Enhancing camera surveillance using computer vision: a research note (1808.03998v1)

Abstract: $\mathbf{Purpose}$ - The growth of police operated surveillance cameras has out-paced the ability of humans to monitor them effectively. Computer vision is a possible solution. An ongoing research project on the application of computer vision within a municipal police department is described. The paper aims to discuss these issues. $\mathbf{Design/methodology/approach}$ - Following the demystification of computer vision technology, its potential for police agencies is developed within a focus on computer vision as a solution for two common surveillance camera tasks (live monitoring of multiple surveillance cameras and summarizing archived video files). Three unaddressed research questions (can specialized computer vision applications for law enforcement be developed at this time, how will computer vision be utilized within existing public safety camera monitoring rooms, and what are the system-wide impacts of a computer vision capability on local criminal justice systems) are considered. $\mathbf{Findings}$ - Despite computer vision becoming accessible to law enforcement agencies the impact of computer vision has not been discussed or adequately researched. There is little knowledge of computer vision or its potential in the field. $\mathbf{Originality/value}$ - This paper introduces and discusses computer vision from a law enforcement perspective and will be valuable to police personnel tasked with monitoring large camera networks and considering computer vision as a system upgrade.