): Kohlenstrasse / Dorfhainer Strasse | |
Person(s) who is (are) responsible for the content of the research data | Bäumler, Maximilian - Technische Universität Dresden (ORCID: 0000-0003-4052-0572) | |
Person(s) who is (are) responsible for the content of the research data | Lehmann, Matthias - Technische Universität Dresden (ORCID: 0000-0002-6407-3028) | |
Used research instruments or devices | DJI Mini 2 | |
Research objects | Other: Traffic observation videos of an intersection | |
Abstract | The dataset can be used to investigate road traffic and derive test scenarios for scenario-based testing, for example. The dataset includes three months of drone videos and their corresponding trajectories recorded in Dresden, Germany, at a 4-way intersection. The data collection followed a fixed sampling plan covering four different time slots daily (weekdays: 07.30-09.00 / 10.00-11.30 / 13.00-14.30 / 15.30-17.00) within June and August 2022. Moreover, extensive metadata is provided following the ListDB specification (w3id.org/listdb). Source trajectory data was extracted from video using DataFromSky TrafficSurvey (https://ai.datafromsky.com/aerial) - an AI video analytics-based service for gathering advanced traffic data for researchers and traffic engineers. Main facts: 855 minutes of video (June: 285 minutes / July: 285 minutes / August: 285 minutes). The analysed trajectories are available for each video. We sincerely thank DataFromSky for supporting the analysis. The video-based traffic observation was conducted within the MOTUS project (19FS2015A; motus-project.com) and supported by the mFUND grant by Germany’s Federal Ministry for Digital and Transport. | |
Applied methods and techniques | The videos were collected using consumer drones. The metadata was collected using the ListDBApp (see .apk). The source trajectory data was extracted from video using DataFromSky TrafficSurvey (https://ai.datafromsky.com/aerial) - an AI video analytics-based service for gathering advanced traffic data for researchers and traffic engineers. | |
Table of contents | - Sample video data - Sample trajectory data - Video data - Trajectory data - ListDBApp to collect metadata - ListDB codebook to specify the metadata | |
Counties, the data is referencing | GERMANY | de |
Coordinates of places, the data is referencing | 51.018819, 13.718199 | |
Regions the data is referencing | Saxony | |
Additional keywords | drone | |
Additional keywords | uav | |
Additional keywords | traffic observation | |
Additional keywords | trajectories | |
Additional keywords | Data From Sky | |
Additional keywords | video analysis | |
Additional keywords | object detection | |
Additional keywords | traffic scenario | |
Additional keywords | autonomous driving | |
Language | eng | |
Year or period of data production | 2022-2023 | |
Publication year | 2023 | |
Publisher | Technische Universität Dresden | |
References on related materials | IsPartOf: 123456789/5882 (Handle) | |
References on related materials | IsPartOf: https://w3id.org/listdb/onto (URL) | |
References on related materials | IsDocumentedBy: https://index.mirasmart.com/27esv/PDFfiles/27ESV-000122.pdf (URL) | |
Content of the research data | Text, Audiovisual, Dataset, Software: Video: Videos containing traffic observation (.mp4) Dataset: Minded trajectories (.csv; .tlgx) Software: ListDBApp to collect metadata (.apk) Text: Text files containing metadata (.txt; .csv) Text: Codebook specifying the metadata (.pdf) | |
Holder of usage rights | Technische Universität Dresden | |
Usage rights of the data | CC-BY-NC-4.0 | |
Software | Resource Production: ListDBApp (Android; self-developed) | |
Software | Resource Processing: Data From Sky Traffic Survey | |
Discipline(s) | Engineering | de |
Title of the dataset | ListDB RepTwo: 3 months (Jun'22-Aug'22) of drone videos and trajectories at a 4-way intersection |
Files in this item
This item appears in the following Collection(s)
-
ListDB: Representative datasets of video-based traffic observations [3]
Representative datasets of video-based traffic observations according to the ListDB specification (w3id.org/listdb/). We collected the videos mainly at different intersections in Germany following a fixed sampling plan to ensure representativity. We describe the sampling plan and the collection procedure in the following paper: Maximilian Bäumler, Matthias Lehmann, Günther Prokop (2023). "Generating representative test scenarios: The "Fuse for Representativity" (FUSE4Rep) process model to collect and analyse traffic observation data". In: 27th ESV Conference. Yokohama. Paper NO.23-0122-O The paper is available here: https://index.mirasmart.com/27esv/PDFfiles/27ESV-000122.pdf