Crime Scene Post Event Analysis

The Objective: After a terrorist attack or criminal act is committed, law enforcement’s top priority is to identify the perpetrators as quickly as possible in order to protect the public from further harm and to bring these individuals to justice. In today’s high-tech mobile society, the amount of video and photographic evidence that is readily available is staggering. Investigators need to shorten the amount of time and manpower required to review and analyze the thousands of hours of video surveillance recordings, cell phone videos and photographs that are being collected from the public. Every hour that can be saved in identifying the perpetrators may be critical in successfully apprehending the person(s) of interest.
MXSERVER facial identification in crowd.

MXSERVER Facial Identification in Crowd


The Problem: Today’s video surveillance systems and cell phones can contain thousands of hours of video and tens of thousands of photographs. Investigators are currently manually reviewing this type of content, spending days, weeks and even months viewing this content. This manual process is hugely manpower intensive, tedious and expensive. To make the problem even more challenging, video and image files consume a huge amount of storage and may be saved in a myriad of video and photo image file formats.

The Solution: Tygart’s MXSERVER™ System is currently being used by law enforcement and intelligence agencies who investigate acts of terrorism and other crimes where large amounts of video and photo evidence has been collected. Investigators can batch load video surveillance and photograph evidence into the MXSERVER system, which automatically detects faces and indexes the content so it can be searched using facial recognition technology. Once the video content has been processed, MXSERVER displays a timeline view of extracted faces that can be quickly scanned and reviewed to locate suspicious subjects. This saves investigators immense amounts of time, avoiding the need to watch every second of each video. When a person of interest is located, MXSERVER uses powerful facial recognition technology to search all indexed videos and photographs to find additional instances where the suspect was seen in videos or photographs. Investigators can then quickly piece together where potential suspects have been seen over time and at different locations. To determine the identity of a suspect, MXSERVER can also search digital “watchlist” databases containing pictures of previously known persons-of-interest. MXSERVER is built upon a cloud computing platform and can be scaled to meet the processing demands of large investigative task forces, intelligence agencies and computer forensics laboratories.

Benefits/Value Proposition: Investigators and analysts no longer have to watch video and view photographs to find and extract images of persons of interest. Using MXSERVER, investigators can quickly preview the content containing faces. MXSERVER’s powerful facial search capability enables investigators to find other instances where a person of interest is depicted within the indexed content.

MXSERVER reduces the amount of manpower required to analyze, manage and disseminate huge volumes of video surveillance and photographs. MXSERVER can process video and photo collections in hours that otherwise would take investigators and forensic examiners days to manually review.

MXSERVER’s face search and link diagramming capability enable investigators and analysts to identify unknown subjects and connect-the-dots related to criminal, gang and/or terrorist networks.

End User Profiles: Law enforcement Investigators, Intelligence Analysts, and Forensic Examiners