Organizations of all kinds are applying analytics to a wide range of problems, and law enforcement is no exception. With the proliferation of video surveillance, video analytics has become more common. But the scope of analytics is now broadening, to include video, speech, and text.
Many cities today are blanketed in video surveillance cameras; some have thousands of video channels in operation. But recording video is one thing; finding critical information fast, in thousands of hours of recorded video, is an entirely different matter. Thanks to the next generation of analytics, content-based forensics is now making this possible. A new, patent-pending video analytics technology called Suspect Search enables law enforcement organizations to locate a specific suspect in surveillance video faster, cutting potential search time from days or hours to minutes or seconds.
Instead of manually scanning hours of video, with no guarantee of accurate results, law enforcement can tell the analytics software who or what to look for, using either an uploaded picture or a user-generated avatar. The software then scans the video and identifies relevant matches. It can also pinpoint the suspect’s path and last known location. Beyond reducing the time and resources used to find a suspect, this technology allows law enforcement to mitigate risk by apprehending suspects faster. Law enforcement could also use the technology in other ways, for example to search for a missing child.
Speech analytics has also improved over the last few years and has become a sought after technology for analyzing emergency center communications. Speech analytics, or speech indexing, lets law enforcement search for spoken words within recorded audio, to quickly find or even link recorded calls, where available data is insufficient to find recordings needed for an investigation. Using keywords, speech analytics can also identify calls that are related to specific types of incidents, locations, or a wide range of other parameters and topics.
Text analytics will become increasingly relevant as PSAPs (which handle 9-1-1 calls for law enforcement) begin to transition to text-to-9-1-1. Text analytics will be needed to search for keyword, phrases, and linkages in text communications, much in the same way that speech analytics operates today.
Correlating Information Using Analytics
Video analytics, License Plate Readers (LPR), and Crowd and Intrusion Detection applications are nothing new, but when used in conjunction with Physical Security Information Management (PSIM) software, can uncover insights for law enforcement through data correlation. For example, say an LPR registered a speeding car in the same vicinity where an intrusion detection alert was raised just moments prior. The ability to correlate these two seemingly separate incidents can help law enforcement officials establish connections that might not otherwise be quickly or easily identified.