Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
7
datasets available to search
ShareScore release 0.9.0
Dataset results
7 results for “traffic detection”
Traffic Detection Datasets
<p><em>Public (anonymized) road traffic detection datasets from Huawei Munich Research Center.</em></p> <p>Traffic detection datasets from a variety of traffic sensors (i.e. induction loops). The data is useful for traffic indexing, dominant flows detection, forecasting traffic patterns, and adjusting stop-light control parameters, i.e. cycle length, offset and split times.</p> <p>There are three datasets:</p> <ul> <li><strong>RM </strong>is a real-life dataset collected in the period of March 2020 from traffic detectors in an area of a Chinese city. The detectors were located in 6 intersections monitoring the traffic on 44 road edges. Each detector was collecting data every 1 second for all the road edges in its radius. In total, 2894174 detections were collected, from 337089 different vehicles.</li> <li><strong>COM </strong>is a synthetic dataset that generated in the same road network as the real-life data RM and RD, with the difference that we included detectors in the 2 intersections where the real scenario didn’t have. Then, we generated equally random trips over the road network. In total we generated 18910 detections from 7500 vehicles.</li> <li><strong>GRID </strong> was created using the SUMO Simulation of Urban Mobility [2]. We randomly generated trips on a 10𝑥10 intersections grid road network using a utility from SUMO that equally generates trips over the road network. Then, running the simulation and using TraCI Traffic Control Interface library [3] we read the simulation data and collect the detections. The simulation collected data include 1806141 detections from 135618 different vehicles.</li> </ul> <p>The datasets were used in the Querying Top-k Dominant Traffic Flows on Large Urban Road Networks [1] paper.</p> <p>[1] Stella Maropaki, Paolo Sottovia, and Stefano Bortoli. 2021. Querying Top-k Dominant Traffic Flows on Large Urban Road Networks. In 2021 24th International Conference on Extending Database Technology (EDBT).</p>
HIKARI-2021: Generating Network Intrusion Detection Dataset Based on Real and Encrypted Synthetic Attack Traffic
<p>Available datasets from the paper Generating Encrypted Network Traffic for Intrusion Detection Datasets.</p> <p>To produce the dataset follow the technical detail in <a href="https://github.com/andreysfc/generating-encrypted-network">github</a></p>
CESNET-TimeSeries24: Time Series Dataset for Network Traffic Anomaly Detection and Forecasting
<h2><strong>CESNET-TimeSeries24: The dataset for network traffic forecasting and anomaly detection</strong></h2> <p>The dataset called CESNET-TimeSeries24 was collected by long-term monitoring of selected statistical metrics for 40 weeks for each IP address on the ISP network CESNET3 (Czech Education and Science Network). The dataset encompasses network traffic from more than 275,000 active IP addresses, assigned to a wide variety of devices, including office computers, NATs, servers, WiFi routers, honeypots, and video-game consoles found in dormitories. Moreover, the dataset is also rich in network anomaly types since it contains all types of anomalies, ensuring a comprehensive evaluation of anomaly detection methods.<br><br>Last but not least, the CESNET-TimeSeries24 dataset provides traffic time series on institutional and IP subnet levels to cover all possible anomaly detection or forecasting scopes. Overall, the time series dataset was created from the 66 billion IP flows that contain 4 trillion packets that carry approximately 3.7 petabytes of data. The CESNET-TimeSeries24 dataset is a complex real-world dataset that will finally bring insights into the evaluation of forecasting models in real-world environments.<br><br></p> <p>Please cite the usage of our dataset as:</p> <blockquote> <p>Koumar, J., Hynek, K., Čejka, T. <em>et al.</em> CESNET-TimeSeries24: Time Series Dataset for Network Traffic Anomaly Detection and Forecasting. <em>Sci Data</em> <strong>12</strong>, 338 (2025). https://doi.org/10.1038/s41597-025-04603-x<br><br>@Article{cesnettimeseries24,<br> author={Koumar, Josef and Hynek, Karel and {\v{C}}ejka, Tom{\'a}{\v{s}} and {\v{S}}i{\v{s}}ka, Pavel},<br> title={CESNET-TimeSeries24: Time Series Dataset for Network Traffic Anomaly Detection and Forecasting},<br> journal={Scientific Data},<br> year={2025},<br> month={Feb},<br> day={26},<br> volume={12},<br> number={1},<br> pages={338},<br> issn={2052-4463},<br> doi={10.1038/s41597-025-04603-x},<br> url={https://doi.org/10.1038/s41597-025-04603-x}<br>}<br><br></p> </blockquote> <p> </p> <h3>Time series</h3> <p>We create evenly spaced time series for each IP address by aggregating IP flow records into time series datapoints. The created datapoints represent the behavior of IP addresses within a defined time window of 10 minutes. The vector of time-series metrics v_{ip, i} describes the IP address ip in the i-th time window. Thus, IP flows for vector v_{ip, i} are captured in time windows starting at t_i and ending at t_{i+1}. The time series are built from these datapoints. </p> <p>Datapoints created by the aggregation of IP flows contain the following time-series metrics:</p> <ul> <li><strong><em>Simple volumetric metrics:</em></strong> the number of IP flows, the number of packets, and the transmitted data size (i.e. number of bytes)</li> <li><strong><em>Unique volumetric metrics:</em></strong> the number of unique destination IP addresses, the number of unique destination Autonomous System Numbers (ASNs), and the number of unique destination transport layer ports. The aggregation of \textit{Unique volumetric metrics} is memory intensive since all unique values must be stored in an array. We used a server with 41 GB of RAM, which was enough for 10-minute aggregation on the ISP network. </li> <li><strong><em>Ratios metrics:</em></strong> the ratio of UDP/TCP packets, the ratio of UDP/TCP transmitted data size, the direction ratio of packets, and the direction ratio of transmitted data size</li> <li><em><strong>Average metrics:</strong></em> the average flow duration, and the average Time To Live (TTL)</li> </ul> <p> </p> <p><strong>Multiple time aggregation: </strong> The original datapoints in the dataset are aggregated by 10 minutes of network traffic. The size of the aggregation interval influences anomaly detection procedures, mainly the training speed of the detection model. However, the 10-minute intervals can be too short for longitudinal anomaly detection methods. Therefore, we added two more aggregation intervals to the datasets--1 hour and 1 day.</p> <p><strong>Time series of institutions:</strong> We identify 283 institutions inside the CESNET3 network. These time series aggregated per each institution ID provide a view of the institution's data. </p> <p><strong>Time series of institutional subnets:</strong> We identify 548 institution subnets inside the CESNET3 network. These time series aggregated per each institution ID provide a view of the institution subnet's data. </p> <p> </p> <h3>Data Records</h3> <p>The file hierarchy is described below:</p> <blockquote> <p>cesnet-timeseries24/</p> <p> |- institution_subnets/</p> <p> | |- agg_10_minutes/<id_institution>.csv</p> <p> | |- agg_1_hour/<id_institution>.csv</p> <p> | |- agg_1_day/<id_institution>.csv</p> <p> | |- identifiers.csv</p> <p> |- institutions/</p> <p> | |- agg_10_minutes/<id_institution_subnet>.csv</p> <p> | |- agg_1_hour/<id_institution_subnet>.csv</p> <p> | |- agg_1_day/<id_institution_subnet>.csv</p> <p> | |- identifiers.csv</p> <p> |- ip_addresses_full/</p> <p> | |- agg_10_minutes/<id_ip_folder>/<id_ip>.csv</p> <p> | |- agg_1_hour/<id_ip_folder>/<id_ip>.csv</p> <p> | |- agg_1_day/<id_ip_folder>/<id_ip>.csv</p> <p> | |- identifiers.csv</p> <p> |- ip_addresses_sample/</p> <p> | |- agg_10_minutes/<id_ip>.csv</p> <p> | |- agg_1_hour/<id_ip>.csv</p> <p> | |- agg_1_day/<id_ip>.csv</p> <p> | |- identifiers.csv</p> <p> |- times/</p> <p> | |- times_10_minutes.csv</p> <p> | |- times_1_hour.csv</p> <p> | |- times_1_day.csv</p> <p> |- ids_relationship.csv<br> |- weekends_and_holidays.csv</p> </blockquote> <p>The following list describes time series data fields in CSV files:</p> <ul> <li><strong>id_time: </strong>Unique identifier for each aggregation interval within the time series, used to segment the dataset into specific time periods for analysis.</li> <li><strong>n_flows: </strong>Total number of flows observed in the aggregation interval, indicating the volume of distinct sessions or connections for the IP address.</li> <li><strong>n_packets: </strong>Total number of packets transmitted during the aggregation interval, reflecting the packet-level traffic volume for the IP address.</li> <li><strong>n_bytes: </strong>Total number of bytes transmitted during the aggregation interval, representing the data volume for the IP address.</li> <li><strong>n_dest_ip: </strong>Number of unique destination IP addresses contacted by the IP address during the aggregation interval, showing the diversity of endpoints reached.</li> <li><strong>n_dest_asn: </strong>Number of unique destination Autonomous System Numbers (ASNs) contacted by the IP address during the aggregation interval, indicating the diversity of networks reached.</li> <li><strong>n_dest_port: </strong>Number of unique destination transport layer ports contacted by the IP address during the aggregation interval, representing the variety of services accessed.</li> <li><strong>tcp_udp_ratio_packets: </strong>Ratio of packets sent using TCP versus UDP by the IP address during the aggregation interval, providing insight into the transport protocol usage pattern. This metric belongs to the interval <0, 1> where 1 is when all packets are sent over TCP, and 0 is when all packets are sent over UDP.</li> <li><strong>tcp_udp_ratio_bytes:</strong> Ratio of bytes sent using TCP versus UDP by the IP address during the aggregation interval, highlighting the data volume distribution between protocols. This metric belongs to the interval <0, 1> with same rule as <em>tcp_udp_ratio_packets</em>.</li> <li><strong>dir_ratio_packets: </strong>Ratio of packet directions (inbound versus outbound) for the IP address during the aggregation interval, indicating the balance of traffic flow directions. This metric belongs to the interval <0, 1>, where 1 is when all packets are sent in the outgoing direction from the monitored IP address, and 0 is when all packets are sent in the incoming direction to the monitored IP address.</li> <li><strong>dir_ratio_bytes: </strong>Ratio of byte directions (inbound versus outbound) for the IP address during the aggregation interval, showing the data volume distribution in traffic flows. This metric belongs to the interval <0, 1> with the same rule as <em>dir_ratio_packets</em>.</li> <li><strong>avg_duration: </strong>Average duration of IP flows for the IP address during the aggregation interval, measuring the typical session length.</li> <li><strong>avg_ttl: </strong>Average Time To Live (TTL) of IP flows for the IP address during the aggregation interval, providing insight into the lifespan of packets.</li> </ul> <p>Moreover, the time series created by re-aggregation contains following time series metrics instead of <strong>n_dest_ip</strong>, <strong>n_dest_asn</strong>, and <strong>n_dest_port</strong>:</p> <ul> <li><strong>sum_n_dest_ip: </strong>Sum of numbers of unique destination IP addresses.</li> <li><strong>avg_n_dest_ip: </strong>The average number of unique destination IP addresses.</li> <li><strong>std_n_dest_ip: </strong>Standard deviation of numbers of unique destination IP addresses.</li> <li><strong>sum_n_dest_asn: </strong>Sum of numbers of unique destination ASNs.</li> <li><strong>avg_n_dest_asn: </strong>The average number of unique destination ASNs.</li> <li><strong>std_n_dest_asn: </strong>Standard deviation of numbers of unique destination ASNs)</li> <li><strong>sum_n_dest_port: </strong>Sum of numbers of unique destination transport layer ports.</li> <li><strong>avg_n_dest_port: </strong> The average number of unique destination transport layer ports.</li> <li><strong>std_n_dest_port: </strong>Standard deviation of numbers of unique destination transport layer ports.</li> </ul> <p> </p> <p>Moreover, files <em>identifiers.csv</em> in each dataset type contain IDs of time series that are present in the dataset. Furthermore, the <em>ids_relationship.csv</em> file contains a relationship between IP addresses, Institutions, and institution subnets. The <em>weekends_and_holidays.csv</em> contains information about the non-working days in the Czech Republic.</p>
German Traffic Sign Detection Benchmark - 3 different types of backdoor patterns added
<p>Datasets are split in Training and Test datasets</p> <p>GTSRB_backdoor_green_1.zip - a green squared pattern sized 1% of the images area is added randomly around the center in an interval of +/-20% of time images width and height</p> <p>GTSRB_backdoor_green_0_5.zip - a green squared pattern sized 0.5% of the images area is added randomly around the center in an interval of +/-20% of time images width and height</p> <p>GTSRB_backdoor_black_1.zip - a black squared pattern sized 1% of the images area is added randomly around the center in an interval of +/-20% of time images width and height</p>
Detection and Estimation of Inundation and Associated Risks Using Traffic and Monitoring Cameras and Image Processing Under Extreme Flooding Conditions
<p>The main objective of this project is to develop an inundation detection and evaluation framework using images from traffic monitoring cameras and reliable flood monitoring under extreme precipitation conditions. This study presents a comparative assessment of image enhancement and segmentation techniques to automatically identify the flash flooding from the low-resolution images taken by traffic-monitoring cameras. Due to inaccurate equipment in severe weather conditions (e.g., raindrops or light refraction on camera lenses), low-resolution images are subject to noises that degrade the quality of information. De-noising procedures are carried out for the enhancement of images by removing different types of noises. After the de-noising, image segmentation is implemented to detect the inundation from the images automatically. In addition, the detection of the inundation using the image segmentation with and without de-noising techniques are compared. The results indicate that among de-noising methods, the Bayes shrink with the thresholding discrete wavelet transform shows the most reliable result. For the image segmentation, the Bayesian segmentation is superior to the others. The results demonstrate that the proposed image enhancement and segmentation methods can be effectively used to identify the inundation from low-resolution images taken in severe weather conditions. A new Bayesian filtering method will be devised and applied to estimate the inundation from low-resolution images that will allow traffic engineers to take preventive or proactive actions to improve the safety of drivers and protect and preserve the transportation infrastructure. This new observation with improved accuracy will enhance our understanding of dynamic urban flooding by filling an information gap in the locations where conventional observations have limitations.</p>
Dataset of Annotated Virtual Detection Line for Road Traffic Monitoring
<p>Annotated Virtual Detection Line (AVDL) dataset is presented for multiple object detection, consisting of 74 108 data files and 74 108 manually annotated files divided into six classes: Vehicles, Trucks, Pedestrians, Bicycles, Motorcycles, and Scooters from the video. The data were captured from real road scenes using 50 video cameras from the leading video camera manufacturers at different road locations and under different meteorological conditions. The AVDL dataset consists of two directories, the Data directory and the Labels directory. Both directories provide the data as NumPy arrays. The dataset can be used to train and test deep neural network models for traffic and pedestrian detection, recognition, and counting.</p>
German Traffic Sign Detection Benchmark (resized to 128x128)
<p>German Traffic Sign Detection Benchmark Dataset</p> <p>All images resized to 128x128</p> <p>Split in Training and Test datasets according to source</p> <p> </p> <p>Original data available under: http://benchmark.ini.rub.de/?section=gtsrb</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.