Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 16편

Traffic Flow Forecasting Data Set

Traffic
Traffic 설명 보기

Abstract: 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. | Data Set Characteristics | Number of Instances | Area | Attribute Characteristics | Number of Attributes | Date Donated | Associated Tasks | Missing Values | | ------------------------ | ------------------- | -------- | ------------------------- | -------------------- | ------------ | ---------------- | -------------- | | Multivariate | 2101 | Computer | Real | 47 | 2020-11-17 | Regression | N/A | ### Source: Liang Zhao, liang.zhao '@' emory.edu, Emory University. ### Data Set 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. 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. ### Attribute Information: 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). ### Relevant Papers: Liang Zhao, Olga Gkountouna, and Dieter Pfoser. 2019. Spatial Auto-regressive Dependency Interpretable Learning Based on Spatial Topological Constraints. ACM Trans. Spatial Algorithms Syst. 5, 3, Article 19 (August 2019), 28 pages. DOI:[Web Link] ### Citation Request: To use these datasets, please cite the papers: Liang Zhao, Olga Gkountouna, and Dieter Pfoser. 2019. Spatial Auto-regressive Dependency Interpretable Learning Based on Spatial Topological Constraints. ACM Trans. Spatial Algorithms Syst. 5, 3, Article 19 (August 2019), 28 pages. DOI:[Web Link]

관련 논문 374편

German Traffic Sign Recognition Benchmark

GTSRB
GTSRB 설명 보기

The German Traffic Sign Recognition Benchmark (GTSRB) contains 43 classes of traffic signs, split into 39,209 training images and 12,630 test images. The images have varying light conditions and rich backgrounds. Source: Invisible Backdoor Attacks Against Deep Neural Networks Image Source: https://www.researchgate.net/figure/An-example-of-the-43-traffic-sign-classes-of-GTSRB-dataset_fig9_311896388

관련 논문 25편

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

LargeST
LargeST 설명 보기

In this work, we propose LargeST as a new benchmark dataset (see Figure 1), with the goal of facilitating the development of accurate and efficient methods in the context of large-scale traffic forecasting. The distinguishing characteristic of LargeST lies not only in its extensive graph size, encompassing a total of 8,600 sensors in California, but also in its substantial temporal coverage and rich node information – each sensor contains 5 years of data and comprehensive metadata. LargeST comprises four sub-datasets, each characterized by a different number of sensors. The biggest one is California (CA), including a total number of 8,600 sensors. We also construct three subsets of CA by selecting three representative areas within CA and forming the sub-datasets of Greater Los Angeles (GLA), Greater Bay Area (GBA), and San Diego (SD).

관련 논문 19편

SUTD-TrafficQA

SUTD-TrafficQA 설명 보기

SUTD-TrafficQA (Singapore University of Technology and Design - Traffic Question Answering) is a dataset which takes the form of video QA based on 10,080 in-the-wild videos and annotated 62,535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios. Specifically, the dataset proposes 6 challenging reasoning tasks corresponding to various traffic scenarios, so as to evaluate the reasoning capability over different kinds of complex yet practical traffic events.

관련 논문 16편

CURE Traffic Sign Recognition

CURE-TSR
CURE-TSR 설명 보기

Includes more than two million traffic sign images that are based on real-world and simulator data. Source: CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition

관련 논문 9편

DoTA

Detection of Traffic Anomaly
Detection of Traffic Anomaly 설명 보기

Contains 4,677 videos with temporal, spatial, and categorical annotations. Source: When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos

관련 논문 9편

USA Air-Traffic

USA Air-Traffic 설명 보기

Leonardo Filipe Rodrigues Ribeiro, Pedro H. P. Saverese, and Daniel R. Figueiredo. struc2vec: Learning node representations from structural identity.

관련 논문 8편

Web Traffic Time Series Forecasting

Wiki
Wiki 설명 보기

Context There's a story behind every dataset and here's your opportunity to share yours. ### Content What's inside is more than just rows and columns. Make it easy for others to get started by describing how you acquired the data and what time period it represents, too. ### Acknowledgements We wouldn't be here without the help of others. If you owe any attributions or thanks, include them here along with any citations of past research. ### Inspiration Your data will be in front of the world's largest data science community. What questions do you want to see answered?

관련 논문 5편

VPN/NONVPN NETWORK APPLICATION TRAFFIC DATASET

VNAT
VNAT 설명 보기

This dataset is a collection of labelled PCAP files, both encrypted and unencrypted, across 10 applications, as well as a pandas dataframe in HDF5 format containing detailed metadata summarizing the connections from those files. It was created to assist the development of machine learning tools that would allow operators to see the traffic categories of both encrypted and unencrypted traffic flows. In particular, features of the network packet traffic timing and size information (both inside of and outside of the VPN) can be leveraged to predict the application category that generated the traffic.

관련 논문 4편

Blockchain Network Attack Traffic dataset

BNaT
BNaT 설명 보기

Tran Viet Khoa, Do Hai Son, Dinh Thai Hoang, Nguyen Linh Trung, Tran Thi Thuy Quynh, Diep N. Nguyen, Nguyen Viet Ha, and Eryk Dutkiewicz, "Collaborative Learning for Cyberattack Detection in Blockchain Networks," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 54, no. 7, pp. 3920-3933, Apr. 2024.

관련 논문 4편

CVL Traffic Signs Dataset

CVL Traffic Signs Dataset 설명 보기

A video dataset for recognising traffic signs hosted with the first IEEE Video and Image Processing (VIP) Cup within the IEEE Signal Processing Society. Source: Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions

관련 논문 4편

SJTU Small Traffic Light Dataset

S2TLD
S2TLD 설명 보기

S2TLD is a traffic light dataset, which contains 5,786 images of approximately 1,080 * 1,920 pixels and 720 * 1,280 pixels. It also contains 5 categories (include red, yellow, green, off and wait on) of 1,4130 instances. The scenes cover a decent variety of road scenes and typical: * Busy street scenes inner-city, * Dense stop-and-go traffic * Strong changes in illumination/exposure * Flickering/Fluctuating traffic lights * Multiple visible traffic lights * Image parts that can be confused with traffic lights (e.g. large round tail lights) Source: https://github.com/Thinklab-SJTU/S2TLD Image Source: https://github.com/Thinklab-SJTU/S2TLD

관련 논문 4편

Traffic Control Gesture

TCG
TCG 설명 보기

The TCG dataset is used to evaluate Traffic Control Gesture recognition for autonomous driving. The dataset is based on 3D body skeleton input to perform traffic control gesture classification on every time step. The dataset consists of 250 sequences from several actors, ranging from 16 to 90 seconds per sequence. Source: https://arxiv.org/pdf/2007.16072.pdf Image Source: https://github.com/againerju/tcg_recognition

관련 논문 3편

CURE Traffic Sign Detection

CURE-TSD
CURE-TSD 설명 보기

Based on simulated challenging conditions that correspond to adversaries that can occur in real-world environments and systems. Source: Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics

관련 논문 3편

Pedestrian-Traffic-Lights

PTL
PTL 설명 보기

A dataset of pedestrian traffic lights containing over 5000 photos taken at hundreds of intersections in Shanghai. Source: LYTNet: A Convolutional Neural Network for Real-Time Pedestrian Traffic Lights and Zebra Crossing Recognition for the Visually Impaired

관련 논문 3편

Traffic-Sign Detection and Classification in the Wild

Tsinghua-Tencent 100K
Tsinghua-Tencent 100K 설명 보기

Although promising results have been achieved in the areas of traffic-sign detection and classification, few works have provided simultaneous solutions to these two tasks for realistic real world images. We make two contributions to this problem. Firstly, we have created a large traffic-sign benchmark from 100000 Tencent Street View panoramas, going beyond previous benchmarks. We call this benchmark Tsinghua-Tencent 100K. It provides 100000 images containing 30000 traffic-sign instances. These images cover large variations in illuminance and weather conditions. Each traffic-sign in the benchmark is annotated with a class label, its bounding box and pixel mask. Secondly, we demonstrate how a robust end-to-end convolutional neural network (CNN) can simultaneously detect and classify traffic-signs. Most previous CNN image processing solutions target objects that occupy a large proportion of an image, and such networks do not work well for target objects occupying only a small fraction of an image like the traffic-signs here. Experimental results show the robustness of our network and its superiority to alternatives. The benchmark, source code and the CNN model introduced in this paper is publicly available.

관련 논문 2편

IoT Traffic Traces - Data Collected for IEEE TMC 2018

IoT Traffic Traces
IoT Traffic Traces 설명 보기

IOT TRAFFIC TRACES # Data Collected for IEEE TMC 2018 Cite our data A. Sivanathan, H. Habibi Gharakheili, F. Loi, A. Radford, C. Wijenayake, A. Vishwanath and V. Sivaraman, "Classifying IoT Devices in Smart Environments Using Network Traffic Characteristics", IEEE Transactions on Mobile Computing, Aug, 2018. Post Processing Tools https://github.com/arunmir/sdn-sim Resources List_Of_Devices.txt

관련 논문 2편

Traffic Accident Prediction data repository

TAP
TAP 설명 보기

The Traffic Accident Prediction (TAP) data repository offers extensive coverage for 1,000 US cities (TAP-city) and 49 states (TAP-state), providing real-world road structure data that can be easily used for graph-based machine learning methods such as Graph Neural Networks. Additionally, it features multi-dimensional geospatial attributes, including angular and directional features, that are useful for analyzing transportation networks. The TAP repository has the potential to benefit the research community in various applications, including traffic crash prediction, road safety analysis, and traffic crash mitigation. The datasets can be accessed in the TAP-city and TAP-state directories. For example, this repository can aid in traffic accident occurrence prediction and accident severity prediction. Binary labels are used to indicate whether a node contains at least one accident for the occurrence prediction task, while severity is represented by a number between 0 and 7 for the severity prediction task. A severity level of 0 denotes no accident, and 1 to 7 represents increasingly significant impacts on traffic.

관련 논문 2편

VR traffic traces

VR traffic traces 설명 보기

The dataset contains traffic traces collected from 3 different VR applications. Researchers can use this dataset to replicate the behavior of real VR traffic directly in their studies, e.g., their simulations. Further information can be found in the repository.

관련 논문 1편

complex traffic video question answer datset

Complex-TV-QA
Complex-TV-QA 설명 보기

The Complex-TV-QA dataset, to our knowledge, is the inaugural resource that provides human-annotated, detailed video captions within traffic scenarios, alongside complex reasoning questions. This novel dataset not only stands as a vital tool for evaluating language models in real-world video-QA and video-reasoning research, but also offers valuable insights for the development and understanding of multi-modal video reasoning models and related works.

관련 논문 1편

Equilibrium-Traffic-Networks

Equilibrium-Traffic-Networks 설명 보기

This repository contains three graph datasets for the UE traffic assignment problem on Sioux-Falls, Eastern-Massachusetts and Anaheim networks in both dgl and pyg formats. The datasets are generated and used to train and evaluate models for solving the User Equilibrium (UE) problem on three transportation networks: - ** Sioux-Falls** - ** Eastern-Massachusetts** - **Anaheim ** These networks are sourced from the well-known "transport networks for research" repository. These datasets are generated for the study "A hybrid deep-learning-metaheuristic framework for bi-level network design problems" by Bahman Madadi and Gonçalo H. de Almeida Correia, published in Expert Systems with Applications. ## Metadata Detailed information can be found in the Metadata.md file. ## Links - Figshare Dataset Repository: Link ## References - Article: A hybrid deep-learning-metaheuristic framework for bi-level network design problems - Link - GitHub Repository: HDLMF_GIN-GA - Link - Primary Figshare Data Repository: Link Note: This dataset is maintained at Figshare.

관련 논문 1편

Interaction Data of Autonomous Vehicles with Traffic Lights and Signs Based on Waymo Motion Open Dataset

Interaction Dataset of Autonomous Vehicles with Traffic Lights and Signs
Interaction Dataset of Autonomous Vehicles with Traffic Lights and Signs 설명 보기

This dataset is derived from the Waymo Motion dataset and focuses on capturing the interactions between autonomous vehicles (AVs) and traffic control devices such as traffic lights and stop signs. It addresses a critical gap by providing real-world trajectory data that reflects how AVs interpret and respond to traffic control signals, supporting research in AV behavior modeling, traffic simulation, and the design of intelligent transportation systems. # Dataset Overview - Data Source: Waymo Motion dataset - Interaction Scenarios: - Traffic Light Interactions: Includes stopping, left turns, right turns, and proceeding straight. Over 37,000 trajectory segments are provided. - Stop Sign Interactions: Includes four-way stops, right turns, one-step left turns, and two-step left turns. Over 44,000 trajectory segments are available. - Data Content: - Each segment represents a 9.1-second interval sampled at 0.1-second intervals. - Contains AV positions, speeds, and accelerations. - Includes the position and state information of traffic lights or stop signs (e.g., red, yellow, green; arrow or circle). # Data Processing Pipeline - Data Extraction - Segments are selected from the Waymo Motion dataset based on predefined rules (e.g., presence of traffic control devices, non-stationary vehicle movement, and trajectory intersection with the control device). - Trajectory Organization - Original data in tfrecord format is converted into CSV format. In the CSV files, each column represents a time-series variable (e.g., position, speed, acceleration), and each row corresponds to a time step. - Quality Assessment and Enhancement - Trajectories are evaluated using metrics such as anomalous acceleration, jerk, and jerk sign inversion ratios. - A wavelet-based denoising method (using the db6 wavelet) is applied to reduce noise and anomalies, resulting in smoother and more reliable trajectories. # Repository Structure The directory structure of this repository is as follows: . ├── interactions_with_stop_sign │ ├── four_way_stops │ │ ├── left_turns │ │ ├── right_turns │ │ └── straight_proceeds │ ├── one_step_left_turns_at_stop_sign │ └── two_step_left_turns_at_stop_sign ├── interactions_with_traffic_light │ ├── left_turns_at_traffic_light │ ├── right_turns_at_traffic_light │ ├── stops_at_traffic_light │ └── straight_proceeds_at_traffic_light └── README.md # Data Structure The structure of the AV-traffic light interaction data is as follows: | Attribute | Unit | Description | | -------------------- | ----- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | AV_speed | m/s | The raw speed of the AV. | | AV_x | m | The x-coordinate of the AV in the coordinate system defined by the Waymo dataset. | | AV_y | m | The y-coordinate of the AV in the coordinate system defined by the Waymo dataset. | | AV_acc | m/s^2 | The raw acceleration of the AV. | | AV_distance_to_light | m | The Euclidean distance between the current position of the AV and the controlling traffic light (stop line). | | nearest_light_x | m | The x-coordinate of the controlling traffic light in the same coordinate system. | | nearest_light_y | m | The y-coordinate of the controlling traffic light in the same coordinate system. | | nearest_light_state | - | The state of the controlling traffic light, encoded as follows:<br><br>0: unknown<br>1: arrow red<br>2: arrow yellow<br>3: arrow green<br>4: circle red<br>5: circle yellow<br>6: circle green<br>7: flashing red<br>8: flashing yellow | | AV_speed_enhanced | m/s | The denoised speed of the AV, which helps reduce measurement noise. | | AV_acc_enhanced | m/s^2 | The denoised acceleration of the AV, which helps reduce the effects of noise and discrete differentiation. | The structure of the AV-stop sign interaction data is as follows: | Attribute | Unit | Description | | ------------------------ | ----- | ---------------------------------------------------------------------------------------------------------- | | AV_speed | m/s | The raw speed of the AV. | | AV_x | m | The x-coordinate of the AV in the coordinate system defined by Waymo dataset. | | AV_y | m | The y-coordinate of the AV in the coordinate system defined by Waymo dataset. | | AV_acc | m/s^2 | The raw acceleration of the AV. | | AV_distance_to_stop_sign | m | The Euclidean distance between the current position of the AV and the nearest stop sign. | | nearest_stop_sign_x | m | The x-coordinate of the nearest stop sign in the same coordinate system. | | nearest_stop_sign_y | m | The y-coordinate of the nearest stop sign in the same coordinate system. | | AV_speed_enhanced | m/s | The denoised speed of the AV, which helps reduce measurement noise. | | AV_acc_enhanced | m/s^2 | The denoised acceleration of the AV, which helps reduce the effects of noise and discrete differentiation. | # Note Due to GitHub repository size limitations, only ten sample data files are provided in each directory of this repository. The full dataset is hosted on Google Drive: https://drive.google.com/drive/folders/1bJa62v7YHbsfcZ4yItmFxoIxhrVZvOLW If you would like to use the complete dataset, please email us to request access. Contact: Zheng Li, zli2674@wisc.edu # Citation If you use this dataset in your research, please cite the following paper: > Li, Z., Bao, Z., Meng, H., Shi, H., Li, Q., Yao, H., & Li, X. (2025). Interaction Dataset of Autonomous Vehicles with Traffic Lights and Signs. arXiv preprint arXiv:2501.12536.

관련 논문 1편

IoT-23: A labeled dataset with malicious and benign IoT network traffic

IoT-23
IoT-23 설명 보기

IoT-23 is a dataset of network traffic from Internet of Things (IoT) devices. It has 20 malware captures executed in IoT devices, and 3 captures for benign IoT devices traffic. It was first published in January 2020, with captures ranging from 2018 to 2019. These IoT network traffic was captured in the Stratosphere Laboratory, AIC group, FEL, CTU University, Czech Republic. Its goal is to offer a large dataset of real and labeled IoT malware infections and IoT benign traffic for researchers to develop machine learning algorithms. This dataset and its research was funded by Avast Software. The malware was allow to connect to the Internet.

관련 논문 1편

Malware Traffic Analysis Knowledge Dataset 2019

MTA-KDD'19
MTA-KDD'19 설명 보기

Malware Traffic Analysis Knowledge Dataset 2019 (MTA-KDD'19) is an updated and refined dataset specifically tailored to train and evaluate machine learning based malware traffic analysis algorithms. To generate it, that authors started from the largest databases of network traffic captures available online, deriving a dataset with a set of widely-applicable features and then cleaning and preprocessing it to remove noise, handle missing data and keep its size as small as possible. The resulting dataset is not biased by any specific application (although specifically addressed to machine learning algorithms), and the entire process can run automatically to keep it updated. Source: Letteri et al.

관련 논문 1편

Open RAN Commercial Traffic Twinning Dataset

Open RAN Commercial Traffic Twinning Dataset 설명 보기

Dataset of cross-layer Radio Access Network (RAN) Key Performance Measurements (KPMs) and protocol stack logs collected on an Open RAN deployment instantiated on Colosseum with traffic twinned from that of commercial cellular traces. The dataset includes Base Station (BS)- and User Equipment (UE)-level KPMs from PHY, MAC, and App layers under different RAN configurations representative of AI/ML control policies, number of UEs, and traffic demand. The fine-grained metrics of the dataset make it possible to understand the connection between PHY and MAC KPMs measured at the BS and UEs, control policies, and end-to-end and App-layer KPMs that reflect user experience.

관련 논문 1편

Songdo Traffic: High Accuracy Georeferenced Vehicle Trajectories from a Large-Scale Study in a Smart City

Songdo Traffic
Songdo Traffic 설명 보기

The Songdo Traffic dataset delivers precisely georeferenced vehicle trajectories captured through high-altitude bird's-eye view (BeV) drone footage over Songdo International Business District, South Korea. Comprising approximately 700,000 unique trajectories, this resource represents one of the most extensive aerial traffic datasets publicly available, distinguishing itself through exceptional temporal resolution that captures vehicle movements at 29.97 points per second, enabling unprecedented granularity for advanced urban mobility analysis.

관련 논문 1편

TSN-FlexTest Traffic Streams for Spot Robot, Tactile Internet, and Generic Data

TSN-FlexTest Traffic Streams for Spot Robot, Tactile Internet, and Generic Data 설명 보기

In this dataset, we provide detailed traffic stream data for the Spot robot, including both the Spot robot control traffic stream and the Spot video stream. The Spot robot traffic streams provide realistic traffic data for communication network evaluations, e.g., for measurements with the TSN FlexText testbed. Furthermore, we share data for the tactile internet including audio, video, and robotic communication. Finally, the dataset includes generic data streams for three different intervals (0.2ms, 0.3ms, and 0.5ms) with two different Ethernet frame sizes. The data is provided as .*pcap which can be replayed with various tools or be analyzed, e.g., with Wireshark. The Spot data streams are split into two directions and are based on Spot API calls.

관련 논문 1편

TUMTraffic-VideoQA

TUMTraffic-VideoQA 설명 보기

TUMTraffic-VideoQA is a novel dataset designed to understand spatiotemporal video in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatiotemporal object expressions, TUMTraffic-VideoQA unifies three essential tasks—multiple-choice video question answering, referred object captioning, and spatiotemporal object grounding—within a cohesive evaluation framework.

관련 논문 1편

Traffic demand in NYC and CHI

Traffic demand in NYC and CHI 설명 보기

This dataset includes four real-world sub-datasets about traffic demand. Each dataset spans 16 months, from January to April of the next year. - NYCbike: This dataset covers shared bike usage records in New York City from January 2022 to April 2023. Each entry represents a bike pickup and drop-off event. We divided New York into 200 grids and calculated the bike pickup and drop-off quantities for each grid every hour. - NYCtaxi: This dataset covers taxi usage data from January 2018 to April 2019 in New York City, with hourly usage for each region, including both pick-up and drop-off dimensions. The division of regions is based on the scheme provided by the official website. - CHIbike: The dataset contains shared bike usage records in Chicago from January 2022 to April 2023. Chicago is divided into 200 grids and hourly bike pickup and drop-off quantities for each grid are collected. - CHItaxi: This dataset contains hourly taxi pick-up and drop-off values of census regions in Chicago from January 2016 to April 2017.

관련 논문 1편

A Multi-Modal Real-World Dataset of ETSI ITS V2X Messages in Public Road Traffic

V2AIX
V2AIX 설명 보기

Connectivity is a main driver for the ongoing megatrend of automated mobility: future Cooperative Intelligent Transport Systems (C-ITS) will connect road vehicles, traffic signals, roadside infrastructure, and even vulnerable road users, sharing data and compute for safer, more efficient, and more comfortable mobility. In terms of communication technology for realizing such vehicle-to-everything (V2X) communication, the WLAN-based peer-to-peer approach (IEEE 802.11p, ITS-G5 in Europe) competes with C-V2X based on cellular technologies (4G and beyond). Irrespective of the underlying communication standard, common message interfaces are crucial for a common understanding between vehicles, especially from different manufacturers. Targeting this issue, the European Telecommunications Standards Institute (ETSI) has been standardizing V2X message formats such as the Cooperative Awareness Message (CAM). In this work, we present V2AIX, a multi-modal real-world dataset of ETSI ITS messages gathered in public road traffic, the first of its kind. Collected in measurement drives and with stationary infrastructure, we have recorded more than 230000 V2X messages from more than 1800 vehicles and roadside units in public road traffic. Alongside a first analysis of the dataset, we present a way of integrating ETSI ITS V2X messages into the Robot Operating System (ROS). This enables researchers to not only thoroughly analyze real-world V2X data, but to also study and implement standardized V2X messages in ROS-based automated driving applications.

관련 논문 1편

aiMotive 3D Traffic Light and Traffic Sign Dataset

aiMotive 3D Traffic Light and Traffic Sign Dataset 설명 보기

A large-scale traffic sign and traffic light dataset with accurate 3D positioning and temporally consistent 3D bounding boxes of traffic management objects from up to 200 meters away. The dataset contains additional attributes such as traffic light state, traffic light mask type, traffic sign type, and occlusion. The application areas are 3D traffic lights and sign detection for autonomous driving.

관련 논문 0편

Bosch Small Traffic Lights Dataset

BSTLD
BSTLD 설명 보기

This dataset contains 13427 camera images at a resolution of 1280x720 pixels and contains about 24000 annotated traffic lights. The annotations include bounding boxes of traffic lights as well as the current state (active light) of each traffic light. The camera images are provided as raw 12bit HDR images taken with a red-clear-clear-blue filter and as reconstructed 8-bit RGB color images. The RGB images are provided for debugging and can also be used for training. However, the RGB conversion process has some drawbacks. Some of the converted images may contain artifacts and the color distribution may seem unusual. Source: BSTLD

관련 논문 0편

Damaged Traffic Signs Dataset

Damaged Traffic Signs Dataset 설명 보기

Description: <a href="https://gts.ai/dataset-download/damaged-traffic-signs-dataset/" target="_blank">👉 Download the dataset here</a> The Damaged Traffic Signs Dataset focuses on Portuguese traffic signs captured under a variety of conditions, providing a comprehensive collection of images showcasing signs in both their regular state and with various forms of damage or deterioration. The dataset is designed to support research and development efforts in the areas of traffic sign detection, classification, and damage recognition for AI and machine learning models. Dataset Features: This dataset includes traffic signs that have undergone several types of wear and tear, presenting realistic conditions encountered on the road. The goal is to offer a broad set of visual challenges for training models that can accurately identify and classify traffic signs, even in less-than-ideal circumstances. Download Dataset Conditions Captured: The dataset encapsulates a range of deteriorations and flaws, including but not limited to: Discoloration: Signs with faded colors due to prolonged exposure to sunlight or environmental factors. Paint Peeling: Signs with paint coming off, making it harder to detect their design elements. Scratches and Surface Damage: Signs damaged by vehicles or debris, which obscures the visibility of key information. Bending or Warping: Traffic signs that are bent or physically distorted, altering their appearance from the standard design. Rust: Older signs suffering from rust, particularly those made from metal. Graffiti or Stickers: Signs vandalized with graffiti, stickers, or other forms of defacement. Partial Occlusion: Signs partially blocked by objects such as tree branches, poles, or other obstructions. Design and Manufacturing Flaws: Some images capture signs with design flaws or imperfections resulting from poor manufacturing. Reflections and Glare: Signs affected by reflections from sunlight or vehicle headlights, which create visibility challenges. Blurring: Signs captured under motion or with out-of-focus camera settings, simulating real-world challenges in detection. Environmental Wear: The dataset also captures signs under various environmental factors such as rain, dirt, and dust. Additional Information: Resolution: Images are captured at various resolutions, ensuring diversity in image quality. Weather Conditions: The dataset includes images taken in different weather conditions, such as sunny, rainy, and foggy days, which add further complexity. Lighting Conditions: Photographs were taken under a mix of lighting conditions, including bright daylight, evening, and low-light situations. Applications: This dataset is an excellent resource for developing and training machine learning models for: Traffic sign recognition and detection systems. Damage classification for traffic sign maintenance and road safety assessment. Autonomous vehicle navigation and obstacle detection. Government or municipal agencies for traffic infrastructure analysis. This dataset is sourced from Kaggle.

관련 논문 0편

Indian Traffic Sign Image Dataset

Indian Traffic Sign Image Dataset 설명 보기

This dataset is collected by Datacluster Labs. To download full dataset or to submit a request for your new data collection needs, please drop a mail to: sales@datacluster.ai This dataset is an extremely challenging set of over 2000+ original Indian Traffic Sign images captured and crowdsourced from over 400+ urban and rural areas, where each image is manually reviewed and verified by computer vision professionals at DC Labs. ### Dataset Features - Dataset size : 2000+ - Captured by : Over 400+ crowdsource contributors - Resolution : 100% of images HD and above (1920x1080 and above) - Location : Captured with 400+ cities accross India - Diversity : Various lighting conditions like day, night, varied distances, view points etc. - Device used : Captured using mobile phones in 2020-2021 - Usage : Traffic sign detection, Self-driving systems, traffic detection, sign detection, etc. ### Available Annotation formats COCO, YOLO, PASCAL-VOC, Tf-Record *To download full datasets or to submit a request for your dataset needs, please drop a mail on sales@datacluster.ai . Visit www.datacluster.ai to know more.

관련 논문 0편

Traffic Management and Optimization

Traffic Management and Optimization 설명 보기

Problem Statement <a href="https://globaltechnosol.com/case_studies/Traffic-Management-and-Optimization/" target="_blank">👉 Download the case studies here</a> Urban areas worldwide face increasing traffic congestion due to rapid urbanization and rising vehicle density. A city’s transportation department struggled with inefficient traffic flow, leading to longer travel times, increased fuel consumption, and higher emissions. Traditional traffic management systems were reactive rather than predictive, requiring a smarter, data-driven solution to address these issues. Challenge Developing an intelligent traffic management system involved tackling several challenges: Collecting and processing real-time traffic data from multiple sources, including sensors, cameras, and GPS devices. Predicting traffic patterns and optimizing signal timings to reduce congestion. Ensuring scalability to handle the growing urban population and vehicle density. Solution Provided An AI-powered traffic management system was developed using advanced algorithms, real-time data analytics, and IoT sensors. The solution was designed to: Monitor and analyze traffic flow in real time using data from IoT-enabled sensors and connected vehicles. Optimize traffic signal timings dynamically to minimize congestion at key intersections. Provide actionable insights to city planners for long-term infrastructure improvements. Development Steps Data Collection Installed IoT sensors at intersections and leveraged data from traffic cameras and connected vehicles to gather real-time traffic data. Preprocessing Cleaned and processed the collected data to identify patterns, peak congestion times, and traffic bottlenecks. AI Model Development Developed machine learning models to predict traffic flow and congestion based on historical and real-time data. Implemented optimization algorithms to adjust traffic signal timings dynamically. Simulation & Validation Tested the system in simulated environments to evaluate its effectiveness in reducing congestion and improving traffic flow. Deployment Deployed the system across key urban areas, integrating it with existing traffic control systems for seamless operation. Continuous Monitoring & Improvement Established a feedback loop to refine models and algorithms based on real-world performance and new traffic data. Results Decreased Traffic Congestion The system reduced congestion by 25%, resulting in smoother traffic flow across the city. Improved Travel Times Optimized traffic management led to significant reductions in average travel times for commuters. Enhanced Urban Mobility Efficient traffic flow improved access to key areas, benefiting both residents and businesses. Reduced Environmental Impact Lower congestion levels minimized fuel consumption and greenhouse gas emissions, contributing to sustainability goals. Scalable and Future-Ready The system’s modular design allowed easy expansion to new areas and integration with emerging transportation technologies.

관련 논문 0편

Traffic Sign Recognition YOLOv8

Traffic Sign Recognition YOLOv8 설명 보기

Description: The Traffic Sign Recognition Dataset is designed to support the development of deep learning models, particularly for object detection and classification. The dataset includes images of various traffic signs, each annotated with bounding boxes and corresponding class labels. These images have been preprocessed for uniform size and pixel normalization, ensuring optimal training conditions for models like YOLOv8. The dataset captures a wide variety of traffic signs, making it ideal for tasks related to traffic safety and autonomous vehicle systems. Download Dataset Applications The dataset is well-suited for training models in autonomous driving, transportation safety, and smart traffic management systems. It can be used in various environments to improve the recognition of traffic signs in different weather conditions, lighting, and angles. This diversity enhances the dataset’s robustness, making it useful for real-time object detection tasks in smart city infrastructure and road safety systems. Dataset Structure Image Annotations: Each traffic sign in the dataset is mark with bounding boxes, allowing precise localization during model training. Class Labels: The dataset includes class labels for different types of traffic signs, such as stop signs, speed limits, and warnings. Preprocessing: The images have been resize and normalize to maintain consistent pixel values, which aids in model training. Use Cases This dataset can be extend beyond traffic sign recognition. It can be used in conjunction with other datasets for multi-class object detection in road environments, facilitating the development of comprehensive autonomous navigation systems. Additionally, the dataset supports research into improving model accuracy in challenging conditions such as low-light, occluded signs, or varying weather. Why Use YOLOv8? YOLOv8 is a highly efficient model for object detection, offering speed and accuracy improvements over its predecessors. The architecture of YOLOv8 enables quick real-time detection of traffic signs with high precision, making this dataset particularly suitable for applications where rapid recognition is essential. Future Improvements Further development of this dataset could involve incorporating more challenging real-world conditions, such as damage or obscured signs, or training models to handle multiple sign types in a single image. The dataset can also be expand to cover more countries, including region-specific signs and regulations. Visit Here: https://gts.ai/dataset-download/traffic-sign-recognition-yolov8/ This dataset is sourced from Kaggle.

관련 논문 0편

Simulated Dataset of UAV Food Delivery using Air Traffic Simulator

UAV Trajectory
UAV Trajectory 설명 보기

The UAV Delievery dataset created to advance the research in drone delivery, contains trajectory details of UAV in different speed, altitude, and wind conditions. The dataset is created from the Truck based "Online Food Delivery Platform" using Open Air Traffic Simulator (ATS) with a UAVTrajectory.py plugin. A pre-processing step is used to select the deliveries under distance 5km, due to battery constraints of UAVs. After the pre-processing, the dataset consists of a total number of 6911 deliveries that are simulated and collected in log files.