A dataset for audio-video based vehicle speed estimation

VS13 dataset

The VS13 dataset contains video recordings of 13 vehicles (Citroen C4 Picasso, Kia Sportage, Mazda 3 Skyactive, Mercedes AMG 550, Mercedes GLA 200D, Nissan Qashqai, Opel Insignia, Peugeot 208, Peugeot 3008, Peugeot 307, Renault Captur, Renault Scenic and VW Passat B7) passing by the camera at a known constant speed. Specification of vehicles (engine type, power, transmission type and production year) is given in Table 1 in the paper. The dataset comprises 400 video recordings (MP4 format, full HD resolution, 30 fps, 10-second length), each containing a single drive of a single vehicle. The speed of vehicles ranges from 30 to 105 km/h (exact values given in Table 1 in the paper). The speed is maintained stable by the on-board cruise control, all vehicles were equipped with.

Annotation text files contain the speed of a vehicle and its pass-by-camera instant. Relative time from the beginning of the file, given in seconds with a two-decimal precision, was measured. Precise annotations were obtained by visual screening, i.e., by identifying a video frame when a vehicle starts to exit the camera view, which approximately corresponds to the closest point of approach.

For dataset recording, we used a GoPro Hero5 Session camera. It was installed by the road, at a distance of around 0.5 m from the road and at a height of around 1.2 m. The camera was installed in various positions (both sides of the road and different angles of the camera with respect to the road) in order not to be sensitive to the actual camera position.

The VS13 dataset can be downloaded from two separate folders: Video + annotations and Audio + annotations, given below. It is suitable for both video- and audio-based vehicle speed estimation.

Citroen C4 Picasso (80 km/h)

Kia Sportage (72 km/h)

Mazda 3 (86 km/h)

Mercedes AMG (78 km/h)

Mercedes GLA (88 km/h)

Nissan Qashqai (82 km/h)

Opel Insignia (70 km/h)

Peugeot 208 (79 km/h)

Peugeot 3008 (83 km/h)

Peugeot 307 (82 km/h)

Renault Captur (66 km/h)

Renault Scenic (80 km/h)

VW Passat (85 km/h)

Sample video files of each vehicle. The dataset was recorded on a local road, 622 m long, located 90 m away from the main road Podgorica-Petrovac in Montenegro.

Video + annotations Show dataset

Audio + annotations Show dataset

Paper abstract:

Accurate speed estimation of road vehicles is important for several reasons. One is speed limit enforcement, which represents a crucial tool in decreasing traffic accidents and fatalities. Compared with other research areas and domains, the number of available datasets for vehicle speed estimation is still very limited. We present a dataset of on-road audio-video recordings of single vehicles passing by a camera at known speeds, maintained stable by the on-board cruise control. The dataset contains thirteen vehicles, selected to be as diverse as possible in terms of manufacturer, production year, engine type, power and transmission, resulting in a total of 400 annotated audio-video recordings. The dataset is fully available and intended as a public benchmark to facilitate research in audio-video vehicle speed estimation. In addition to the dataset, we propose a cross-validation strategy which can be used in a machine learning model for vehicle speed estimation. Two approaches to training-validation split of the dataset are proposed.

You can download the paper here.

Publication

In case you use this dataset in your research, please cite the following paper:

@inproceedings{djukanovic2022dataset,
author = "Slobodan Djukanovi\'{c} and Nikola Bulatovi\'{c} and Ivana \v{C}avor",
title = "A dataset for audio-video based vehicle speed estimation",
booktitle = "2022 30th Telecommunications Forum (TELFOR)",
year = "2022",
pages = "1-4"
}

Related papers

  1. I. Čavor, and S. Djukanović, "Vehicle Speed Estimation From Audio Signals Using 1D Convolutional Neural Networks," Information Technology - IT 2023, 15-18 February 2023, Žabljak, Montenegro.
  2. A. Cvijetić, S. Djukanović, and A. Peruničić, "Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN," Information Technology - IT 2023, 15-18 February 2023, Žabljak, Montenegro.
  3. A. Peruničić, S. Djukanović, and A. Cvijetić, "Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN," Information Technology - IT 2023, 15-18 February 2023, Žabljak, Montenegro.

Contact

For all inquiries and questions regarding the paper and the dataset, contact Slobodan Djukanović.

IEEE Copyright Notice