Southeast university distracted driver dataset download. , it is composed of the same ten distraction activities).
Southeast university distracted driver dataset download. 2. [2011a] designed a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the This GitHub repository contains code for building a distracted driver detection model using the State Farm Distracted Driver Detection dataset. The driver drowsiness datasets contains videos/frames of three subjects performing eyeclose, yawning, happy and neutral state of driver's infront of camera while driving. 3736752024-12-03T10:55:28. Gearbox dataset is from Southeast University, China. In this paper, we present the first publicly available dataset for “distracted driver” posture estimation with more distracti. [2011a] designed a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the Jan 26, 2024 · A large-scale, diverse posture-based distracted diver dataset, with more than 470K images taken by 4 cameras observing 100 drivers over 79 hours from 5 vehicles. This performance is similar, and/ or better when compared to larger, more complex deep learning models trained for similar driver distraction detection applications. The images, presented in raw, unannotated form, allow for flexible pre-processing by machine learning practitioners. Their dataset consists of frontal image view of a Data Collection We chose to use the State Farm Distracted Driver Detection dataset, a collection of 22,424 images of drivers operating a vehicle [4]. Chapter 1: Introduction Dec 12, 2023 · Request PDF | Driver distraction detection using semi-supervised lightweight vision transformer | The continuously increasing number of traffic accidents necessitates addressing distracted driving We evaluate results of the proposed network on the American University in Cairo (AUC) distracted driver detection dataset as well as Statefarm's dataset on Kaggle and compare the performance with Nov 21, 2024 · High-resolution images in the dataset were collected across different lighting conditions and vehicle types, representing diverse driving situations. In addition, an interpretable method based on Gradient-weighted Class Activation Mapping (Grad-CAM) is applied to explain the proposed driver behavior recognition model. This dataset is pivotal for training and testing our convolutional neural network models to accurately identify different types of driver distractions and is considered a standard when dealing with data for driver distraction training. The dataset contains 22424 driver images in total downloaded from kaggle. In the 1990s, researchers began developing datasets to detect phone usage behind the wheel. First column is normal driving posture; second column is the posture of operating the shift gear; third column is Feb 3, 2021 · In [], the authors designed a more inclusive distracted-driving dataset with a side view of the driver considering four activities: Safe driving, operating the shift lever, eating, and talking on a cell phone. de heraqi@aucegypt. DBNet is a large-scale driving behavior dataset, which provides large-scale high-quality point clouds scanned by Velodyne lasers, high-resolution videos recorded by dashboard cameras and standard drivers' behaviors (vehicle speed, steering angle) collected by real-time sensors. Southeast University Distracted Driver Dataset A dataset for driving posture recognition, includes images of drivers with different postures. The State Farm dataset consists of ten categories, marked as C0 C8. The studies evaluate the algorithms on a single dataset and do not consider cross-dataset Dataset Design Figure 1: Examples of the American University in Cairo (AUC) Distracted Driver’s Dataset. from publication: Toward Extremely Lightweight Distracted Driver American University in Cairo (AUC) Distracted Driver’s Dataset A new dataset for distracted driver posture estimation, proposed a novel system that achieves 95. Following are the file descriptions and URL’s from which the data can be obtained : Apr 1, 2025 · Download Citation | On Apr 1, 2025, Haibin Sun and others published A lightweight model for distracted driver detection based on neural architecture search and coordinate attention | Find, read May 28, 2024 · The dataset used in our project is the ”State Farm Distracted Driver Detection,” [4] available through Kaggle. Feb 1, 2024 · The DMS is designed, and the Hunan University (HNU) distracted driver dataset is built. From the Aug 15, 2017 · This dataset enables research into driving behaviors under neatly abstracted distracting stressors, which account for many car crashes. [12] proposed capturing images of driver behavior by mounting cameras on The Driver Monitoring Dataset is the largest visual dataset for real driving actions, with footage from synchronized multiple cameras (body, face, hands) and multiple streams (RGB, Depth, IR) recorded in two scenarios (real car, driving simulator). Distracted driving is characterized by driver interference, driver mobile use and some entertainment aspects, while specific harmful and risky actions are considered for aggressive driving. The dataset is organized into five behavioral classes: Safe Driving: Images show drivers fully attentive to the road, either with . Zhao et al. 09498v3 [cs. Download Table | Comparison of results with previous studies on AUC-DDD v2 dataset (sorted on average accuracy of the model). Smartphone use while driving has been identified as a leading cause of distracted driving [11]. The dataset can be downloaded from this Kaggle competition. The dataset contains coloured images of size 640 x 480 pixels which are resized to 64 X 64 coloured images for training and testing pusposes. American University in Cairo (AUC) Distracted Driver’s Dataset A new dataset for distracted driver posture estimation, proposed a novel system that achieves 95. The RGB-D was built with Kinect and updated by the University of California, San Diego, with the main task of detecting hands on the wheel. 387–405). edu arXiv:1706. It mainly includes holding the steering wheel, operating the gear lever, eating, and calling four categories of distracted driving behaviors. We collected the data in a stationary vehicle using three in-vehicle cameras positioned at locations: on the dashboard, near the rearview mirror, and on the top right-side window corner Download scientific diagram | Summary details of the AUC dataset from publication: Distracted Driver Classification Using Deep Learning | One of the most challenging topics in the field of Feb 1, 2023 · This article presents a synthetic distracted driving (SynDD1) dataset for machine learning models to detect and analyze drivers' various distracted behavior and different gaze zones. Different annotated labels related to distraction 2. From the Real-time Distracted Driver Posture Classification Yehya Abouelnaga Hesham M. abouelnaga@tum. Feb 1, 2024 · At present, distracted driver datasets mainly include the AUC distracted driver dataset, StateFarm, the SEU distracted driver dataset, and the RGB-D [47]. This dataset contains 2 subdatasets, including bearing data and gear data, which are both acquired on Drivetrain Dynamics Simulator (DDS). Jul 1, 2022 · Driver behavior recognition has been studied in recent years [1], [2], [5], [6]. Trivedi et al. Feb 26, 2025 · This dataset provides a diverse and rich resource for analyzing driving behaviors in real-world scenarios, making it invaluable for research on driver distraction and aggressive behavior [26, 28]. This largely limits the development of DDC since many practical problems such as the cross-modality setting cannot be fully studied. Ohn-bar et al. 696216Zhao et al. Unreliable ad hoc methods are Apr 7, 2023 · Early research on distracted driving was mainly based on a Southeast University driving posture dataset (SEU dataset), which contained four types of distracted driving postures, ‘holding the steering wheel,’ ‘shifting,’ ‘eating,’ and ‘calling’ []. Kaggle is the world’s largest data science community with powerful tools and resources to help you achieve your data science goals. from publication: Optimally-Weighted Image-Pose Approach (OWIPA) for Apr 17, 2022 · This article presents a synthetic distracted driving (SynDD2 - a continuum of SynDD1) dataset for machine learning models to detect and analyze drivers' various distracted behavior and different gaze zones. Download scientific diagram | Example images from the SEU driving dataset [13]. In this paper, we present the first publicly available dataset for driver distraction identification with more distraction postures than existing alternatives. A total of 44 volunteers from seven different countries participated in the creation of this dataset. Dec 22, 2020 · Distracted driving behavior has become a leading cause of vehicle crashes. Apr 1, 2025 · This section reviews relevant studies on distracted driver detection and the development for distracted driver detection. The dataset captures real-world driver behaviors under diverse driving conditions, including private vehicles and public buses, in Dhaka, Bangladesh. Download scientific diagram | NTHU Dataset Sample Images from publication: Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application | A sleepy Jun 1, 2025 · This paper introduces a novel dataset designed to support the development of AI-driven driver monitoring systems. StateFarm’s Distracted Driver Detection Dataset A dataset for driver behavior recognition, includes images of drivers with different behaviors. Because labels were only provided for the training data, we split the training portion of the dataset into a new training set (80%) and test set (20%). The json representation of the dataset with its distributions based on DCAT. Driver distraction, defined as the diversion of attention away from activities critical for safe driving toward a competing activity, is increasingly recognized as a significant source of methods to detect those distractions. Download scientific diagram | Sample images of distracted driving behaviors on the AUC Distracted Driver Dataset (AUCD2) [24]. With this purpose, we created a new data set that includes driver images and sensor data collected from real-world drives. Oct 2, 2023 · Detecting driver distractions in real-time using deep learning, PyTorch, and the MobileNetV3 neural network model. In this paper May 1, 2012 · [14] created the Southeast University Driving Posture (SEU-DP) dataset in 2011, which includes four types of behaviours: safe driving, operating the shift lever, calling and eating, and talking on The project leverages a subset of the State Farm Distracted Driver Detection Kaggle competition dataset. This dataset is obtained from Kaggle (State Farm Distracted Driver Detection competition). Download scientific diagram | AUC Distracted Driver dataset [24]. The frames are divided into 5 labelled regions with classes: One hand, no hands, two hands, two hands + cell, two hands + map, and two hands + bottle. - leogachimu/Distracted_Driver_Detection The State Farm Distracted Driver dataset is used to pretrain our proposed ViT model since the dataset contains more types of driver distraction behavior. Distracted Driver Dataset, yielding accuracies as high as 93% and speeds as high as 11 FPS when detecting distracted driving. The Southeast University (SUE-DP) dataset [3] was proposed in 2011. This repo presents the code for distracted driver detection and classification with deep Convolutional Neural Network (CNN) network on AUC dataset. from publication: Driver Behavior Analysis via Two-Stream Deep Convolutional Neural Network | According to the World Health We present a realtime distracted driver pose estimation system using a weighted ensemble of con-volutional neural networks and a challenging distracted driver’s dataset on which we evaluate our We present a realtime distracted driver pose estimation system using a weighted ensemble of con-volutional neural networks and a challenging distracted driver’s dataset on which we evaluate our DMD: A Large-Scale Multi-modal Driver Monitoring Dataset for Attention and Alertness Analysis. Zhang et al. This paper proposes a data augmentation method for distracted driving detection based on the driving operation area. From the dataset perspective, the available dataset includes the American University in Cairo Distracted Driver (AUC) dataset, StateFarm dataset, Southeast University Distracted Driver (SEU) dataset, and RGB-D dataset [1], [5]. 25 million deaths yearly due toroad trafic accidentsworldwide and the number has been continuously increasing over the last few years. We collected the data in a stationary vehicle using three in-vehicle cameras positioned at locations: on the dashboard, near the rearview mirror, and on the top right-side window corner. Early research on distracted driving was mainly based on a Southeast University driving posture dataset (SEU dataset), which contained four types of distracted driving postures, ‘hold-ing the steering wheel,’ ‘shifting,’ ‘eating,’ and ‘calling’ [27]. In 2018, a new Distracted Driver dataset similar to the StateFarm's dataset was created (i. In: A. Sep 14, 2020 · Our proposed approach is evaluated on the American University in Cairo (AUC) Distracted Driver Dataset, the most comprehensive and detailed dataset on driver distraction postures to date. Feb 13, 2019 · Southeast University Distracted Driver Dataset Reference [32] designs a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the steering wheel, operating the shift lever, eating a cake, and talking on a cellular phone. SEU_PML Dataset is a large and detailed dataset for monitoring-based traffic participants detection, jointly proposed by Southeast University and Purple Mountain Laboratories This dataset coupled with its paper have been accepted by the top journal IEEE Transactions on Intelligent Transportation Systems Paper name: Monitoring-based Traffic Participant Detection in Urban Mixed Traffic: A Novel In [29], the authors designed a more inclusive distracted-driving dataset with a side view of the driver considering four activities: Safe driving, operating the shift lever, eating, and talking on a cell phone. Nearly fifth of these accidents are caused by distracted drivers. See full list on github. The proposed model was trained and tested by state farm distracted driver detection image datasets available at Kaggle that contains images of drivers in the most common activities performed, which lead to distraction while driving divided into ten classes. n postures than existing alternatives. Mar 1, 2025 · The Southeast University Driving Posture dataset (SEU-DP dataset) has been created for the purpose of studying driver behavior recognition. CV] 29 Nov 2018 Mohamed N. The project involves data preprocessing, model creation, training, and evaluation. Experiments and validation were conducted using the open-source Yawn detection dataset (YawDD) and National Tsing Hua University drowsy driver detection dataset (NTHU-DDD). The AUC dataset contains 10 distracted behaviors and is publicly available. It introduces a contourlet transform for feature extraction, and then, evaluates the perfor-mance of different classifi Dec 1, 2022 · Few studies have evaluated the robustness of deep learning distracted driver detection algorithms. We evaluate 10 state-of-the-art CNN and RNN methods using the average cross-entropy loss, accuracy, F1-score and training time on the American University in Cairo (AUC) Distracted Driver Dataset, which is the most comprehensive and detailed dataset on driver distraction to date. 3 Southeast University Distracted Driver Dataset Zhao et al. Distracted Driver Detection dataset by new-workspace-vrhvx. This dataset consists of: Images: 22,424 dashboard camera images categorized into 10 classes (c0-c9) representing driver behavior. The work in the distracted driver detection field over the past seven years could be clustered into four groups: multiple independent cell-phone usage detection publications, Laboratory of Intelligent and Safe Automobiles in University of California San Diego (UCSD) datasets and publications, Southeast University Distracted Driver dataset and Southeast University Distracted Driver Dataset Reference [32] designs a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the steering wheel, operating the shift lever, eating a cake, and talking on a cellular phone. An assisted driving testbed is developed for the purpose of creating realistic driving experiences and validating the distraction detection algorithms. , it is composed of the same ten distraction activities). For more information on the competition see here. com Loading… 2000 open source driver images. 1. Bartoli & A. The dataset contains two Southeast University Distracted Driver DatasetA dataset for driving posture recognition, includes images of drivers with different postures. A dataset for driving posture recognition, includes images of drivers with different postures. distracted driving). This dataset includes images captured by cameras, featuring 4 driving behaviors performed by 10 male and 10 female subjects. 98% driving posture estimation classification accuracy. 3 Southeast University Distracted Driver Dataset ing wheel, operating the shift lever, eating a cake and talking on a cellular phone. Dec 8, 2018 · In this paper, we present the first publicly available dataset for "distracted driver" posture estimation with more distraction postures than existing alternatives. Refer-ence [32] designs a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the steering wheel, operating the shift lever, eating a cake, and talking on a cellular phone. The provided data set has driver images, each taken in a car with a driver doing something in the car (texting, eating, talking on the phone, makeup, reaching behind, etc). 98% d. The dataset is the sole property of the AutoMan group at the Nanyang Technological University and is protected by copyright. Data we used are all from fan end which is marked as 'FE' in the data files. Although many datasets are introduced to support the study of DDC, most of them are small in data size and are short of diversity in environmental variations. [8], they evaluated the proposed approaches on the Southeast University Driving-posture Dataset and achieved mean Average Precision on the dataset, illustrating the proposed method is effective in recognizing drivers actions. No OrganizationOriginal MetadataThe json representation of the Distracted driver classification (DDC) plays an important role in ensuring driving safety. This repository contains code to train models for the State Farm Distracted Driver Detection competition on Kaggle. The dataset shall remain the exclusive property of AutoMan. cf665c34-0329-4687-9de2-0d844cb41d88computer visiondistracted drivingposture recognition2024-12-03T10:55:28. These data are collected from Drivetrain Dynamic Simulator. Existing work of distracted driver detection is concerned with a small set of distractions (mostly, cell phone usage). Fusiello (eds), Computer Vision — ECCV 2020 Workshops (pg. [2011a] designed a more inclusive distracted driving dataset with a side view of the driver and more activities: grasping the Jan 22, 2019 · Unreliable ad-hoc methods are often used. However, the dataset is not balanced and not well annotated. Moustafa Department of Computer Science and Engineering The American University The work in the distracted driver detection field over the past seven years could be clustered into four groups: multiple independent cell phone detection publications, Laboratory of Intelligent and Safe Automobiles in University of California San Diego (UCSD) datasets and publications, Southeast A new dataset for distracted driver posture estimation, proposed a novel system that achieves 95. Jan 28, 2025 · Yan et al. Therefore, this study proposes a method based on multi-feature processing in conjunction with you only look once (YOLO)-based object detection to classify driver attention. Cell Phone Usage Detection [7] presents an SVM-based model that detects the use of mobile phone while driving (i. It introduces a contourlet transform for feature extraction, and then, evaluates the perfor-mance of different classifi The work in the distracted driver detection field over the past seven years could be clustered into four groups: multiple independent cell phone detection publications, Laboratory of Intelligent and Safe Automobiles in University of California San Diego (UCSD) datasets and publications, Southeast Feb 13, 2019 · Furthermore, the existing SFDDD [29] and AUC [30] datasets lack representation of distracted behaviors such as yawning, wiping glass, smoking, voicing right, and voicing left, and similar Abstract: Distracted driving behavior has become a leading cause of vehicle crashes. Contribute to Crystal-wzy/Distracted-Driver-Dataset development by creating an account on GitHub. c0: Safe driving c1-c4: Texting/Talking on phone (left/right hand) c5: Operating radio c6: Drinking c7: Reaching behind c8: Hair and makeup c9: Talking to Feb 18, 2023 · At first, distracted driving behavior was an evaluation of multiple issues such as drivers making phone calls and not wearing seat belts. Distracted driver detetion is one of the safety measures in Advanced Driver Assistance Systems (ADAS) to take countermeasures and enable safe driving. Download scientific diagram | IR images dataset of HNUST and HNU for driver distraction behaviors from publication: CEAM-YOLOv7: Improved YOLOv7 Based on Channel Expansion and Attention Mechanism This project aims to leverage computer vision and machine learning techniques to develop a system capable of detecting in real-time, whether or not a driver is distracted, contributing to enhanced road safety. Southeast University Distracted Driver Dataset A dataset for driving posture recognition, includes images of drivers with different postures. In a column-level order, postures are: drinking, adjusting the radio, driving in a safe posture, fiddling with hair or makeup, reaching behind, talking to passengers, talk on cell phone using left hand, talk on cell phone using right hand, texting using left hand, and texting using right Southeast University Distracted Driver Dataset. Nov 1, 2020 · In this work, we propose to integrate sensor data into the vision-based distracted driver detection model to improve the generalization ability of the system. Abstract This article presents a synthetic distracted driving (SynDD2 - a continuum of SynDD1 [1]) dataset for machine learning models to detect and analyze drivers' various distracted behavior and different gaze zones. Eraqi Department of Informatics Department of Computer Science and Engineering Technical University of Munich The American University in Cairo yehya. Jan 7, 2021 · We evaluate 10 state-of-the-art CNN and RNN methods using the average cross-entropy loss, accuracy, F1-score and training time on the American University in Cairo (AUC) Distracted Driver Dataset, which is the most comprehensive and detailed dataset on driver distraction to date. This paper proposes a data augmentation method for distracted driving detection based on the driving op-eration area. In addition, we propose a reliable system that achieves a 95. Aug 1, 2011 · Early research on distracted driving was mainly based on a Southeast University driving posture dataset (SEU dataset), which contained four types of distracted driving postures, 'holding the American University in Cairo (AUC) Distracted Driver’s Dataset A new dataset for distracted driver posture estimation, proposed a novel system that achieves 95. Sep 7, 2023 · With features extracted from a driving posture dataset created at Southeast University (SEU), holdout and cross-validation experiments on driving posture classification were then conducted using The frames are divided into 5 labelled regions with classes: One hand, no hands, two hands, two hands + cell, two hands + map, and two hands + bottle. In addition to the Anaconda libraries, you need to install tensorflow, tensorflow-addons, tensorflow-hub, albumentations and wandb. The authors collected a dataset which consists of images of the drivers in both normal and distracted driving postures. Southeast University Distracted Driver Dataset. The World Health Organization (WHO) reported1. e. First, the class activation mapping method is used to show the key feature areas of driving behavior analysis, and then the driving operation areas are detected by the faster R-CNN detection model for Driver Distraction Dataset download. lny wph5 exfrn 0nuj 9m 1gq1kj gjxtd weazu 0q tkvk