UA, Tuscaloosa File Joint Patent to Detect Community Blight
January 27, 2021
The University of Alabama and the City of Tuscaloosa collaborated to create a system that can automatically detect blighted areas in a community, helping prevent issues before they escalate into costly repairs for property owners.
This patent-pending technology will reduce personnel time devoted to inspection, limit potentially harmful interaction on properties and uniformly expand detection to all parts of the city.
"This partnership to create an innovative solution for a real-world challenge shows how public and private organizations can leverage the talent at The University of Alabama to benefit our local community,” said Dr. Russell J. Mumper, UA vice president for research and economic development.
The technology uses images of property captured by cameras mounted on city vehicles, particularly garbage collection trucks, which feed into a computer model trained to spot blighted properties and nuisances. The model provides an assessment and information on potential remedies.
“The City of Tuscaloosa’s standard of excellence is to be the most innovative and effectively managed city in the United States,” Mayor Walt Maddox says, “This innovative technology is a perfect example of how our partnership with The University of Alabama allows us to be more data-driven and effective. I’m proud of the work this team has done so far, and excited to see this technology implemented in our community.”
After a successfully training the machine learning model, UA and the city applied for a patent. The pilot phase of the project continues, with further testing and improvements to the technology to ensure it can effectively expand.
“We are very excited about this unique partnership and the progress made to push this technology to become a tool that can be used by cities and local governments to improve quality of life,” said Dan Blakley, associate vice president for economic and business engagement. “The ingenuity of our faculty extends beyond campus while it enriches the University’s mission of teaching, research and service.”
The inventors of the technology are Dr. Erik Johnson, assistant professor of economics in the Culverhouse College of Business, and Brendan Moore, executive director of urban development for the City of Tuscaloosa.
“This system helps to prevent neighborhood decline in an affordable way using a unique method to collect and analyze data on blighted properties,” Johnson said. “The ability of the model to determine exactly what part of the property is driving the blight score can help inform property owners and lead to low-cost interventions.”
Johnson developed the artificial intelligence that powers the blight analysis using data and images of past blighted properties and code violations to train the computer model.
“The more data deep-learning models are given to analyze, the more effective they become. The city has been great about putting together data from across departments to inform the model,” Johnson said.
The City frequently receives calls about overgrown grass, abandoned vehicles, litter, illegal parking, and appliances or furniture left outside. The new technology can analyze images of properties and highlight issues using a scoring system.
“Efforts to address blight are not new or distinct to Tuscaloosa,” Moore explains, “but it is a constant problem that is difficult to appropriately staff and address. This technology allows us to create early, equitable interventions that can enhance communities, prevent neighborhood decline, and connect underserved populations to social services to generate long-lasting change.”
By placing the cameras on municipal garbage trucks, an entire city can be scanned each week, automating the initial inspections performed now by city staff. This contactless method can minimize potential confrontations between residents and city employees, Moore said.
Early notification can allow the city to connect residents and property owners who need assistance to community service organizations at the onset of a problem, before a cheap fix becomes a contentious and expensive compliance challenge.
“This started in Tuscaloosa, but it can expand and scale to other communities,” Moore said. “This partnership with the University allows us to work out any issues with the system before it is implemented.”