ROCHESTER, N.Y. (WROC) — An RIT professor is partnering with the Rochester Police Department to use machine-learning techniques to analyze body-worn camera footage to improve police training.
According to RIT, Professor Ernest Fokoue of the School of Mathematical Sciences received a $1 million grant from the Department of Justice and RPD to conduct the study for the next three years.
Since the cameras were implemented in 2016, RPD has approximately 500 body-worn cameras for personnel. Professor Faokoue believes that, because the program has massive amounts of data to analyze, it would be better for artificial intelligence to search the data rather than people.
The goals of the project are to produce datasets from a model scanning the footage, video for RPD to analyze for various tactics, and several algorithms to transcribe camera audio, flag words, compare reports to footage, and detect bias from RPD officers.
“The hope is that this is as objective as it gets,” said Fokoue. “The camera doesn’t decide what was happening at the scene, so the idea is to analyze what it picks up in an objective way. We hope to see patterns emerging through natural-language processing and to share the findings with other police departments around the country.”
Adrian Martin, a data analyst for RPD, said that this project will help improve the department’s body-worn camera program since there’s already too much footage for review.
“Professor Fokoue is recognized internationally as a leader in the field of statistical machine learning, and we have enjoyed working with him for the past several years on other projects,” said Martin. “The current grant-funded project will help RPD improve upon our already successful body-worn camera program by using our vast amount of footage for training, compliance, and increasing our transparency to the public.”
More information about the Rochester Police Department’s body-worn camera program can be found on the department’s website.