Existing research suggests that LPRs can improve public safety, but the technology’s impact depends on its implementation.
The goal of project is to better understand the public safety impact of automatic license plate readers (LPRs). Use of LPRs has spread rapidly across law enforcement agencies in the United States. While a national survey of law enforcement agencies (LEAs) estimates that approximately 66% of LEAs with more than 100 officers had LPRs by 2016 (Lum et al., 2016), the rapid adoption has taken place in a relatively low information environment. Few rigorous studies have been conducted to understand the efficacy of ALPRs in achieving relevant public safety outcomes or best practices for privacy and data protection.
Existing research suggests that LPRs can be effective for increasing recovery of stolen vehicles and arrests for auto thefts (Koper et al., 2013, 2019, 2021; Ohio State Highway Patrol, 2005; Ozer, 2010; Taylor et al., 2012), and, under certain conditions, may improve clearance rates for auto theft and robbery (Koper & Lum, 2019).
However, several studies exploring the crime prevention value of LPRs have found varied effectiveness based on several factors. These may include volume and concentration of ALPRs deployed, the type of LPR deployed (e.g., fixed vs. mobile), location of use, the types of databases connected to LPR system and how often they are updated, how officers use ALPRs in the field, and agency pursuit and response policies for officers informed about suspects by LPR technology.
Modern LPR systems can use machine learning to capture a variety of additional information beyond license plate information. This may include information about the vehicle (such as vehicle color and type) that could not be systematically identified previously. This additional information may have implications for both how ALPRs are used for investigative purposes and ultimately their impact on public safety. Considering recent improvements in ALPR technology, the current study seeks to expand understanding of the public safety benefits of LPRs through a multi-site data collection and analysis, focused on fixed-location LPR systems in several large law enforcement agencies across the United States.
This current study will be done through multi-site, quasi-experimental assessment. The study also seeks to expand understanding of privacy protections for collected data, agency policies on collected data, and transparency with the community. How agencies share data and the policies that control that information sharing will be explored by the project team.
As of June 2022, 93 law enforcement agencies in 27 states have committed to participating in this national evaluation. Evaluation strategies will be tailored to fit the conditions at each agency. Data collected will be used to evaluate the effect of fixed location LPR implementation at specific agency locations as well as the combined, average effect across all participating agencies.
At the minimum, an assessment in key outcomes (e.g., number of stolen vehicles recovered) will be conducted before and after implementation of the LPR system. Where possible, more sophisticated evaluation design will be used. For agencies that have existing fixed location LPR units in place, the project team will capitalize on the opportunity to study longer-term effects of the technology. Key issues addressed in the evaluation will include:
- The crime reduction impact of LPRs
- The investigative value of LPRs
- How to optimize use and placement of fixed-location LPRs
- Best practices for privacy and data protection
Project Timeline & Next Steps
- August 2022: Collect baseline data about agencies to inform the evaluation design; determine agencies’ involvement.
- September 2022: Conduct meetings with agencies to customize evaluation strategies; finalize evaluation plan for participating agencies.
- December 2022: Data collection on the outputs and outcomes of LPR implementation.
- April 2023: Data analysis and reporting.
Strategic Priority Area(s)
Project Status: Active
Project Period: April 2022 -
Research Design: Quasi-experiment
Research Method(s): Longitudinal study, Secondary data analysis
Strategic Priority Area(s)