Overview

The Traffic System Dataset provides a collection of key metrics for analyzing and optimizing traffic flow patterns across multiple lanes and intersections. It can be used for predictive modeling, congestion analysis, and intelligent traffic control system design. This dataset includes real-time measurements such as vehicle counts, average speed, lane occupancy, and waiting time, making it ideal for researchers, data scientists, and urban mobility engineers working on smart city and transportation analytics.

Context

Efficient traffic management is one of the most crucial challenges in modern urban planning. With the growth of smart cities, AI and data-driven solutions have become essential for monitoring traffic flow, predicting congestion, and reducing waiting times. This dataset captures multiple time-based and performance-related parameters of a traffic system, providing a foundation for: • Predictive traffic control systems • Vehicle flow optimization • Intelligent transportation system (ITS) modeling • Reinforcement learning applications in traffic light scheduling

Dataset Features

Feature Name Description vehicle_count Number of vehicles passing through a specific observation point during a given time interval. average_speed Mean speed (in km/h or mph) of all vehicles detected in the observation period. lane_occupancy Percentage of lane space occupied by vehicles, indicating traffic density. flow_rate Rate of vehicle flow per unit time (e.g., vehicles per minute). time_of_day Time label or categorical feature representing different traffic periods (e.g., morning peak, afternoon, evening). waiting_time Average waiting time (in seconds) for vehicles during signal cycles or congestion periods.

Deploy a powerful traffic monitoring model trained on a massive 880-image dataset for comprehensive urban surveillance. This project features a pre-trained computer vision model optimized to detect 10 distinct classes, including cars, buses, emergency vehicles, and pedestrians, providing the scale needed for advanced smart city infrastructure.

Ways to Use Traffic Detection Dataset

1. Traffic Flow Analysis: The dataset can be used in machine learning models to analyze traffic flow in cities. It can identify the type of vehicles on the city roads at different times of the day, helping in planning and traffic management.

2. Vehicle Class Based Toll Collection: Toll booths can use this model to automatically classify and charge vehicles based on their type, enabling a more efficient and automated system.

3. Parking Management System: Parking lot owners can use this model to easily classify vehicles as they enter for better space management. Knowing the vehicle type can help assign it to the most suitable parking spot.

4. Traffic Rule Enforcement: The dataset can be used to create a computer vision model to automatically detect any traffic violations like wrong lane driving by different vehicle types, and notify law enforcement agencies.

5. Smart Ambulance Tracking: The system can help in identifying and tracking ambulances and other emergency vehicles, enabling traffic management systems to provide priority routing during emergencies.

The Traffic-Net dataset, released in the version 1.0, contains 4,400 images of sparse traffic, dense traffic, accident, and fire. This dataset can be used for various computer vision tasks, including object detection, image classification, and segmentation.

The images in the dataset are of varying sizes and resolutions, and were collected from different sources, including Google Images, Bing Images, and Flickr. The dataset is divided into four classes, each with a distinct set of images and labels:

1. Sparse traffic: This class contains images of traffic signs and signals in low-traffic areas, such as rural roads and small towns.

2. Dense traffic: This class contains images of traffic signs and signals in high-traffic areas, such as urban roads and highways.

3. Accident: This class contains images of traffic accidents and related objects, such as damaged cars and emergency services.

4. Fire: This class contains images of fire-related objects, such as burning vehicles and buildings.

Researchers and developers can use the Traffic-Net dataset to train and evaluate their own models for traffic sign recognition and related tasks. The dataset can also be used to benchmark existing models and compare their performance on this specific dataset.

Here is the traffic dataset description in a single paragraph:

The Traffic Dataset provides comprehensive, real-world data on vehicle movement and road conditions collected from various urban and highway environments. It includes timestamped information such as vehicle counts, speeds, lane occupancy, congestion levels, and recorded traffic incidents, captured through traffic cameras, road sensors, and automated monitoring systems. This dataset is designed to support traffic pattern analysis, congestion prediction, transportation planning, and the development of intelligent transportation systems by offering detailed insights into how traffic behaves across different times of day, weather conditions, and roadway types.

Traffic Dataset - 500 Videos

Dataset comprises 500 videos of urban traffic captured by surveillance cameras, providing real-time traffic data enriched with bounding box annotations for vehicles and pedestrians. Designed for traffic monitoring and safety research, the dataset supports tasks like vehicle detection, traffic flow analysis, and accident prediction. By leveraging this dataset, researchers and engineers can advance real-time object detection, traffic surveillance… See the full description on the dataset page: https://huggingface.co/datasets/UniDataPro/real-time-traffic-video-dataset.

context : Worldwide traffic data shows how vehicles move on roads across different countries. It includes information about traffic flow, speed, and congestion. This data is used for traffic prediction, route planning, and smart city development. ** Feature Distribution** : 🚗 Traffic Volume: number of vehicles on road ⏱️ Time: date, hour, day (peak / off-peak) 🌍 Location: country, city, latitude, longitude 🚀 Speed: average speed, travel time 🚦 Condition: congestion level, accidents 🌦️ External Factors: weather, events

Here are a few use cases for this project:

1. Traffic Management Systems: This model can be utilized in traffic monitoring and control centers to gain insights about the types of vehicles on roads. By recognizing different vehicle classes, the authorities can manage congestion, prioritize vehicle types, and introduce effective traffic rules.

2. Smart Parking Solutions: The model can be employed to recognize vehicles entering parking lots. By identifying vehicle types, it can allocate suitable parking spots. For instance, a truck would require more space than a car.

3. Automated Toll Collection: By identifying the type of vehicle, it can provide differential toll rates. For example, a truck might be charged more than a minibus, depending on regional laws.

4. Traffic Study and Urban Planning: This model can act as an essential tool for doing traffic analysis, helping urban planners to design better and more efficient roadways according to the traffic composition.

5. Surveillance and Law Enforcement: The Traffic Detection model can assist in identifying potential traffic violations such as trucks or buses using lanes designated for smaller vehicles. It can enhance the capacity of law enforcement agencies to maintain road safety rules.

This data set contains internet traffic data captured by an Internet Service Provider (ISP) using Mikrotik SDN Controller and packet sniffer tools. The data set includes traffic from over 2000 customers who use Fibre to the Home (FTTH) and Gpon internet connections. The data was collected over a period of several months and contains all traffic in its original format with headers and packets.

The data set contains information on inbound and outbound traffic, including web browsing, email, file transfers, and more. The data set can be used for research in areas such as network security, traffic analysis, and machine learning.

**Data Collection Method: ** The data was captured using Mikrotik SDN Controller and packet sniffer tools. These tools capture traffic data by monitoring network traffic in real-time. The data set contains all traffic data in its original format, including headers and packets.

**Data Set Content: ** The data set is provided in a CSV format and includes the following fields:

1. Timestamp: The date and time the traffic was captured
2. Source IP Address: The IP address of the device that sent the traffic Destination IP Address: The IP address of the device that received the traffic Protocol: The network protocol used for the traffic (e.g. TCP, UDP) Source Port: The port used by the source device for the traffic Destination Port: The port used by the destination device for the traffic Packet Size: The size of the packet in bytes Payload: The payload data of the packet The data set contains a large volume of traffic data from over 2000 customers. The data is organized by timestamp and includes all traffic data in its original format, including headers and packets. The data set contains both inbound and outbound traffic, and covers various types of internet traffic, including web browsing, email, file transfers, and more. one of listed protocols: ipsec-ah - IPsec AH protocol *ipsec-esp - IPsec ESP protocol ddp - datagram delivery protocol egp - exterior gateway protocol ggp - gateway-gateway protocol gre - general routing encapsulation hmp - host monitoring protocol idpr-cmtp - idpr control message transport icmp - internet control message protocol icmpv6 - internet control message protocol v6 igmp - internet group management protocol ipencap - ip encapsulated in ip ipip - ip encapsulation encap - ip encapsulation iso-tp4 - iso transport protocol class 4 ospf - open shortest path first pup - parc universal packet protocol pim - protocol independent multicast rspf - radio shortest path first rdp - reliable datagram protocol st - st datagram mode tcp - transmission control protocol udp - user datagram protocol vmtp - versatile message transport vrrp - virtual router redundancy protocol xns-idp - xerox xns idp xtp - xpress transfer protocol

MAC Protocol Examples 802.2 - 802.2 Frames (0x0004) arp - Address Resolution Protocol (0x0806) homeplug-av - HomePlug AV MME (0x88E1) ip - Internet Protocol version 4 (0x0800) ipv6 - Internet Protocol Version 6 (0x86DD) ipx - Internetwork Packet Exchange (0x8137) lldp - Link Layer Discovery Protocol (0x88CC) loop-protect - Loop Protect Protocol (0x9003) mpls-multicast - MPLS multicast (0x8848) mpls-unicast - MPLS unicast (0x8847) packing-compr - Encapsulated packets with compressed IP packing (0x9001) packing-simple - Encapsulated packets with simple IP packing (0x9000) pppoe - PPPoE Session Stage (0x8864) pppoe-discovery - PPPoE Discovery Stage (0x8863) rarp - Reverse Address Resolution Protocol (0x8035) service-vlan - Provider Bridging (IEEE 802.1ad) & Shortest Path Bridging IEEE 802.1aq (0x88A8) vlan - VLAN-tagged frame (IEEE 802.1Q) and Shortest Path Bridging IEEE 802.1aq with NNI compatibility (0x8100)

**Data Usage: ** The data set can be used for research in areas such as network security, traffic analysis, and machine learning. Researchers can use the data to develop new algorithms for detecting and preventing cyber attacks, analyzing internet traffic patterns, and more.

**Data Availability: ** If you are interested in using this data set for research purposes, please contact us at asfandyar250@gmail.com for more information and references. The data set is available for download on Kaggle and can be accessed by researchers who have obtained permission from the ISP.

We hope this data set will be useful for researchers in the field of network security and traffic analysis. If you have any questions or need further information, please do not hesitate to contact us. https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F5985737%2F61c81ce9eb393f8fc7c15540c9819b95%2FData.PNG?generation=1683750473536727&alt=media" alt=""> You can use Wireshark or other software's to view files

Daily utilization metrics for data.lacity.org and geohub.lacity.org. Updated monthly

APOO Indian Traffic Dataset

Synthetic training data for the Adaptive Platoon Offset Optimizer (APOO) — a framework for Indian traffic signal coordination.

  Overview

5,000 synthetic samples calibrated for Indian heterogeneous traffic conditions, designed for training ML models that predict platoon travel time between signals.

  Features (20 input features)

Feature Description Range

link_length_m Distance between signals 150-600m

speed_limit_kmh Posted… See the full description on the dataset page: https://huggingface.co/datasets/omshrivastava/APOO-Indian-Traffic-Dataset.

The main aim of this dataset is to enable detection of traffic congestion from surveillance cameras using one-stage object detectors. The dataset contains congested and uncongested traffic scenes with their respective labels. This dataset is collected from different surveillance cameras video footage. To prepare the dataset frames are extracted from video sources and resized to a dimension of 500 x 500 with .jpg image format. To Annotate, the image LabelImg software has used. The format of the label is .txt with the same name as the image. The dataset is mainly prepared for YOLO Models but it can be converted to other models format.

This table provides the traffic studies in hourly bins and some statistics. The SDOT Traffic Counts group runs studies across the city to collect traffic volumes. Most studies are done with pneumatic tubes, but some come from video systems as well. Use the field study_id to match it with other tables for more information.

Network traffic datasets created by Single Flow Time Series Analysis

Datasets were created for the paper: Network Traffic Classification based on Single Flow Time Series Analysis -- Josef Koumar, Karel Hynek, Tomáš Čejka -- which was published at The 19th International Conference on Network and Service Management (CNSM) 2023. Please cite usage of our datasets as:

J. Koumar, K. Hynek and T. Čejka, "Network Traffic Classification Based on Single Flow Time Series Analysis," 2023 19th International Conference on Network and Service Management (CNSM), Niagara Falls, ON, Canada, 2023, pp. 1-7, doi: 10.23919/CNSM59352.2023.10327876.

This Zenodo repository contains 23 datasets created from 15 well-known published datasets which are cited in the table below. Each dataset contains 69 features created by Time Series Analysis of Single Flow Time Series. The detailed description of features from datasets is in the file: feature_description.pdf

In the following table is a description of each dataset file:

Yolov8 Traffic

## Overview

Yolov8 Traffic is a dataset for object detection tasks - it contains Car Truck Bus Motobike Bike annotations for 1,502 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [Public Domain license](https://creativecommons.org/licenses/Public Domain).

This table provides traffic studies in 15 minutes bins and some statistics. The SDOT Traffic Counts group runs studies across the city to collect traffic volumes. Most studies are done with pneumatic tubes, but some come from video systems as well. Use the field study_id to match it with other tables for more information.

The task for this dataset is to forecast the spatio-temporal traffic volume based on the historical traffic volume and other features in neighboring locations.

Subject Area: Computer Science

Associated Tasks: Regression

Instances: 2101

Dataset Information

For what purpose was the dataset created? To share the research community with a benchmark dataset for spatiotemporal prediction

Who funded the creation of the dataset? National Science Foundation

What do the instances in this dataset represent? traffic surveillance signals

Was there any data preprocessing performed? The task for this dataset is to forecast the spatio-temporal traffic volume based on the historical traffic volume and other features in neighboring locations. Specifically, the traffic volume is measured every 15 minutes at 36 sensor locations along two major highways in Northern Virginia/Washington D.C. capital region. The 47 features include: 1) the historical sequence of traffic volume sensed during the 10 most recent sample points (10 features), 2) week day (7 features), 3) hour of day (24 features), 4) road direction (4 features), 5) number of lanes (1 feature), and 6) name of the road (1 feature). The goal is to predict the traffic volume 15 minutes into the future for all sensor locations. With a given road network, we know the spatial connectivity between sensor locations. For the detailed data information, please refer to the file README.docx

Additional Information Attribute information: The 47 attributes include: (1) the historical sequence of traffic volume sensed during the 10 most recent sample points (10 features), (2) week day (7 features), (3) hour of day (24 features), (4) road direction (4 features), (5) number of lanes (1 feature), and (6) name of the road (1 feature).

Has Missing Values? No

Introductory Paper

Title: Spatial Auto-regressive Dependency Interpretable Learning Based on Spatial Topological Constraints

Authors: Liang Zhao, Olga Gkountouna, D. Pfoser. 2019

Journal: Published in ACM Trans. Spatial Algorithms Syst.

Abstract of Introductory Paper

Spatial regression models are widely used in numerous areas, including detecting and predicting traffic volume, air pollution, and housing prices. Unlike conventional regression models, which commonly assume independent and identical distributions among observations, existing spatial regression requires the prior knowledge of spatial dependency among the observations in different spatial locations. Such a spatial dependency is typically predefined by domain experts or heuristics. However, without sufficient consideration on the context of the specific prediction task, it is prohibitively difficult for one to pre-define the numerical values of the spatial dependency without bias. More importantly, in many situations, the existing techniques are insufficient to sense the complete connectivity and topological patterns among spatial locations (e.g., in underground water networks and human brain networks). Until now, these issues have been extremely difficult to address and little attention has been paid to the automatic optimization of spatial dependency in relation to a prediction task, due to three challenges: (1) necessity and complexity of modeling the spatial topological constraints; (2) incomplete prior spatial knowledge; and (3) difficulty in optimizing under spatial topological constraints that are usually discrete or nonconvex. To address these challenges, this article proposes a novel convex framework that automatically jointly learns the prediction mapping and spatial dependency based on spatial topological constraints. There are two different scenarios to be addressed. First, when the prior knowledge on existence of conditional independence among spatial locations is known (e.g., via spatial contiguity), we propose the first model named Spatial-Autoregressive Dependency Learning I (SADL-I) to further quantify such spatial dependency. However, when the knowledge on the conditional independence is unknown or incomplete, our second model named Spatial-Autoregressive Dependency Learning II (SADL-II) is proposed to automatically learn the conditional independence pattern as well as quantify the numerical values of the spatial dependency based on spatial topological constraints. Topological constraints are usually discrete and nonconvex, which makes them extremely difficult to be optimized together with continuous optimization problems of spatial regression. To address this, we propose a convex and continuous equivalence of the original discrete topological constraints with a theoretical guarantee. The proposed models are then transferred to convex problems that can be iteratively optimized by our new efficient algorithms until convergence to a global optimal solution. Extensive experimentation using sever...

Annual Average Daily Traffic (AADT) is an estimate of the average daily traffic along a defined segment of roadway. This value is calculated from short term counts taken along the same section which are then factored to produce the estimate of AADT. Because of this process, the most recent AADT for any given roadway will always be for the previous year. Data is available for all New York State Routes and roads that are part of the Federal Aid System.

Here are a few use cases for this project:

1. Smart Traffic Management: The "traffic" computer vision model can be used in intelligent traffic management to detect and categorize various traffic participants. It would help in real-time traffic control by adjusting traffic light patterns based on the density and types of vehicles on the road.

2. Autonomous Vehicles Navigation: Self-driving cars or drones could benefit from this model by identifying and classifying different elements in their path such as other cars, people, buses, 2-wheelers, etc. This would enhance their ability for safe and efficient navigation.

3. Pedestrian Safety: This model can be utilized in pedestrians' mobile applications to alert them about incoming vehicles such as trucks, vans, autos, buses, or 2-wheelers while they are crossing the road or walking on the pavement.

4. Security Surveillance Systems: In commercial or residential zones, the model could assist in accurately identifying and logging vehicle types or detecting anomalies like a person in a vehicle-restricted area, potentially enhancing security measures.

5. Retail & Marketing Research: Stores selling vehicle-related products or services might use this model to monitor the types of vehicles in their parking lots as a form of market research. This data could help them tailor their products, services, or marketing strategies accordingly.

Traffic data from traffic detectors installed on strategic routes / major roads including traffic volume, traffic speed and road occupancy (Raw Data). Traffic speeds from traffic detectors installed on strategic routes / major roads mapped onto the respective road network segments (Processed Data).