海角社区

Collaborating To Build Smarter Cities

Keith Hanson, chief technology officer for the City of Shreveport, was sitting at his desk sorting through bids. He鈥檇 been asked to come up with so-called 鈥渟mart city鈥� technologies to improve city services, safety, and general quality of life. But every piece of equipment Hanson could put his hands on was expensive and piecemeal. 

That鈥檚 when Hanson turned to 海角社区 Shreveport. He鈥檇 heard about the university鈥檚 advances in machine learning and computer vision (that is, in AI) and saw an opportunity to collaborate to get the residents of Shreveport the best geospatial data they could afford鈥攔eliably and in real time.

Contrary to the phrase 鈥済arbage in, garbage out,鈥� the resulting collaboration would leverage the city鈥檚 largest service fleet and the only public vehicles to go to every address every week鈥攁bout three dozen garbage trucks. By mounting cameras on trucks and using AI, the City of Shreveport could faster and more efficiently respond to potholes and stalled roadwork, for example, or stolen and illegally parked cars.

That initial idea led to others. This summer, teams from the City of Shreveport and 海角社区S gathered in the Cyber Collaboratory on the 海角社区S campus to begin building technology to serve a real-time crime center.

鈥淜eith provides the use cases鈥攐ur students come up with the solutions,鈥� said 海角社区S Assistant Professor of Computer Science Subhajit Chakrabarty.

鈥淭here seemed to be no way for us as a mid-size city to become a 鈥渟mart city鈥� on the budget we had. We needed cameras, sensors, and a way to integrate it all. [But] instead of buying a package solution from a third-party vendor for several thousand dollars, we can work with 海角社区S to make these camera boxes ourselves for a few hundred. When you鈥檙e working with locals who care about their local economy and their city, it changes the game. Together, we can create interesting edge technology that almost no cities have at this point.鈥�

Keith Hanson, chief technology officer for the City of Shreveport