Finding a parking spot can be a real drag. For Sai Nikhil Reddy Mettupally, a graduate student at The University of Alabama in Huntsville’s (UAH) Department of Computer Science, it was the light bulb moment to build a tool that uses big data and deep learning to guide drivers to that coveted empty parking spot, The University of Alabama in Huntsville reports.
"The data show that, on a typical day, there is a high chance that students or faculty members will have difficulty getting a parking spot between 11 a.m. and 1 p.m., leading to the wastage of time and fuel, and adding to the pollution of the environment. Hence, finding a parking spot as soon as a person enters the parking lot is essential," Mettupally told The University of Alabama in Huntsville.
Technological solutions for this task typically rely on in-ground sensors, which is an expensive approach. Mettupally instead conceived of a convolutional neural network (CNN) that could sift and sort surveillance camera footage to detect empty spaces. He found an ally in Dr. Vineetha Menon, an Assistant Professor of Computer Science at UAH as well as the university’s Big Data Analytics Lab director, who helped him access the necessary computing power and a parking lot dataset courtesy of the Federal University of Paraná in Brazil.
While Mettupally’s research has garnered awards both within UAH and statewide, the technology still needs a bit of tinkering. For example, the model sometimes fails to differentiate between an empty space and a black car. Mettupally is working to refine the model to avoid these mishaps. "My model has four layers, but I plan to increase it to a greater number of layers and train it with pre-processed images. More focus needs to be put on the pre-processing of the images to improve the results,” Mettupally explained to The University of Alabama in Huntsville.
"I’ll be happy if I can solve a problem that bothers a lot of people and help save their time and resources."
He also has plans to develop a real-time mobile app called InstaPark for UAH campus users. "The app could then be constantly updated based on parking information from the cloud classifier," Mettupally told The University of Alabama in Huntsville. "This would assist both UAH students and employees in managing their time efficiently in finding their closest parking spot, help ease the traffic flow on campus, and provide better parking management services."
While commercialization could someday be lucrative for Mettupally, he sees this work as his duty to turn a constant annoyance into yesterday’s news. "I’ll be happy," he told The University of Alabama in Huntsville, "if I can solve a problem that bothers a lot of people and help save their time and resources."
