City of Memphis: Detecting potholes for better driving experiences

Memphis can now detect potholes and vacant properties with more than 96% accuracy.

Client-Story-CIty of Memphis
Using SpringML (now known as Egen) and Google Cloud Platform to detect indicators of vacant or blighted properties will help Memphis create safer neighborhoods that will be more attractive to businesses and home buyers. Property values and employment will go up, crime will go down, and social services can be more focused and effective.
Mike Rodriguez, CIO, City of Memphis

The City of Memphis wanted to replace its antiquated, time-consuming, and expensive processes for identifying potholes and patterns of urban blight, so it brought in Egen and Google Cloud to solve this challenge using the latest in computer vision and machine learning. 

Memphis has more than 6,800 lane-miles of city streets. Keeping those streets well maintained and safe for residents and visitors is a top priority for the city. Approximately 32,000-work hours each year are spent repairing potholes. 

Like many large cities, Memphis also struggles with vacant and blighted properties. Nearly 15,000 properties in Memphis are likely vacant. Residents’ frustration and concerns over the number of blighted properties made blight eradication a major focus for Memphis. 

Historically, residents reported potholes and blighted properties by calling Memphis 311 or using the app. However, these reports only covered about 20% of the problems.

Recognizing that potholes and vacant properties are often the most visible indicators of whether a city government is doing its job efficiently, the city asked Egen and Google Cloud for ways of applying technology to help address the problems. 

Egen and Google Cloud trained TensorFlow models for machine-learning object detection, using preconfigured AI Platform Deep Learning VM Images on Compute Engine. Egen helped set up cameras and developed a user interface to collect pothole data and automate the 311 ticketing process. Pothole detection accuracy quickly climbed to more than 96% as models were taught to differentiate a pothole from a manhole cover or other objects.

With these technologies in place, Memphis expects to substantially reduce the number of potholes on its streets, creating a better driving experience for residents and visitors. Fewer potholes save the city between $10,000 and $20,000 annually in claims that the city pays out in cases where vehicle damage results from a pothole that was not addressed in a timely manner.

Memphis is able to better prioritize road maintenance based on condition and impact, increasing the efficiency of its road crews. Analyzing video of streets gave the city visibility into issues it was not previously aware of, such as curbs, gutters, and manhole covers that had been mistakenly paved over and needed to be excavated. The machine-learning process is easily transferable to other concerns as well, helping the city identify illegal signs or spools of cable hanging on light posts that could be potentially unsafe.

With help from Egen and Google Cloud, Memphis is now also using technology to address vacant and blighted properties. To predict where homes are starting to become run down and where neighborhood decay is most likely to occur, BigQuery analyzes city property records, tax records, 311 reports, and third-party survey data on-demand. The Egen team created a pilot analysis to begin vacant property protections and developed a user interface tool to interact with the model’s results. Memphis is having success in analyzing predictive trends to combat high rates of abandoned and blighted properties, surpassing 97.5% accuracy.

Scroll to Top