Context

Driver behavior is one of the most important aspects in the design, development, and application of Advanced Driving Assistance Systems (ADAS) and Intelligent Transportation Systems (ITS), which can be affected by many factors. If you are able to measure the driving style of your staff, there is a lot of actions you can take in order to improve fleet safety, global road safety as well as fuel efficiency and emissions.

Content

• Dataset for modeling risky driver behaviors based on accelerometer (X,Y,Z axis in meters per second squared (m/s2)) and gyroscope (X,Y, Z axis in degrees per second (°/s) ) data.
• Sampling Rate: Average 2 samples (rows) per second
• Cars: Ford Fiesta 1.4, Ford Fiesta 1.25, Hyundai i20
• Drivers: 3 different drivers with the ages of 27, 28 and 37
• Driver Behaviors: 1.Sudden Acceleration (Class Label: 1) 2.Sudden Right Turn (Class Label: 2) 3.Sudden Left Turn (Class Label: 3) 4.Sudden Break (Class Label: 4)
• Best Window Size: 14 seconds
• Sensor: MPU6050
• Device: Raspberry Pi 3 Model B

Acknowledgements

Yuksel, Asim; Atmaca, Şerafettin (2020), “Driving Behavior Dataset”, Mendeley Data, V2, doi: 10.17632/jj3tw8kj6h.2

Data set is available in below link- Click here

Dataset for modeling risky driver behaviors based on accelerometer (X,Y,Z axis in meters per second squared (m/s2)) and gyroscope (X,Y, Z axis in degrees per second (°/s) ) data. Sampling Rate: Average 2 samples (rows) per second Cars: Ford Fiesta 1.4, Ford Fiesta 1.25, Hyundai i20 Drivers: 3 different drivers with the ages of 27, 28 and 37 Driver Behaviors: Sudden Acceleration (Class Label: 1), Sudden Right Turn (Class Label: 2), Sudden Left Turn (Class Label: 3), Sudden Break (Class Label: 4) Best Window Size: 14 seconds Sensor: MPU6050 Device: Raspberry Pi 3 Model B Please See Summary Table for summary of the collected data.

air pollution

[y_axis]

Driving behavior plays a vital role in maintaining safe and sustainable transport, and specifically, in the area of traffic management and control, driving behavior is of great importance since specific driving behaviors are significantly related with traffic congestion levels. Beyond that, it affects fuel consumption, air pollution, public health as well as personal mental health and psychology. Use of Smartphone sensors for data acquisition has emerged as a means to understand and model driving behavior. Our aim is to analyze driving behavior using on Smartphone sensors’ data streams. We present Smartphone sensor (Accelerometer, Gyroscope, Proximity, etc.) data recorded in live traffic while driver was executing the driving events. The datasets folder include .csv files of sensor data like Accelerometer, Gyroscope, etc. This data was recorded in live traffic while driver was executing certain driving events. The travel time for each one way trip was approximately 5kms - 20kms. The smartphone position was fixed horizontally in the vehicles utility box. Vehicle type used for data recording was LMV.

Driver activity dataset

Dataset consists of 2,400+ images capturing the driving behaviors of 304 individuals through the use of RGB and infrared cameras. This extensive dataset is specifically designed for behavior analysis and driver monitoring, focusing on various driving scenarios and environments to enhance traffic and road safety. By utilizing this dataset, researchers and developers can advance their understanding and capabilities in recognition tasks such as driver behavior… See the full description on the dataset page: https://huggingface.co/datasets/UniDataPro/driver-behaviour-dataset.

Driver dataset - 2 400+ Image

Dataset comprises 2,400+ images of 304 people capturing diverse driving behaviors, monitored by RGB and infrared cameras. It is designed for research in behavior monitoring, improving driver safety, and reducing risky driving incidents and reducing risky driving incidents, analyzing aggressive driving, distracted driving, and other unsafe behaviors to develop solutions for safer driving practices. - Get the data

  Dataset characteristics:… See the full description on the dataset page: https://huggingface.co/datasets/ud-smart-city/Driving-Behavior-Dataset.

Driving Behavior

## Overview

Driving Behavior is a dataset for object detection tasks - it contains Driving Behavior annotations for 9,890 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).

Distracted driving-related accidents are a critical global issue, especially as road traffic increases in densely populated areas. To address the challenge of driver distraction, we introduce a novel dataset that supports the development of real-time monitoring and detection systems by capturing authentic driver behaviors. Collected in Ashulia, Dhaka, Bangladesh, in October 2024, this dataset includes images captured under real-world driving conditions within both private vehicles and public buses. The photos were taken using personal mobile phones, ensuring a realistic and diverse set of visual data. This dataset spans a wide range of driving behaviors, including safe driving, turning, texting, talking on the phone, and other potentially risky behaviors, such as drowsy driving. By depicting these behaviors in everyday driving scenarios, the dataset serves as a valuable resource for training and evaluating models designed to detect unsafe driving practices in real-time.The dataset includes high-resolution photos taken inside public buses and personal cars in Ashulia, Dhaka, Bangladesh, under actual driving circumstances. The photographs, which were taken using the cameras on personal cell phones, offer a genuine and varied collection of visual information under normal driving circumstances. The following five behavioral classes comprise the dataset: I. Safe Driving: Images showing a driver who seems to be paying attention to the road, both hands on the wheel, and concentrated or 1 hand on the steering wheel and other on the gear stick. This is the perfect example of driving without distractions. II. Turning: Photographs that show drivers changing direction during turns by moving their heads or full bodies. This behavior is crucial for figuring out how focused the driver is on everyday tasks like rotating the steering wheel. III. Texting Phone: Pictures of drivers using their phones, whether it is to type messages or to interact with the screen. Since texting and driving is one of the main causes of distracted driving, this training is very important for identifying it. IV. Talking Phones: When drivers talk on their phones or hold them up to their ears while driving a vehicle. This category aids in identifying actions connected to phone talks, which are another frequent source of interruptions. V. Others: Contains any actions that go against safe driving practices, like drinking water or anything while driving, sleeping while driving, or talking with someone behind while driving. Relevant photos are included in each session, and they differ in terms of vehicle type and illumination to represent the variety of driving situations found in the real world. Because the images are unprocessed and unannotated, there is freedom in how machine learning

In source data folder, we provide the source data of figures in manuscript. In Supplementary Data folder, we provide the explanatory document about the dataset, along with some dataset segments of SIND dataset. In addition, we have provided a MATLAB version of the AD4CHE visualization program and a Python version of the SIND visualization program. The usage of the visualization program is attached in the respective folder. Recorded scenarios include the input and output data of the Field test. Original traffic law includes the original traffic laws and the subdivided version.

Sample Data: https://cloud.drivertechnologies.com/shared?s=146&t=4:03&token=0f469c88-d578-4b4f-80b2-f53f195683b2

At Driver Technologies, we are dedicated to harnessing advanced technology to gather anonymized critical driving data through our innovative dash cam app, which operates seamlessly on end users' smartphones. Our Speed Over Limit Driver Behavior Data offering is a key resource for understanding driver behavior and improving safety on the roads, making it an essential tool for various industries.

What Makes Our Data Unique? Our Speed Over Limit Driver Behavior Data is distinguished by its real-time collection capabilities, utilizing our built-in computer vision technology to identify and capture instances where a driver nearly gets into an accident. This data reflects critical safety events that are indicative of potential risks and non-compliance with traffic regulations. By providing data on these significant events, our dataset empowers clients to perform in-depth analysis.

How Is the Data Generally Sourced? Our data is sourced directly from users who utilize our dash cam app, which harnesses the smartphone’s camera and sensors to record during a trip. This direct sourcing method ensures that our data is unbiased and represents a wide variety of conditions and environments. The data is not only authentic and reflective of current road conditions but is also abundant in volume, offering millions of miles of recorded trips that cover diverse scenarios. For our Speed Over Limit Driver Behavior Data, we leverage computer vision models to read speed limit signs as the driver drives past them, then compare that to speed data captured using the phone's sensor.

Primary Use-Cases and Verticals Driver Behavior Analysis: Organizations can leverage our dataset to analyze driving habits and identify trends in driver behavior. This analysis can help in understanding patterns related to rule compliance and potential risk factors.

Training Computer Vision Models: Clients can utilize our annotated data to develop and refine their own computer vision models for applications in autonomous vehicles, ensuring better decision-making capabilities in complex driving environments.

Improving Risk Assessment: Insurers can utilize our dataset to refine their risk assessment models. By understanding the frequency and context of significant events, they can better evaluate driver risk profiles, leading to more accurate premium pricing and improved underwriting processes.

Integration with Our Broader Data Offering The Speed Over Limit Driver Behavior Data is a crucial component of our broader data offerings at Driver Technologies. It complements our extensive library of driving data collected from various vehicles and road users, creating a comprehensive data ecosystem that supports multiple verticals, including insurance, automotive technology, and smart city planning.

In summary, Driver Technologies' Speed Over Limit Driver Behavior Data provides a unique opportunity for data buyers to access high-quality, actionable insights that drive innovation across mobility. By integrating our Speed Over Limit Driver Behavior Data with other datasets, clients can gain a holistic view of transportation dynamics, enhancing their analytical capabilities and decision-making processes.

This dataset contains the responses from an online survey. The survey asked respondents to give numerical and binary ratings for how aggressive they considered various short video clips depicting driving behaviors to be.Each csv file contains data for a seperate set of driving behaviors. (Close car following, Illegal passing, Speeding, or collisions and near-collisions)Descriptions for data columns are in data_description.yaml

At Driver Technologies, we are dedicated to harnessing advanced technology to gather anonymized critical driving data through our innovative dash cam app, which operates seamlessly on end users' smartphones. Our Forward Collision Warning Driver Behavior Data offering is a key resource for understanding driver behavior and improving safety on the roads, making it an essential tool for various industries.

What Makes Our Data Unique? Our Forward Collision Warning Driver Behavior Data is distinguished by its real-time collection capabilities, utilizing our built-in computer vision technology to identify and capture instances where a driver is either tailgating or experiences a near collision and recieves a warning through our app. These critical safety events are indicative of aggressive driving behavior and potential risks on the road. By providing data on these significant events, our dataset empowers clients to perform in-depth analysis and take proactive measures to enhance road safety.

How Is the Data Generally Sourced? Our data is sourced directly from users who utilize our dash cam app, which harnesses the smartphone’s camera and sensors to record during a trip. This direct sourcing method ensures that our data is unbiased and represents a wide variety of conditions and environments. The data is not only authentic and reflective of current road conditions but is also abundant in volume, offering millions of miles of recorded trips that cover diverse scenarios.

Primary Use-Cases and Verticals Driver Behavior Analysis: Organizations can leverage our dataset to analyze driving habits and identify trends in driver behavior related to tailgating and near collisions. This analysis can help in understanding patterns related to rule compliance, driver attentiveness, and potential risk factors.

Training Computer Vision Models: Clients can utilize our annotated data to develop and refine their own computer vision models for applications in autonomous vehicles, ensuring better object detection and decision-making capabilities in complex road environments.

Improving Risk Assessment: Insurers can utilize our dataset to refine their risk assessment models. By understanding the frequency and context of forward collision warnings, they can better evaluate driver risk profiles, leading to more accurate premium pricing and improved underwriting processes.

Integration with Our Broader Data Offering The Forward Collision Warning Driver Behavior Data is a crucial component of our broader data offerings at Driver Technologies. It complements our extensive library of driving data collected from various vehicles and road users, creating a comprehensive data ecosystem that supports multiple verticals, including insurance, automotive technology, and smart city planning.

In summary, Driver Technologies' Forward Collision Warning Driver Behavior Data provides a unique opportunity for data buyers to access high-quality, actionable insights that drive innovation across mobility. By integrating our Forward Collision Warning Driver Behavior Data with other datasets, clients can gain a holistic view of transportation dynamics, enhancing their analytical capabilities and decision-making processes.

Based on the development of the concept of a resource-saving and environmentally friendly society, needing to develop low-carbon and sustainable urban transportation. Most of the pollutants come from the emissions of motor vehicle exhaust. Therefore, this paper analyzes the relationship between driving behavior and traffic emissions, to constrain driver behavior to reduce pollutant emissions. The GPS data are preprocessed by using Navicat for data integration, data screening, data sorting, etc., and then, the speed data are cleaned by using a combination of box-and-line plots and linear interpolation in SPSS. Second, this paper uses principal component analysis (PCA) to downsize 12 indicators such as average speed, average acceleration, and maximum speed and then adopts K-MEANS and K-MEDOIDS methods to cluster the driver’s behavioral indicators, selects the aggregation method based on the clustering indexes optimally, and analyzes the driver’s driving state by using the symbolic approximation aggregation method; finally, according to the above research results and combined with the MOVES traffic emission model to analyze the relationship between the driver’s driving mode, driving state, and traffic emissions, the decision tree can be used to predict the unknown driving mode of the driver to estimate the degree of its emissions.

Linguistic rules in the presented data reflect the behavior of drivers, during application of the car-following driving behavior.

Driving behaviour multimodal human factors preprocessed dataset, including EEG, EMG, ECG and GSR.

This dataset provides granular vehicle telemetry and driver action records, including speed, acceleration, location, and risk event indicators, enabling comprehensive analysis of driving behavior and risk profiling. Designed for insurers, telematics providers, and transportation safety analysts, it supports advanced modeling of driver risk and safety interventions.

Unidata’s Driver Behaviour dataset helps AI analyze real-world driving patterns to enhance road safety and autonomous systems

This is the code and processed data related to the publication:

Dong, Y., Zhang, L., Farah, H., Zgonnikov, A., & van Arem, B. (2023). Data-driven Semi-supervised Machine Learning with Surrogate Safety Measures for Abnormal Driving Behavior Detection. arXiv preprint arXiv:2312.04610. https://arxiv.org/abs/2312.04610

The original data is from https://github.com/UCF-SST-Lab/UCF-SST-CitySim1-Dataset

The codes make use of open-sourced implementation of HELM and other semi-supervised learning algorithms.

After setting up the folder and fetching the data, one can simply run the code with the specific function (identified by their names) get the relevant results.

Details about the implementation are demonstrated in the paper.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Detecting abnormal driving behaviour is critical for road traffic safety and the evaluation of drivers' behaviour. With the advancement of machine learning (ML) algorithms and the accumulation of naturalistic driving data, many ML models have been adopted for abnormal driving behaviour detection (also referred to as anomalies). Most existing ML-based detectors rely on supervised methods, which require substantial labelled data. However, ground truth labels are not always available in the real world, and labelling large amounts of data is tedious. Thus, there is a need to explore unsupervised or semi-supervised methods to make the anomaly detection process more feasible and efficient. To fill this research gap, this study analyzes large-scale real-world data revealing several abnormal driving behaviours (e.g., sudden acceleration, rapid lane-changing) and develops a Hierarchical Extreme Learning Machines (HELM) based semi-supervised ML method using partly labelled data to accurately detect the identified abnormal driving behaviours. Moreover, previous ML-based approaches predominantly utilized basic vehicle motion features (e.g., velocity and acceleration) to label and detect abnormal driving behaviours, while this study seeks to introduce event-level safety indicators as input features for ML models to improve detection performance. Results from extensive experiments demonstrate the effectiveness of the proposed semi-supervised ML model with the introduced safety indicators serving as important features. The proposed semi-supervised ML method outperforms other baseline semi-supervised or unsupervised methods regarding various metrics, e.g., delivering the best accuracy (99.58%) and the best F-1 measure (0.9913). The ablation study further highlights the significance of safety indicators for advancing the detection performance.

Description:

This comprehensive gray-scale dataset is a valuable resource for researchers and developers in the field of computer vision, machine learning and deep learning, particularly those focused on driver behavior analysis and driver assistance systems. Comprising over 14,000 labeled images across six distinct classes, it provides a diverse and extensive collection for training, validation, and testing purposes, specifically tailored for gray-scale image processing.

The dataset is organized into three main directories:

Training Set (train):This directory contains 11,942 gray-scale images, carefully curated and labeled across the six classes.

Validation Set (validation): With 1,922 gray-scale images, this subset provides a means for fine-tuning models and evaluating their performance during development.

Test Set (test): Comprising 985 gray-scale images, this directory is reserved for final model evaluation and benchmarking.

The dataset encompasses six classes of driving behaviors:

1- Dangerous Driving: Gray-scale images capturing instances of reckless or hazardous driving behavior, such as speeding or erratic lane changes. 2- Distracted Driving: Instances where the driver's attention is diverted away from the road, possibly due to smartphone usage, eating, or interacting with passengers. 3- Drinking: Gray-scale images depicting drivers consuming alcoholic beverages while behind the wheel, highlighting the dangers of driving under the influence. 4- Safe Driving: Examples of responsible and cautious driving behavior captured in gray-scale, including obeying traffic laws, maintaining safe distances, and using turn signals. 5- Sleepy Driving: Instances where drivers exhibit signs of drowsiness or fatigue, posing a significant risk of accidents due to reduced alertness, depicted in gray-scale. 6- Yawn: Gray-scale images capturing drivers in the act of yawning, often indicative of fatigue or tiredness, which can impair driving performance.