Bridging the gap between criminology and computer vision: A multidisciplinary approach to curb gun violence

Abstract

Gun violence significantly threatens tens of thousands of people annually in the United States. This paper proposes a multidisciplinary approach to address this issue. Specifically, we bridge the gap between criminology and computer vision by exploring the applicability of firearm object detection algorithms to the criminal justice system. By situating firearm object detection algorithms in situational crime prevention, we outline how they could enhance the current use of closed-circuit television (CCTV) systems to mitigate gun violence. We elucidate our approach to training a firearm object detection algorithm and describe why its results are meaningful to scholars beyond the realm of computer vision. Lastly, we discuss limitations associated with object detection algorithms and why they are valuable to criminal justice practices.