U.S. flag

An official website of the United States government, Department of Justice.

Dot gov

The .gov means it’s official.
Federal government websites always use a .gov or .mil domain. Before sharing sensitive information online, make sure you’re on a .gov or .mil site by inspecting your browser’s address (or “location”) bar.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

CPD FY2014 Optimizing the Use of Video Technology to Improve Criminal Justice Outcomes

Award Information

Award #
2014-R2-CX-K002
Location
Congressional District
Status
Open
Funding First Awarded
2014
Total funding (to date)
$1,070,179

Description of original award (Fiscal Year 2014, $528,957)

This award was competitively made in response to a proposal submitted by the City of Chicago to a National Institute of Justice FY 2014 solicitation, "Optimizing the Use of Video Technology to Improve Criminal Justice Outcomes." Chicago proposes to undertake a comprehensive, quantitative, and data-driven optimization of key aspects of video technology and its use in policing. The project will leverage Chicago's vast video surveillance network, noted as the largest such integrated platform in the United States, and its data clearinghouse CLEAR system. The proposed project incorporates a unique and emerging policing strategy known as predictive policing, which constitutes the application of data analytics to police resource allocation and management. Through this established predictive capability, the proposed study seeks to identify data-driven locations for camera resources to reduce crime. Chicago proposes to develop approaches to systematically optimize three major design elements: (1) camera placement and density, (2) camera monitoring, and (3) the use of video analytics. The first will use retrospective statistical and machine-learning analyses of CPD's camera installation and crime data to measure the effect on crime of camera location and density to develop an optimum strategy for placing cameras. The second will statistically optimize the way in which cameras are monitored using prediction models to determine which cameras should be watched at which times for maximum benefit. The third will involve a Request for Demonstrations to quantitatively evaluate commercial video analytics tools to determine the statistical performance of various analytics paradigms in real-world application. The proposed project utilizes both retrospective and prospective experimental designs. The retrospective method is to mine data from Chicago's noteworthy CLEAR system and explore pre/post impacts of camera installation into different areas. The prospective method is to identify areas where mobile cameras (PODS) can be deployed to reduce crime. This deployment will be data-driven and conducted on a real-time/ass-needed basis depending on crime dynamics. Differences pre/post treatment will be determined through econometric modeling. Chicago also proposes to develop a database of video sequences for use in training officers to monitor cameras and perform statistical evaluations, and to develop future enhancements to video analytics technology. This project will be funded incrementally, with the effort funded in FY14 representing the first phase. ca/ncf

The initial award was competitively made in response to a proposal submitted by the City of Chicago to a National Institute of Justice FY 2014 solicitation, “Optimizing the Use of Video Technology to Improve Criminal Justice Outcomes.” Chicago proposes to undertake a comprehensive, quantitative, and data-driven optimization of key aspects of video technology and its use in policing. The project will leverage Chicago’s vast video surveillance network, noted as the largest such integrated platform in the United States, and its data clearinghouse CLEAR system. The proposed project incorporates a unique and emerging policing strategy known as predictive policing, which constitutes the application of data analytics to police resource allocation and management. Through this established predictive capability, the proposed study seeks to identify data-driven locations for camera resources to reduce crime. Chicago proposes to develop approaches to systematically optimize three major design elements: (1) camera placement and density, (2) camera monitoring, and (3) the use of video analytics. The first will use retrospective statistical and machine-learning analyses of CPD’s camera installation and crime data to measure the effect on crime of camera location and density to develop an optimum strategy for placing cameras. The second will statistically optimize the way in which cameras are monitored using prediction models to determine which cameras should be watched at which times for maximum benefit. The third will involve a Request for Demonstrations to quantitatively evaluate commercial video analytics tools to determine the statistical performance of various analytics paradigms in real-world application. The proposed project utilizes both retrospective and prospective experimental designs. The retrospective method is to mine data from Chicago’s noteworthy CLEAR system and explore pre/post impacts of camera installation into different areas. The prospective method is to identify areas where mobile cameras (PODS) can be deployed to reduce crime. This deployment will be data-driven and conducted on a real-time/as-needed basis depending on crime dynamics. Differences pre/post treatment will be determined through econometric modeling. Chicago also proposes to develop a database of video sequences for use in training officers to monitor cameras and perform statistical evaluations, and to develop future enhancements to video analytics technology. At the time of the initial award, the decision was made to fund this effort incrementally. This is funding for the 2nd phase of the project, and is the first supplement for this award.

This project contains a research and/or development component, as defined in applicable law.

nca/ncf

Date Created: September 14, 2014