The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Presenting the Multi-view Traffic Intersection Dataset (MTID): A Detailed Traffic-Surveillance Dataset
Open accessAbstract
This work presents a novel and unique traffic surveillance dataset, the MTID. When capturing data for traffic surveillance, the positioning of the camera is crucial, and depending on the task different approaches provide different advantages. Multiple viewpoints, however, are rarely compared. Our dataset gives the ability to analyze the difference between two viewpoints in great detail. A complex traffic scene has been captured simultaneously from two different viewpoints: that of a camera mounted on existing infrastructure, and an that of a drone. The frames from each video capture have been synchronized in time and all road users have been carefully annotated down to pixel-level accuracy. The dataset consists of 3100 frames from each viewpoint, containing 18883 individual annotations on the pole viewpoint, and 50274 individual annotations on the drone viewpoint. The dataset is freely available online*. Apart from the dataset, which is our main contribution, we also provide benchmark detection results for four different groups of road users for other researchers to compare their results with. We show that the detection problem is challenging, as we achieve mAPs of only 22.62% and 27.75% using a pre-trained state-of-the-art detector on the two viewpoints.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In [42], an aerial dataset of a road scene was produced using two different points of view: a static camera and a drone; each video consists of 3100 frames.
“Furthermore, in [42], an aerial dataset of a road scene is produced using two different points of view: a static camera and a drone; each video consist of 3100 frames, and the two acquisitions are used to investigate the differences between the two viewpoints.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [42]
In [42], four object categories were labeled at the pixel level.
“Four object categories have been labeled at the pixel level in this dataset.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [42]
The VisDrone and MTID datasets include different types of commercial vehicles and present differences in labeling, even for similar types of object classes.
“Besides including different types of commercial vehicles, they also present differences in labeling, even for similar types of object classes.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [42]
Type and shape of vehicles are different with respect to world region and location.
“In addition, type and shape of vehicles are different with respect to world region and location.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [42]
The VisDrone dataset is captured in the streets of China, while the MTID dataset covers traffic in the European region.
“For example, data in VisDrone dataset is captured in the streets of China, on the contrary, the MTID dataset [42] covers the traffic in European region.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [42]
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Flagged first, then by citations
Research works printed but not linked: 16
- 10.1109/ITSC.2018.8569552 · DOI
- lin, 2014, Microsoft COCO: common objects in context, CoRR, abs 1405 312
- liu, 2016, Ssd Single shot multibox detector, 21
- 10.1109/TITS.2012.2209421 · DOI
- 10.1109/CVPR.2011.5995586 · DOI
- redmon, 2016, YOLO9000: better, faster, stronger, CoRR, abs 1612 8242
- 10.1007/s11263-015-0816-y · DOI · Paper page
- 10.1109/CVPR.2001.990517 · DOI · Paper page
- 10.1109/ICRA40945.2020.9196845 · DOI
- 10.1177/0278364913491297 · DOI · Paper page
- 10.1007/s11263-014-0733-5 · DOI · Paper page
- 10.1109/TITS.2015.2509509 · DOI
- 10.1109/ICCV.2017.322 · DOI · Paper page
- bonetto, 2015, Privacy in mini-drone based video surveillance, 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 4, 1
- 10.1109/TITS.2018.2872502 · DOI
- 10.4236/jtts.2018.84021 · DOI
Cited by
Sorted by citations
A Systematic Review of Drone Based Road Traffic Monitoring System
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2022) · IEEE Access · doi:10.1109/access.2022.3207282 · Cited by 139
Metadata
- Authors
- Jensen, M. B., Mogelmose, A., & Moeslund, T. B.
- Affiliations
- Aalborg University (DK)
- ORCID
- Moeslund, Thomas B.
- Venue
- 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
- Publisher
- IEEE
- Published
- 2020-09-20
- Pages
- 1-6
- OpenAlex
- W3116716570
- Cited by
- 14
- References
- 1
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 3 · 2022: 1 · 2021: 2
- FWCI
- 0.46
- Type
- conference paper
- Language
- en
- Open access
- green
- vbn.aau.dk
- Licence
- Locations
- IEEE International Conference on Intelligent Transportation Systems (ITSC) (publishedVersion)
- VBN Forskningsportal (Aalborg Universitet) (submittedVersion, other-oa)
- Funders
- European Commission (635895, HORIZON2020)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- traffic monitoring, traffic intersections, multi-view cameras, drone camera, road user detection, pixel-level annotation, video synchronization, object detection benchmark, traffic scene understanding
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
