Road Segmentation Dataset

This dataset comprises a collection of images captured through DVRs (Digital Video Recorders) showcasing roads. Each image is accompanied by segmentation masks demarcating different entities (road surface, cars, road signs, marking and background) within the scene.

💴 For Commercial Usage: To discuss your requirements, learn about the price and buy the dataset, leave a request on our website to buy the dataset

The dataset can be utilized for enhancing computer vision algorithms involved in road surveillance, navigation, and intelligent transportation systemsand and in autonomous driving systems.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2Fb0789a0ec8075d9c7abdb0aa9faced59%2FFrame%2012.png?generation=1694606364403023&alt=media" alt="">

DATASETS WITH VEHICLES :

• License Plates - 1 209 438 OCR Plates
• Car Object Detection & Tracking
• Vehicle Images & Segmentation
• Parking Space Detection & Classification Dataset
• Videos around cars

Dataset structure

• images - contains of original images of roads
• masks - includes segmentation masks created for the original images
• annotations.xml - contains coordinates of the polygons, created for the original photo

Data Format

Each image from images folder is accompanied by an XML-annotation in the annotations.xml file indicating the coordinates of the polygons and labels . For each point, the x and y coordinates are provided.

Сlasses:

• road_surface: surface of the road,
• marking: white and yellow marking on the road,
• road_sign: road signs,
• car: cars on the road,
• background: side of the road and surronding objects

Example of XML file structure

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2Fa74a4214f4dd89a35527ef008abfc151%2Fcarbon.png?generation=1694608637609153&alt=media" alt="">

Roads Segmentation might be made in accordance with your requirements.

🧩 This is just an example of the data. Leave a request here to learn more

🚀 You can learn more about our high-quality unique datasets here

keywords: road surface, road scene, off-road, vehicle segmentation dataset, semantic segmentation for self driving cars, self driving cars dataset, semantic segmentation for autonomous driving, car segmentation dataset, car dataset, car images, car parts segmentation, self-driving cars deep learning, cctv, image dataset, image classification, semantic segmentation

Authors introduce the Vehicle Dataset for YOLO, a meticulously curated collection of labeled images that assembles a diverse range of vehicle types, rendering it a valuable resource for computer vision and object detection enthusiasts. This dataset consists of a total of 3000 images, with 2100 designated for train and 900 for valid. It has been constructed by amalgamating data from various sources, including Kaggle, the Stanford Car Dataset, and web scraping, ensuring a rich and varied set of examples. This dataset encompasses six distinct classes: car, threewheel, bus, truck, motorbike, and van, presenting numerous opportunities for the development and refinement of YOLO-based models tailored for vehicle detection tasks.

Vehicle Detection Image Dataset

Introduction

Welcome to the Vehicle Detection Image Dataset! This dataset is meticulously curated for object detection and tracking tasks, with a specific focus on vehicle detection. It serves as a valuable resource for researchers, developers, and enthusiasts seeking to advance the capabilities of computer vision systems.

Objective

The primary aim of this dataset is to facilitate precise object detection tasks, particularly in identifying and tracking vehicles within images. Whether you are engaged in academic research, developing commercial applications, or exploring the frontiers of computer vision, this dataset provides a solid foundation for your projects.

Preprocessing and Augmentation

Both versions of the dataset undergo essential preprocessing steps, including resizing and orientation adjustments. Additionally, the Apply_Grayscale version undergoes augmentation to introduce grayscale variations, thereby enriching the dataset and improving model robustness.

1. Apply_Grayscale

• This version comprises grayscale images and is further augmented to enhance the diversity of training data.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F14850461%2F4f23bd8094c892d1b6986c767b42baf4%2Fv2.png?generation=1712264632232641&alt=media" alt="">

2. No_Apply_Grayscale

• This version includes images without applying grayscale augmentation.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F14850461%2Fbfb10eb2a4db31a62eb4615da824c387%2Fdetails_v1.png?generation=1712264660626280&alt=media" alt="">

Data Formats

To ensure compatibility with a wide range of object detection frameworks and tools, each version of the dataset is available in multiple formats:

1. COCO
2. YOLOv8
3. YOLOv9
4. TensorFlow

These formats facilitate seamless integration into various machine learning frameworks and libraries, empowering users to leverage their preferred development environments.

Real-Time Object Detection

In addition to image datasets, we also provide a video for real-time object detection evaluation. This video allows users to test the performance of their models in real-world scenarios, providing invaluable insights into the effectiveness of their detection algorithms.

Getting Started

To begin exploring the Vehicle Detection Image Dataset, simply download the version and format that best suits your project requirements. Whether you are an experienced practitioner or just embarking on your journey in computer vision, this dataset offers a valuable resource for advancing your understanding and capabilities in object detection and tracking tasks.

Citation

If you utilize this dataset in your work, we kindly request that you cite the following:

Parisa Karimi Darabi. (2024). Vehicle Detection Image Dataset: Suitable for Object Detection and tracking Tasks. Retrieved from https://www.kaggle.com/datasets/pkdarabi/vehicle-detection-image-dataset/

Feedback and Contributions

I welcome feedback and contributions from the Kaggle community to continually enhance the quality and usability of this dataset. Please feel free to reach out if you have suggestions, questions, or additional data and annotations to contribute. Together, we can drive innovation and progress in computer vision.

SpaceKnow uses satellite (SAR) data to capture activity in electric vehicles and automotive factories.

Data is updated daily, has an average lag of 4-6 days, and history back to 2017.

The insights provide you with level and change data that monitors the area which is covered with assembled light vehicles in square meters.

We offer 3 delivery options: CSV, API, and Insights Dashboard

Available companies Rivian (NASDAQ: RIVN) for employee parking, logistics, logistic centers, product distribution & product in the US. (See use-case write up on page 4) TESLA (NASDAQ: TSLA) indices for product, logistics & employee parking for Fremont, Nevada, Shanghai, Texas, Berlin, and Global level Lucid Motors (NASDAQ: LCID) for employee parking, logistics & product in US

Why get SpaceKnow's EV datasets?

Monitor the company’s business activity: Near-real-time insights into the business activities of Rivian allow users to better understand and anticipate the company’s performance.

Assess Risk: Use satellite activity data to assess the risks associated with investing in the company.

Types of Indices Available Continuous Feed Index (CFI) is a daily aggregation of the area of metallic objects in square meters. There are two types of CFI indices. The first one is CFI-R which gives you level data, so it shows how many square meters are covered by metallic objects (for example assembled cars). The second one is CFI-S which gives you change data, so it shows you how many square meters have changed within the locations between two consecutive satellite images.

How to interpret the data SpaceKnow indices can be compared with the related economic indicators or KPIs. If the economic indicator is in monthly terms, perform a 30-day rolling sum and pick the last day of the month to compare with the economic indicator. Each data point will reflect approximately the sum of the month. If the economic indicator is in quarterly terms, perform a 90-day rolling sum and pick the last day of the 90-day to compare with the economic indicator. Each data point will reflect approximately the sum of the quarter.

Product index This index monitors the area covered by manufactured cars. The larger the area covered by the assembled cars, the larger and faster the production of a particular facility. The index rises as production increases.

Product distribution index This index monitors the area covered by assembled cars that are ready for distribution. The index covers locations in the Rivian factory. The distribution is done via trucks and trains.

Employee parking index Like the previous index, this one indicates the area covered by cars, but those that belong to factory employees. This index is a good indicator of factory construction, closures, and capacity utilization. The index rises as more employees work in the factory.

Logistics index The index monitors the movement of materials supply trucks in particular car factories.

Logistics Centers index The index monitors the movement of supply trucks in warehouses.

Where the data comes from: SpaceKnow brings you information advantages by applying machine learning and AI algorithms to synthetic aperture radar and optical satellite imagery. The company’s infrastructure searches and downloads new imagery every day, and the computations of the data take place within less than 24 hours.

In contrast to traditional economic data, which are released in monthly and quarterly terms, SpaceKnow data is high-frequency and available daily. It is possible to observe the latest movements in the EV industry with just a 4-6 day lag, on average.

The EV data help you to estimate the performance of the EV sector and the business activity of the selected companies.

The backbone of SpaceKnow’s high-quality data is the locations from which data is extracted. All locations are thoroughly researched and validated by an in-house team of annotators and data analysts.

Each individual location is precisely defined so that the resulting data does not contain noise such as surrounding traffic or changing vegetation with the season.

We use radar imagery and our own algorithms, so the final indices are not devalued by weather conditions such as rain or heavy clouds.

→ Reach out to get a free trial

Use Case - Rivian:

SpaceKnow uses the quarterly production and delivery data of Rivian as a benchmark. Rivian targeted to produce 25,000 cars in 2022. To achieve this target, the company had to increase production by 45% by producing 10,683 cars in Q4. However the production was 10,020 and the target was slightly missed by reaching total production of 24,337 cars for FY22.

SpaceKnow indices help us to observe the company’s operations, and we are able to monitor if the company is set to meet its forecasts or not. We deliver five different indices for Rivian, and these indices observe logistic centers, employee parking lot, logistics, product, and prod...

This dataset is designed for the detection of persons and cars in surveillance camera footage. It can be utilized for various useful applications, including:

• Security Systems: Enhancing security measures by accurately detecting and tracking persons and cars in real-time surveillance videos.
• Traffic Monitoring: Analyzing traffic patterns, estimating congestion levels, and optimizing traffic flow by detecting and counting cars on roads or at intersections.
• Safety Enhancement: Identifying potential hazards and ensuring public safety by detecting unauthorized access or suspicious activities involving persons and cars.
• Crowd Management: Monitoring crowded areas and public events to ensure safety, identify crowd density, and estimate crowd movement by detecting and tracking persons.
• Parking Systems: Optimizing parking lot management by detecting available parking spots and monitoring the entry and exit of vehicles.
• Smart Cities: Contributing to the development of smart city infrastructure by integrating the detection of persons and cars into intelligent systems for efficient urban planning and management.

This dataset is based on images collected from various sources, including:

https://universe.roboflow.com/radoslaw-kawczak/virat-ve02s

https://universe.roboflow.com/seminar-object-detection/cars-o1ljf

With this dataset, you can train and develop machine learning models capable of accurately detecting persons and cars, thus empowering surveillance and security systems with advanced object recognition capabilities.

https://i.imgur.com/ztezlER.png" alt="Image example">

Overview

This dataset contains 627 images of various vehicle classes for object detection. These images are derived from the Open Images open source computer vision datasets.

This dataset only scratches the surface of the Open Images dataset for vehicles!

https://i.imgur.com/4ZHN8kk.png" alt="Image example">

Use Cases

• Train object detector to differentiate between a car, bus, motorcycle, ambulance, and truck.
• Checkpoint object detector for autonomous vehicle detector
• Test object detector on high density of ambulances in vehicles
• Train ambulance detector
• Explore the quality and range of Open Image dataset

Tools Used to Derive Dataset

https://i.imgur.com/1U0M573.png" alt="Image example">

These images were gathered via the OIDv4 Toolkit This toolkit allows you to pick an object class and retrieve a set number of images from that class with bound box lables.

We provide this dataset as an example of the ability to query the OID for a given subdomain. This dataset can easily be scaled up - please reach out to us if that interests you.

Vehicle Detection Dataset

This dataset is designed for vehicle detection tasks, featuring a comprehensive collection of images annotated for object detection. This dataset, originally sourced from Roboflow (https://universe.roboflow.com/object-detection-sn8ac/ai-traffic-system), was exported on May 29, 2025, at 4:59 PM GMT and is now publicly available on Kaggle under the CC BY 4.0 license.

Overview

• Purpose: The dataset supports the development of computer vision models for detecting various types of vehicles in traffic scenarios.
• Classes: The dataset includes annotations for 7 vehicle types:
  • Bicycle
  • Bus
  • Car
  • Motorbike
  • Rickshaw
  • Truck
  • Van
• Number of Images: The dataset contains 9,440 images, split into training, validation, and test sets:
  • Training: Images located in ../train/images
  • Validation: Images located in ../valid/images
  • Test: Images located in ../test/images
• Annotation Format: Images are annotated in YOLOv11 format, suitable for training state-of-the-art object detection models.
• Pre-processing: Each image has been resized to 640x640 pixels (stretched). No additional image augmentation techniques were applied.

Source and Creation

This dataset was created and exported via Roboflow, an end-to-end computer vision platform that facilitates collaboration, image collection, annotation, dataset creation, model training, and deployment. The dataset is part of the ai-traffic-system project (version 1) under the workspace object-detection-sn8ac. For more details, visit: https://universe.roboflow.com/object-detection-sn8ac/ai-traffic-system/dataset/1.

Usage

This dataset is ideal for researchers, data scientists, and developers working on vehicle detection and traffic monitoring systems. It can be used to: - Train and evaluate deep learning models for object detection, particularly using the YOLOv11 framework. - Develop AI-powered traffic management systems, autonomous driving applications, or urban mobility solutions. - Explore computer vision techniques for real-world traffic scenarios.

For advanced training notebooks compatible with this dataset, check out: https://github.com/roboflow/notebooks. To explore additional datasets and pre-trained models, visit: https://universe.roboflow.com.

License

The dataset is licensed under CC BY 4.0, allowing for flexible use, sharing, and adaptation, provided appropriate credit is given to the original source.

This dataset is a valuable resource for building robust vehicle detection models and advancing computer vision applications in traffic systems.

Here are a few use cases for this project:

1. Urban Traffic Management: The "Hong Kong vehicle detection" model can be used in improving the city's traffic management system by identifying the ratio and type of vehicles on the road at any given time. This can aid in congestion prediction and reduction.

2. Public Transport Planning: By analyzing the frequency of taxis, mini buses, trams, and other public transport vehicles, authorities and transportation companies can optimize their service routes and schedules.

3. Smart Parking Solutions: This model can detect and monitor the types of vehicles in parking areas, aiding in the design of parking space allocation according to vehicle classes.

4. Surveillance and Security: The model can be integrated into surveillance systems, helping to identify and track suspicious activities involving vehicles in the city.

5. Autonomous Vehicle Training: The data derived from the model can be used in training autonomous vehicles to detect and recognize different types of vehicles, making self-driving technology safer for urban environments.

Key information about US Number of Registered Vehicles

• US Number of Registered Vehicles was reported at 284,614,269 Unit in Dec 2023.
• This records an increase from the previous number of 283,400,986 Unit for Dec 2022.
• US Number of Registered Vehicles data is updated yearly, averaging 93,949,852 Unit from Dec 1910 to 2023, with 114 observations.
• The data reached an all-time high of 284,614,269 Unit in 2023 and a record low of 468,500 Unit in 1910.
• US Number of Registered Vehicles data remains active status in CEIC and is reported by CEIC Data.
• The data is categorized under World Trend Plus’s Global Economic Monitor – Table: No of Registered Vehicles: Annual.

ITS JPO's Connected Vehicle Pilot Deployment Program integrates connected vehicle research concepts into practical and effective elements to enhance existing operational capabilities. Data were collected throughout each pilot to facilitate independent evaluations of the use of connected vehicle technology on real roadways. To encourage additional study and reuse of these data, ITS DataHub has partnered with each pilot site to make sanitized and anonymized tabular and non-tabular data from these projects available to the public. This article gives you a brief overview of what each pilot focused on and what types of CV Pilot data and tools are available on ITS DataHub.

The Dataset

A collection of images of parking lots for vehicle detection, segmentation, and counting. Each image is manually labeled with pixel-wise masks and bounding boxes localizing vehicle instances. The dataset includes about 250 images depicting several parking areas describing most of the problematic situations that we can find in a real scenario: seven different cameras capture the images under various weather conditions and viewing angles. Another challenging aspect is the presence of partial occlusion patterns in many scenes such as obstacles (trees, lampposts, other cars) and shadowed cars. The main peculiarity is that images are taken during the day and the night, showing utterly different lighting conditions.

We suggest a three-way split (train-validation-test). The train split contains images taken during the daytime while validation and test splits include images gathered at night. In line with these splits we provide some annotation files:

train_coco_annotations.json and val_coco_annotations.json --> JSON files that follow the golden standard MS COCO data format (for more info see https://cocodataset.org/#format-data) for the training and the validation splits, respectively. All the vehicles are labeled with the COCO category 'car'. They are suitable for vehicle detection and instance segmentation.

train_dot_annotations.csv and val_dot_annotations.csv --> CSV files that contain xy coordinates of the centroids of the vehicles for the training and the validation splits, respectively. Dot annotation is commonly used for the visual counting task.

ground_truth_test_counting.csv --> CSV file that contains the number of vehicles present in each image. It is only suitable for testing vehicle counting solutions.

Citing our work

If you found this dataset useful, please cite the following paper

@inproceedings{Ciampi_visapp_2021, doi = {10.5220/0010303401850195}, url = {https://doi.org/10.5220%2F0010303401850195}, year = 2021, publisher = {{SCITEPRESS} - Science and Technology Publications}, author = {Luca Ciampi and Carlos Santiago and Joao Costeira and Claudio Gennaro and Giuseppe Amato}, title = {Domain Adaptation for Traffic Density Estimation}, booktitle = {Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications} }

and this Zenodo Dataset

@dataset{ciampi_ndispark_6560823, author = {Luca Ciampi and Carlos Santiago and Joao Costeira and Claudio Gennaro and Giuseppe Amato}, title = {{Night and Day Instance Segmented Park (NDISPark) Dataset: a Collection of Images taken by Day and by Night for Vehicle Detection, Segmentation and Counting in Parking Areas}}, month = may, year = 2022, publisher = {Zenodo}, version = {1.0.0}, doi = {10.5281/zenodo.6560823}, url = {https://doi.org/10.5281/zenodo.6560823} }

Contact Information

If you would like further information about the dataset or if you experience any issues downloading files, please contact us at luca.ciampi@isti.cnr.it

The number of new and used vehicles and the sales dollars respectively sold by month.

MDOT MVA’s Customer Connect modernization project, implemented in July 2020, has increased the amount of data that is collected and used to calculate car sales. This data is updated in real time and may fluctuate based on external factors, including electronic submissions from dealers and other vendors.

This dataset shows counts of transactions associated with authorizing vehicles to be used on public roads, commonly referred to as “buying tabs” or “buying tags”. The data includes registration activity by fuel type, county, primary use class, and date. This is comparable to the Fee Distribution Report #13, that is titled "Motor Vehicle Registration By Class and County".

This dataset contains information about vehicles (or units as they are identified in crash reports) involved in a traffic crash. This dataset should be used in conjunction with the traffic Crash and People dataset available in the portal. “Vehicle” information includes motor vehicle and non-motor vehicle modes of transportation, such as bicycles and pedestrians. Each mode of transportation involved in a crash is a “unit” and get one entry here. Each vehicle, each pedestrian, each motorcyclist, and each bicyclist is considered an independent unit that can have a trajectory separate from the other units. However, people inside a vehicle including the driver do not have a trajectory separate from the vehicle in which they are travelling and hence only the vehicle they are travelling in get any entry here. This type of identification of “units” is needed to determine how each movement affected the crash. Data for occupants who do not make up an independent unit, typically drivers and passengers, are available in the People table. Many of the fields are coded to denote the type and location of damage on the vehicle. Vehicle information can be linked back to Crash data using the “CRASH_RECORD_ID” field. Since this dataset is a combination of vehicles, pedestrians, and pedal cyclists not all columns are applicable to each record. Look at the Unit Type field to determine what additional data may be available for that record. The Chicago Police Department reports crashes on IL Traffic Crash Reporting form SR1050. The crash data published on the Chicago data portal mostly follows the data elements in SR1050 form. The current version of the SR1050 instructions manual with detailed information on each data elements is available here. Change 11/21/2023: We have removed the RD_NO (Chicago Police Department report number) for privacy reasons.

Road Vehicle Count This data set is sourced from Dundee City Council’s Public Space Camera Surveillance System . It shows a count of road vehicles in 8 specified areas across Dundee. The data set shows a snapshot of road vehicles within these areas every Monday, Wednesday and Saturday during the period 1pm-2pm.This data is experimental and subject to further refinement. Please note that due the nature of CCTV cameras at times data may not be collected as specified above. Therefore, caution should be exercised when analysing data and drawing conclusions from this data set.CCTV datasets contain information on object detections taken from a selection of the CCTV cameras throughout Dundee City. CCTV images are translated into object counts, objects counted include ‘person’, ‘car’, ‘bicycle’, ‘bus’, ‘motorcycle', 'truck, ‘pickup truck 'and ‘van’. The data is generated and owned by Dundee City Council. Copyright © Dundee City Council 2022. This dataset is available for use under the Open Government Licence.Background information about the Dundee CCTV cameras including a map showing the location of the cameras is available on the Dundee City Council website and can be accessed using the following link:https://www.dundeecity.gov.uk/service-area/city-development/sustainable-transport-and-roads/dundees-public-space-camera-surveillance-system

Motor Trend Car Road TestsDescriptionThe data was extracted from the 1974 Motor Trend US magazine, and comprises fuel consumption and 10 aspects of automobile design and performance for 32 automobiles (1973–74 models).FormatA data frame with 32 observations on 11 variables.1 - mpg: Miles/(US) gallon2 - cyl: Number of cylinders3 - disp: Displacement (cu.in.)4 - hp: Gross horsepower5 - drat: Rear axle ratio6 - wt: Weight (1000 lbs)7 - qsec: 1/4 mile time8 - vs: Engine shape (0 = v-shaped, 1 = straight)9 - am: Transmission (0 = automatic, 1 = manual)10 - gear: Number of forward gears11 - carb: Number of carburettorsSourceHenderson and Velleman (1981), Building multiple regression models interactively. Biometrics, 37, 391–411.

Radar cars with outsourced driving cover eight eight regions of metropolitan France: Normandy, Brittany, Pays-de-la-Loire, and Centre-Val de Loire, Nouvelle-Aquitaine, Bourgogne-Franche-Comté, Grand-Est, Hauts de France. The other five metropolitan areas are checked by radar cars driven by a police officer or gendarme. Radar cars with outsourced driving run on routes and time slots set by the prefects according to local accident criteria. Such vehicles with an automated control system shall remain the property of the State. They have equipment capable of reading speed limitation signs allowing the radar to operate autonomously, without any intervention from the driver of the vehicle. The published dataset shall provide the measurement of the speeds of vehicles controlled on the move and recorded by the on-board ceinemometer which shall incorporate the technical margin of the equipment. This dataset partially covers the roads of the metropolitan territory. Metadata: These data correspond to the checks carried out by radar cars with outsourced driving. These checks shall record the speed of all vehicles crossed in approach and overtaking. Each statement shall contain: the speed of the vehicle checked, including the technical margin of the equipment, the maximum authorised speed at the checkpoint and the date/time and location of the check. Only the finding of the infringement is automated. The validation of the established offence and the drawing up of the corresponding report remain the responsibility of a judicial police officer under the supervision of the officer of the Public Prosecutor’s Office and the Public Prosecutor’s Office of the RENNES Judicial Court. Measures outside the control area: The GPS receiver of the control device is likely to generate some technical errors. These very small numbers of errors are not corrected in the dataset and can therefore lead to outliers. The checks carried out are therefore excluded from criminal treatment. **Measures observed in Ile de France: ** The road network in the Ile de France region is not controlled by outsourced driving radar cars. The data concerning the department of Val d'Oise (95) correspond to data from vehicles tested by the industrialist in that department, and do not ultimately generate any notice of contravention.

Total Vehicle Sales in the United States decreased to 15.30 Million in October from 16.40 Million in September of 2025. This dataset provides the latest reported value for - United States Total Vehicle Sales - plus previous releases, historical high and low, short-term forecast and long-term prediction, economic calendar, survey consensus and news.