Citywide traffic sensor network in Nova Gorica, Slovenia : 2025-2026 telraam S2 dataset

Berčič, Tomaž (author), Stavrev, Marko (author)

This article describes a multimodal traffic dataset collected through a network of 26 Telraam S2 sensors deployed across Nova Gorica, Slovenia, within the framework of the Interreg Central Europe EnCLOD project. The network comprises 23 indoor window-mounted units and 3 experimental outdoor units, installed along arterial corridors, residential connectors, and sections of the city's ring road. Each Telraam S2 device is a low-cost, citizen-science-oriented Internet of Things (IoT) traffic counter equipped with a Kendryte K210 edge AI chip that performs real-time object detection and classification directly on-device, transmitting only anonymized, aggregated counts via a built-in cellular connection (LTE-M/NB-IoT). The dataset contains 15-minute interval time-series records for each sensor location. Each record includes directional counts for pedestrians, bicycles, motorcycles, cars, light trucks, trucks, buses, trailers, tractors, and strollers, as well as a consolidated night-time detection category. Derived metrics include car speed distribution histograms in 10 km/h bins and the V85 (85th percentile) speed per interval. Accompanying metadata provide sensor coordinates, street names, segment identifiers, installation type, and uptime quality indicators. No images or video are stored or transmitted by the devices; all processing occurs on board, ensuring compliance with privacy regulations. The data were exported from the Telraam dashboard and are archived as structured Excel (.xlsx) files, with CSV mirrors, on Zenodo under a CC BY-NC 4.0 license. This is the first fine-grained, multi-modal urban traffic dataset for Nova Gorica, a city that previously lacked systematic traffic monitoring infrastructure. The dataset is suitable for reuse in transport modelling, modal share analysis, speed behaviour assessment, air-quality exposure linkage, and urban mobility planning, and may serve as a reference for replicating low-cost distributed sensor deployments in comparable European cities.

• Language: English
• Keywords: traffic, cars, pedestrians, bicycles, large vehicles, vehicles, sensors, datasets, enCLOD, citizen science, open data
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FA - Faculty of Architecture
• Publication status: Published
• Publication version: Version of Record
• Publication date: 25.08.2026
• Year: 2026
• Number of pages: 20 str.
• Numbering: Vol. 68, [article no.] 113190
• PID: 20.500.12556/RUL-186919
• UDC: 004.91
• ISSN on article: 2352-3409
• DOI: 10.1016/j.dib.2026.113190
• COBISS.SI-ID: 289132547
• Publication date in RUL: 07.09.2026

Record is a part of a journal

• Title: Data in brief
• Publisher: Elsevier
• ISSN: 2352-3409
• COBISS.SI-ID: 32117977

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: promet, avtomobili, pešci, kolesa, tovorna vozila, vozila, senzorji, podatkovne zbirke, občanska znanost, odprti podatki, Nova Gorica

Projects

• Funder: Other - Other funder or multiple funders
• Project number: CE0200649
• Name: EnCLOD – Enhancing Governance Capacities of Local Authorities using Open Data

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P5-0068-2018
• Name: Trajnostno oblikovanje kvalitetnega bivalnega okolja