---
title: "Road Traffic in Serbia, Videos and Images Dataset"
description: "This Serbian road traffic dataset contains 5,000 high-resolution (≥1080p) videos and annotated frame images with JSON bounding box annotations for vehicle detection and classification tasks.…"
url: "https://unidata.pro/datasets/road-traffic-in-serbia-videos-and-images/"
date_modified: "2025-12-01T14:03:55+03:00"
language: "en-US"
---
This Serbian road traffic dataset contains 5,000 high-resolution (≥1080p) videos and annotated frame images with JSON bounding box annotations for vehicle detection and classification tasks. Collected from bridge vantage points, it provides detailed data on traffic flows, vehicle types (cars and minivans), and traffic density, supporting AI development for traffic prediction, road safety analysis, and computer vision model training.

## Dataset Structure

### The Numbers Section

**Numbered list:** - **Number:** 5,000 — **Text:** Video

### Tooltips Section

**Tooltip items:**

- **Name:** Auto
- **Name:** Detection
- **Name:** Data annotation
- **Name:** Machine Learning
- **Name:** Computer Vision

### Dataset Information

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Description | Vehicles videos with labeling for detection tasks |
| Data types | Video, image |
| Tasks | Detection, Classification |
| Total number of files | 5 000 |
| Marking | Bounding Box |
| Type of vehicles | Light vehicles (cars) and heavy vehicles (minivan) |

**Media Slider:**

- **Image in the slider:** ![](https://unidata.pro/wp-content/uploads/2025/11/serbia-road-traffic-example2.webp)
- **Image in the slider:** ![](https://unidata.pro/wp-content/uploads/2025/11/serbia-road-traffic-example1.webp)

**Link to the sample:** [Download sample](https://drive.google.com/drive/folders/1n6j0WWHm1h-P8XtCK6HYZkvimxEKI3KE?usp=sharing)

### Technical Specifications

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Video Extension | MOV |
| Image Extension | JPG |
| Video Resolutions | ≥ 1920 × 1080 px |
| Extension of labeling file | JSON |

**Source and data collection methodology:** Source and collection methodology: Data was collected by a smartphone from bridge vantage points and annotated by an assessor.

### Dataset Use Cases - Slider

**Industry Cards:**

- **Industry:** Urban Development — **Title:** Modeling Traffic Flows for Smarter City Planning — **Text:** This road traffic dataset can help urban planners analyze real traffic flows and congestion trends across major roads and intersections. Using detailed video data of vehicle types, speeds, and road conditions, cities can optimize road networks, manage daily traffic, and plan future infrastructure with precision.
- **Industry:** Transportation Engineering — **Title:** Enhancing Road Safety and Network Efficiency — **Text:** Engineers can use this traffic dataset to study road conditions, traffic volumes, and vehicle movements under different scenarios. The dataset supports safety analysis, helping identify accident-prone areas and improve road segments. It also enables the simulation of traffic patterns for designing efficient, safer, and more sustainable transportation systems.
- **Industry:** AI and Computer Vision Research — **Title:** Advancing Traffic Video Analysis and Prediction — **Text:** Researchers can use road traffic datasets to develop and train deep learning models for traffic video analysis and traffic prediction. With diverse scenes from highways and city roads, it supports applications such as vehicle detection, speed estimation, and congestion forecasting, contributing to smarter, AI-driven traffic management solutions.
- **Industry:** Public Sector and Policy Making — **Title:** Supporting Data-Driven Transport Planning — **Text:** Government agencies can rely on this dataset to monitor traffic density, estimate travel times, and evaluate road network performance. The visual data enables evidence-based planning for public transport optimization, emission reduction policies, and long-term infrastructure investment, improving mobility and road safety across Serbia’s arterial roads.

### Fact

**FAQs Heading:** FAQ

**List of Questions:**

- **Question:** Can I request a sample of the dataset before purchasing or downloading it? — **Answer:** Yes, Unidata provides free sample files for testing and evaluation. These samples allow you to verify video and image quality, annotation accuracy, and data structure before purchasing the full road traffic dataset.
- **Question:** Is it possible to request a custom dataset? — **Answer:** Yes. You can request a custom dataset tailored to your needs, including specific road types, vehicle categories, or traffic conditions. Our data team can collect or annotate videos to match your research or model training requirements.
- **Question:** How was the data collected? — **Answer:** Data was collected through video recordings of major and arterial roads across Serbia using high-resolution cameras. The data collection process followed consistent protocols to capture traffic flows, vehicle speeds, and road conditions representative of real-world traffic patterns.
- **Question:** How are Unidata datasets licensed? — **Answer:** Unidata datasets follow a dual-licensing model: free samples are available for trial and testing, while full datasets can be purchased for full access. This ensures flexibility for both academic research and commercial applications.
- **Question:** How are Unidata datasets stored? — **Answer:** All datasets are securely hosted on AWS cloud infrastructure, ensuring high availability, scalability, and data integrity. Unidata’s storage framework aligns with ISO 27001 and ISO 27701 standards, providing a privacy-focused and reliable environment for managing large traffic datasets.
- **Question:** How long does it take to receive the dataset? — **Answer:** After submitting a request, Unidata will contact you to finalize documentation and payment. Road Traffic in Serbia Dataset will be delivered within 3 to 10 days, depending on the dataset size and licensing terms.
- **Question:** Is this a real-world dataset or synthetic data? — **Answer:** Road Traffic in Serbia, Videos and Images Dataset is entirely real-world data collected from actual traffic environments. Unlike synthetic datasets, it captures authentic traffic volumes, road networks, and vehicle movements.
- **Question:** Why are bridge-view traffic recordings useful for AI training? — **Answer:** Elevated traffic views provide a broader perspective of road activity, allowing models to analyze vehicle movement, density, and interactions between different road users. This type of data is valuable for developing accurate traffic analysis and prediction systems.
- **Question:** How do annotated traffic images improve vehicle detection accuracy? — **Answer:** Annotated traffic images provide clear examples of vehicle locations and categories, helping machine learning models learn how to identify objects in complex road environments.

[Full list of this site's AI-readable pages](https://unidata.pro/llms.txt)