Aviglon’s Appearance Search technology has been designed to use ‘deep learning’ techniques associated with artificial intelligence to assist in the identification and swift retrieval of video footage which is relevant to an investigation or management of an on-going event. The technology can be accessed via the manufacturer’s ACC (Avigilon Control Center) VMS software.
One of the biggest drawbacks with intelligent video analytics in recent years has been the problems faced by users managing the sheer volume of data generated by these advanced solutions.
Avigilon’s Appearance Search technology enhances the level of security at a site by enabling end users to quickly locate targets of interest, such as specific persons or vehicles, across an entire site. This capability can not only improve incident response times, but additionally makes post-event investigations simpler and more thorough.
The way that Appearance Search can enhance forensic investigations is by enabling operators to quickly locate footage of an event, plus any other associated footage, thus creating a full overview of events, regardless of where and when they happened.
Avigilon Appearance Search technology allows operators to collate footage with ease. The technology scans many hours worth of recorded footage, and using advanced algorithms and artificial intelligence it identifies relevant video data to help track a person or vehicle. This helps to identify routes taken while in the protected area, and can also identify previous visits and last-known locations.
By way of an example, if an asset such as a computer has been removed from a viewed scene, the operator can identify the region in the scene where the item previously was. Using a thumbnail search they can quickly identify the last time when the asset was present. By ‘drilling down’ with regards to time periods they can quickly identify the moment when the asset was removed.
Once they have a video image of the perpetrator they can then ‘select’ that person and request all existing footage which includes them. The technology will then deliver thumbnails of people it has identified as being the suspect. Clicking on the thumbnails will allow the operator to view the video clips.
Where video clips of interest are found, the operator can flag these, and the Appearance Search technology will use these to further filter results. It also creates a timeline of the various clips, assisting in the creation of a trail of events leading up to and following an incident.
In effect, Appearance Search allows operators to ‘click’ a person or vehicle, in the say way that a link on a website would be clicked, and that will bring up all recorded instances of that person or vehicle from across the entire surveillance system, regardless of which camera they been recorded by.
As more incidences are added, the technology is better able to find even occasional appearances in the video. These are often evidential elements that an operator simply ‘scanning’ video feeds will invariably miss, which highlights the importance of Appearance Search.