Streetview Pothole Map Dataset

## Overview

Streetview Pothole Map Dataset is a dataset for object detection tasks - it contains Pothole annotations for 528 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Potholes reported and filled by the the Department of Public works.

Potholes patched. For the previous seven days in map form, see https://data.cityofchicago.org/d/caad-5j9e.

The Street Pothole Work Orders data consists of closed street potholes inspected and repaired by the New York City Department of Transportation. The dataset includes the pothole’s location, the date it was reported, and date the report was completed.

Pothole Risk Prediction Maps Market Outlook

According to our latest research, the Global Pothole Risk Prediction Maps market size was valued at $1.2 billion in 2024 and is projected to reach $4.6 billion by 2033, expanding at a CAGR of 16.5% during 2024–2033. The primary factor fueling this robust growth is the increasing emphasis on proactive road maintenance and safety management by governments and municipal bodies worldwide. As urbanization accelerates and vehicular traffic intensifies, the demand for advanced predictive analytics to minimize infrastructure damage and enhance commuter safety is surging. The integration of real-time data sources, such as IoT sensors and satellite imagery, with sophisticated AI-driven mapping solutions is transforming the way stakeholders identify, predict, and mitigate pothole risks, resulting in significant cost savings and improved public safety outcomes.

Regional Outlook

North America currently commands the largest share of the global Pothole Risk Prediction Maps market, accounting for over 36% of total market value in 2024. This dominance is attributed to the region's mature infrastructure, early adoption of smart city initiatives, and substantial investments in transportation technology. The United States, in particular, has been at the forefront, with several state and local governments deploying advanced mapping solutions to address aging road networks and reduce maintenance costs. The presence of leading technology vendors, coupled with favorable regulatory frameworks and public awareness campaigns on road safety, further accelerates market penetration. In addition, the integration of pothole risk prediction into broader urban mobility and infrastructure management platforms has become a standard practice among North American municipalities, fostering sustained market expansion.

The Asia Pacific region is poised to experience the fastest CAGR of 19.3% from 2024 to 2033, driven by rapid urbanization, burgeoning vehicle ownership, and significant government investments in smart infrastructure. Countries such as China, India, and Japan are aggressively adopting predictive mapping technologies to cope with the challenges posed by expanding road networks and frequent weather-induced road damage. Strategic public-private partnerships and international collaborations are also fueling the deployment of IoT-enabled sensors and drone-based data collection. The region's large population base and growing focus on digital transformation in public services are expected to propel adoption rates, making Asia Pacific a critical growth engine for the global market in the coming years.

Emerging economies in Latin America and the Middle East & Africa are gradually embracing pothole risk prediction solutions, though adoption remains constrained by budgetary limitations and infrastructural disparities. In these regions, localized demand is primarily driven by urban centers facing acute road maintenance challenges and high accident rates due to potholes. Policy reforms and international funding initiatives are beginning to address these gaps, enabling pilot projects and scaled implementations in select cities. However, challenges such as inconsistent data quality, limited technical expertise, and regulatory hurdles continue to impede broader market uptake. As digital infrastructure matures and public sector awareness grows, these regions are expected to witness steady, albeit incremental, market growth over the forecast period.

Report Scope

This map shows potholes patched in the last seven days, based on the corresponding 311 service requests at https://data.cityofchicago.org/id/7as2-ds3y.

The Chicago Department of Transportation (CDOT) oversees the patching of potholes on over 4,000 miles of arterial and residential streets in Chicago. CDOT receives reports of potholes through the 311 call center and uses a computerized mapping and tracking system to identify pothole locations and efficiently schedule crews. One call to 311 can generate multiple pothole repairs. When a crew arrives to repair a 311 pothole, it fills all the other potholes within the block. Pothole repairs are generally completed within 7 days from the first report of a pothole to 311. Weather conditions, particularly frigid temps and precipitation, influence how long a repair takes. On days when weather is cooperative and there is no precipitation, crews can fill several thousand potholes.

If a previous request is already open for a buffer of 4 addresses the request is given the status of "Duplicate (Open)". For example, if there is an existing CSR for 6535 N Western and a new request is received for 6531 N Western (which is within four addresses of the original CSR) then the new request is given a status of "Duplicate (Open)".

Once the street is repaired, the status in CSR will read “Completed” for the original request and "Duplicate (Closed)" for any duplicate requests. A service request also receives the status of “Completed” when the reported address is inspected but no potholes are found or have already been filled. If another issue is found with the street, such as a “cave-in” or “failed utility cut”, then it is directed to the appropriate department or contractor.

Data Owner: Transportation. Time Period: All open requests and all completed requests since January 1, 2011. Frequency: Data is updated daily.

This map shows the reported locations and status of pothole repairs within Calgary. To reduce duplicate requests, check the map to see if we already have a repair request for a location that concerns you.

This map shows potholes patched in the last seven days, based on the corresponding 311 service requests at https://data.cityofchicago.org/id/7as2-ds3y.

311 Explorer is a web-based mapping tool that uses the City’s open data information to search, filter, and display 311 service requests on public property. You will be able to:

View the various types of service requests on public property that have been generated in a neighborhood, ward or across the city, see the status of service requests, use the map or charts for analysis of neighbourhoods

Use this category to report issues with potholes. Street emergencies 402-444-4919.

Mobile map of the northeastern portion of Potholes State Park, Washington. For use in the Field Maps app by ESRI. Published November 2021.

This feature class represents location of reported potholes along the St. Johns County maintained roadway in 2015. Service Requests and Work Orders were recorded using the County's Computerized Maintenance Management System.Data posted on this site are for reference use only. Data provided are derived from multiple sources with varying levels of accuracy. The St. Johns County GIS Division & the Public Works Department disclaims all responsibility for the accuracy or completeness of the data shown.The Public Works Department makes every effort to produce and publish the most current information possible. These data were produced for information purposes only and NOT as a form of a survey information. No warranties, expressed or implied, are provided for the data therein, its use, or its interpretation.

This is a list of all potholes filled in Syracuse this year. NOTE: Some data from the DuraPatchers is missing because a sensor went down from the beginning of 2018 through February 22, 2018. The Department of Public Works is responsible for filling potholes in the City, both in response to requests from constituents, as well as proactively. A row of data in this dataset is created automatically each time a pothole is filled. GPS units on each Durapatcher truck are signaled when the trigger on the emulsion hose is pulled to begin the filling of a pothole. This dataset was last updated on 07/24/2018

On April 6th, 2018, Mayor Muriel Bowser announced the launch of PaveDC, a comprehensive plan to eliminate all roads in poor condition in Washington, DC by 2024. The PaveDC plan has four priorities: road rehabilitation, road maintenance, alley repair and reconstruction, and sidewalk reconstruction. The map indicates which streets and sidewalks are planned for repair in 2018 and when the repairs have been completed. Each year shortly after the winter season, PotholePalooza is launched – a month-long campaign led by the District Department of Transportation (DDOT) to accelerate pothole repairs across Washington, DC.Please contact the map author, DDOT Performance Analyst Ting Ma at ting.ma@dc.gov if you have questions about this map tool.

This dataset for the semantic segmentation of potholes and cracks on the road surface was assembled from 5 other datasets already publicly available, plus a very small addition of segmented images on our part. To speed up the labeling operations, we started working with depth cameras to try to automate, to some extent, this extremely time-consuming phase.

The main dataset is composed of 4340 (image,mask) pairs at different resolutions divided into training/validation/test sets with a proportion of 3340/496/504 images equal to 77/11/12 percent. This is the dataset used in the SHREC2022 competition and it is the dataset that allowed us to train the neural networks for semantic segmentation capable of obtaining the nice images and videos that you have probably already seen.

Along the main dataset we also release a set of RGB-D videos consisting of 797 RGB clips and as many clips with their disparity maps, captured with the excellent OAK-D cameras we won for being finalists at the OpenCV AI Competition 2021. In an effort to achieve (semi-)automatic labeling for these clips, we postprocessed the disparity maps using classic CV algorithms and managed to obtain 359 binary mask clips. Obviously these masks are not perfect (they cannot be by definition, otherwise the problem of automatic road damage detection would not exist), but nonetheless we believe they are an excellent starting point to create, for example, new data augmentations (creating potholes on "intact road images" belonging to other standard road datasets) or to be used as textures in the creation of 3D scenes from which to extract large amounts of images/masks for the training of neural networks. You can have a preview of what you will find in these clips by watching this video showing the overlay of images and binary masks: http://deeplearning.ge.imati.cnr.it/genova-5G/video/pothole-mix-videos/pothole-mix-rgb-d-overlay-videos-concat.html

Please take a look at the readme file inside the main dataset zipfile to have some more details about the single sub-datasets and their sources.

This map service contains service requests for pothole data reported to the City of Coquitlam.

An interactive dashboard that shows statistical information on pothole repairs. The map demonstrates improved response to repairing potholes from 2016 to 2017. Macon-Bibb County's roads are maintained by the Macon-Bibb County Government Public Works Department. The Public Works Department provides general street and storm sewer repair and maintenance. The Streets Division is responsible for all maintenance of city street including storm sewer maintenance and repair, sidewalk repair, asphalt patching, permit cut repair, Right of Way cutting, Litter pickup, house demolition, as well as laying of pipe. Public Works maintains 1,064+ miles of paved registered roads and 39 miles of unpaved registered roads for a total of 1,074+ miles of registered roads throughout Macon-Bibb County, along with maintenance of various alleyways. Public Works assists with Community Cleanups and has a close affiliation with Keep Macon-Bibb Beautiful with Christmas Tree Recycling, Cherry Blossom Festival etc. This division works closely with other city departments to reduce the expense of hiring outside contractors.For more information about street repairs contact the Public Works Department at 478-621-5888 or visit their website at http://www.maconbibb.us/public-works/.

These maps were developed to support an effort to understand the spatial characteristics of piping plover (Charadrius melodus) nesting habitats. The maps show the expected nesting habitat distributions and piping plover intensity between 2000 and 2021 in the U.S. Prairie Pothole Region.

This dataset was collected using a ZED stereo camera. The road disparity images were estimated using PT-SRP [1]; the disparity transformation algorithm was first introduced in [2], and an advanced version was presented later on in [3].

If you use our dataset for research purposes, please also consider citing the following works: [1] Fan, R., Ai, X. and Dahnoun, N., 2018. Road surface 3D reconstruction based on dense subpixel disparity map estimation. IEEE Transactions on Image Processing, 27(6), pp.3025-3035. [2] Fan, R., Ozgunalp, U., Hosking, B., Liu, M. and Pitas, I., 2019. Pothole detection based on disparity transformation and road surface modeling. IEEE Transactions on Image Processing, 29, pp.897-908. [3] Fan, R. and Liu, M., 2019. Road damage detection based on unsupervised disparity map segmentation. IEEE Transactions on Intelligent Transportation Systems.