Shreveport Reporter

“Smart city” efforts are enabled by LSU Shreveport (LSUS)  artificial intelligence (AI) expertise and student innovation combining  high and low tech. Computer vision could soon be leveraged by the city’s  largest service fleet—about three dozen garbage trucks.

Keith Hanson, chief technology officer for the City of Shreveport,  was sitting at his desk sorting through bids. He’d been tasked by his  boss, Mayor Adrian Perkins, to make Shreveport a better place to live by  investing in so-called “smart city” 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.

“What I quickly found was that there’s no commoditized ‘smart city’  product, right? There’s no top company you go to for every need,” Hanson  said. “I can buy a sensor for $2,000 or a camera for $3,000, but I’d  need hundreds of these and an integrated solution to make it all work.  And since we’re government, companies try to overcharge. So, there  seemed to be no way for us as a mid-size city to become a smart city on  the budget we had. That’s when I reached out to LSUS.”

Smart city projects can be thought of as large-scale implementations  of the Internet of Things, or IoT, where sensors and cameras are  networked to provide real-time status updates on everything from traffic  and road repairs to water quality and pollution. What results is  massive amounts of public data that must be analyzed and cross-linked in  an effective way to become meaningful.

City of Shreveport Chief Technology Officer Keith Hanson was  interviewed this summer in the LSU Shreveport Cyber Collaboratory about  their ongoing collaboration to retrofit cameras into sleeker boxes with  fewer wires. Photo by Erin Smith, LSUS.

“And what better way to do that than with AI?” said Hanson, who’d  heard that LSUS had begun offering courses in machine learning and deep  learning, the main technologies behind AI, in 2020.

The resulting collaboration between LSUS and the City of Shreveport  combines high-tech with low-tech solutions. First off, LSU students  developed a prototype of an affordable camera box to be mounted on the  side of garbage trucks—Shreveport’s largest service fleet and the only  public vehicle to go to every residential address every single week.  LSUS Computer Science Assistant Professor Subhajit Chakrabarty then  worked with the students to implement machine learning solutions to  automatically identify objects in the captured camera footage—unfinished  road work, heaps of abandoned tires, damaged signs, potholes, cars  parked on grass, cars without license plates, etc.

“If a road repair hasn’t progressed in several months, we usually  have to wait for citizens to make a complaint to even become aware of  the problem,” Hanson said. “LSUS’ machine learning solution could help  us flag that automatically and get us out to fix problems much sooner.”

What’s the only city vehicle that goes to every address every  single week? It’s garbage trucks. By mounting cameras on garbage trucks  and using computer vision, a type of artificial intelligence, the City  of Shreveport could faster and more efficiently respond to potholes and  stalled roadwork, for example, or stolen and illegally parked cars.  (Image generated by AI and featured in LSU’s fall 2022 issue of Working  for Louisiana; the keywords were  /imagine_garbage_truck_camera_smart_city.)

Safety can also be improved using license-plate recognition as well  as general vehicle recognition, based on make, model, color, and perhaps  a unique dent or scratch.

“This could help us deal with hit-and-runs more easily and make it  possible for us to respond faster to amber alerts,” Hanson said.

He recently brought his own IoT team over to the LSUS Cyber  Collaboratory to work on retrofitting camera boxes using Raspberry Pis,  small computers affordable enough to fit the City of Shreveport’s supply  budget, to enable networking.

“Instead of buying a package solution from a third-party vendor for  several thousand dollars, we can work with LSUS to make these camera  boxes ourselves for a few hundred,” Hanson said. “And they’re as small  and sleek as we can make them—no rat’s nest of wires, everything  enclosed in one tight box. That’s really important because residents  care about the stuff we put up on poles and in public view. You put  something ugly up there, wires hanging out, we’re going to get phone  calls.”

One of the students who worked on the garbage truck project is Mark  Lowery, now in his final semester of the LSUS computer science master’s  program. He took Chakrabarty’s machine learning course in the fall of  2020 after a big career shift. Lowery graduated from LSUS with a  bachelor’s degree in English in 2015 and had been working at the public  library.

“A friend of mine from LSUS graduated a year after me with a  bachelor’s in computer science and got a job immediately,” Lowery said.  “With his sign-on bonus, he was able to buy a house and a car. This  impressed me and got me motivated to return to LSUS.”

This summer, Lowery did an internship with General Dynamics Information Technology (GDIT) in Bossier City.

“Switching to computer science has definitely been challenging, but  I’m holding my own,” Lowery said. “I figure, no matter which job I get,  good writing skills will always be an asset, so my English background is  not for naught.”

The garbage truck project also involved Scott Isaacs, former director  of the LSU Cyber Collaboratory. He and Hanson had several conversations  about also using sensors on garbage trucks to map the City of  Shreveport’s digital divide between communities who do or don’t have  reliable internet access. Instead of census tract data, they wanted  block-by-block data to start implementing a municipal internet plan to  provide free or low-cost Wi-Fi to those who need it most. Familiar with  the computer science phrase “garbage in, garbage out” for flawed input  leading to nonsense output, Isaacs and Hanson both saw some comedic  irony in using garbage trucks to produce the best geospatial data the  City of Shreveport could affordably get, reliably and in real time.

“Computer vision means training a machine to see and recognize  objects from images or video,” Isaacs said. “There’s a long annotation  phase where you have to tell the machine what it’s looking at—what’s a  car, what’s a yard, what’s a driveway—and what’s still a car, yard, or  driveway when the camera angle is extreme and there’s shade or rain.  Over time, our algorithms became pretty accurate.”

Based on his experience working with LSUS, Hanson is now gearing  their ongoing collaboration toward a real-time crime center in  Shreveport.

This summer, LSUS hosted City of Shreveport interns for a day of  collaborative work to develop technology to serve a real-time local  crime center. Photo courtesy of the City of Shreveport.

“I didn’t have millions in my budget for a real-time crime center and  not only that—we had no cameras anywhere; we needed cameras on poles,”  Hanson said. “Again, this is where our relationship with LSUS came in.  Together, we can create interesting edge technology that almost no  cities have at this point. I walk into the LSUS Cyber Collaboratory and  I’m like a kid in a candy store. I’m a huge believer in  micromanufacturing, and with LSUS, we can build a box with AI vision for  like $300.”

As Chakrabarty is teaching machine learning to yet another cohort of  LSUS students this fall, he expects many of the hands-on components and  practical solutions the students will develop to be in service of the  City of Shreveport.

“I always encourage my students to choose to do meaningful projects  for social good,” Chakrabarty said. “I see our program growing as Keith  Hanson’s IoT division is growing; maybe six students in my class this  time will be dedicated to Keith’s projects. He provides the use  cases—our students come up with the solutions.”

Assistant Professor of Computer Science Subhajit Chakrabarty  works with LSU Shreveport students on City of Shreveport “smart city”  projects to improve safety and services for residents in the area: “I  always encourage my students to choose to do meaningful projects for  social good.”

Hanson emphasizes how he, working for the City of Shreveport, never  would have the personnel, time, or budget to come up with these  solutions by himself, even when tapping other external resources:

“Most of the time, I’m talking to vendors who want to sell us a  product packaged up in a box that I can’t touch, right? And I’ve got to  spend more dollars to integrate it the way I want to integrate,” Hanson  added. “Commercial, off-the-shelf solutions are either terrible or too  expensive—one of the two, right—but when you’re working with locals who  care about their local economy and their city, it changes the game.  There’s no shortage of city needs that can be solved by enterprising  young people like LSU students.”

Original source can be found here.