Focus of Attention (FoA)
Focus of Attention (FoA) introduces a new concept in video monitoring and brings to the user a more intuitive way to consume information about potential security events.
The FoA interface shows a comprehensive topology of your entire camera population, with nodes that represent each camera, grouped in a honeycomb formation according to how cameras are organized in the Site View (system tree) in Avigilon Control Center (ACC).
Powered by Avigilon cameras and appliances with self-learning and next-generation analytics, the FoA interface uses artificial intelligence to detect and flag events that may require your attention, highlighting them visually in color-coded nodes to indicate different levels of importance:
- Blue: Motion Detected
- Teal: Unusual Motion Detected or Analytic Event
- Yellow: Unusual Activity Detected, Face Watch List Match Event, License Plate Watch List Match Event, or No Face Mask Detected
- Red: Alarm
For operators, this provides a clean and simple display to verify security event notifications. With just a simple mouse hover over the illuminated node, operators can preview the live video or click into the node to expand it for a closer review and replay of the event.
Avigilon Appearance Search™ Video Analytics Technology
Avigilon Appearance Search™ video analytics technology is a sophisticated deep learning AI search engine for video. It sorts through hours of video with ease, to quickly locate a specific person or vehicle of interest by entering physical descriptions, uploading a photo, or by finding an example within recorded video. Appearance Search can improve incident response time and enhance forensic investigations by helping operators compile robust video evidence, create a powerful narrative of events, and reveal a vehicle or individual’s route or last-known location.
Integrated with Avigilon Control Center (ACC) software, Avigilon cameras with self-learning video analytics and select Avigilon Network Video Recorders (NVRs).
INITIATE SEARCHES BASED ON PHYSICAL DESCRIPTIONS
Allows operators to search for a person by selecting certain specific physical descriptions, including clothing color, gender and age categorization.
SEARCH ACROSS MULTIPLE SITES
Initiate a search for a person or vehicle of interest across one site, then continue the search for the same subject of interest by seamlessly transitioning from one site to the next site that uses the same version of ACC software.
FACE ANALYTICS INCLUDED IN SEARCH
Incorporating the unique characteristics of a person’s face enables the Appearance Search technology to understand that it is searching for the same person, even if items such as their clothing change over time.
PLAYBACK, BOOKMARK AND EXPORT TOOLS
Build a comprehensive set of video evidence from multiple video sources, to create a powerful narrative of events.
Two Ways to Build Your Avigilon AI-Powered Solution
1. AVIGILON INTEGRATED SOLUTION
Enable Appearance Search by combining Avigilon H4 cameras with self-learning video analytics with our NVRs that are pre-loaded and pre-configured with ACC software.
2. ONVIF®-COMPLIANT SOLUTION
Evolve your legacy Avigilon and third-party ONVIF-compliant camera systems with the Avigilon AI Appliance, adding patented self-learning video analytics and Appearance Search when connected to ACC 7 or ACC 6 software.
AI-powered facial recognition technology
AI-powered facial recognition technology, within Avigilon Control Center (ACC), helps you accelerate response times by quickly identifying people of interest. Facial recognition offers the context to make better informed decisions that empower you to respond to events proactively.
Customers using our AI-powered technologies can have a significant impact on society. That’s why we take a more rigorous approach to the application of AI that extends beyond the fundamental tenets of fairness, privacy, understand-ability and reliability. The use of facial recognition in our technology is ‘assistive’ in that we only use it to assist humans in performing tasks they are already authorized and allowed to do. When applied correctly, AI is an incredibly powerful tool that can be used to increase the effectiveness of physical security systems, deliver on business outcomes and improve safety.
Secure Watch Lists
People of interest are identified based on one or more secure watch lists managed by authorized users at your organization. Users can populate and manage multiple watch lists by either adding faces from Appearance Search, uploading reference images, or finding appearances of the person through recorded video. The Identity Retention settings also allow face match events and Appearance Search metadata to be aged out ahead of video if desired.
Robust controls within Avigilon’s facial recognition technology governs the accessibility and retention of watch list data. Authorized users are able to add, edit, and manipulate watch lists, while also adjusting the retention periods of watch list profiles.
Alarms For Watch List Match Events
Augment watch list(s) with alarms that provide operators greater context for people of interest entering a site. If a watch list match is found, operators can be notified either using the Focus of Attention interface or through ACC™ alarms using armed panels or the alarm view. ACC will display the video image that triggered the alarm and the reference image from the watch list, enabling operators to verify the match and act quickly.
Available For Analytic Cameras and Optimized For H5A Platform Cameras
Avigilon cameras licensed for facial recognition technology have the ability to detect faces. ACC matches the face comparisons to identify potential matches against the configured face watch list(s).
Cameras That Can Be Licensed For Facial Recognition Technology
Licenses can be purchased to enable facial recognition technology for general purpose security systems. This enables deployment across as many cameras as possible, rather than just a limited number of specially-positioned cameras, and helps increase the likelihood of detecting a person of interest.
Easy To Install
Avigilon is the first video management software vendor to add native facial recognition technology that is easy to deploy, highly scalable and affordable. In the future, Avigilon’s facial recognition technology will be further developed with expanded functionalities for greater versatility.
License Plate Recognition (LPR) Analytics
Avigilon LPR analytics automatically reads license plate information from vehicles, linking it to live and recorded video. This enables security operators to search and quickly find specific captured license plate video for verification and investigation.
Create and import several license plate watch lists so that ACC™ software can provide you with security alerts, helping you take decisive action when needed.
Our LPR analytics recognize and search license plates with high accuracy. It is easy to configure and use, with broad regional and country support including North America, Europe, Japan, Australia and the United Kingdom.
The data privacy protection features of ACC software enable you to restrict access and set automatic retention time and deletion rules for LPR data.
Self-Learning Video Analytics
Through the use of advanced pattern-based analytics and teach-by-example technology, Avigilon video analytics are designed to increase the productivity of security personnel while making monitoring more affordable and efficient.
KEY FEATURES AND BENEFITS
- Efficient installation and ongoing accuracy
- Pattern-based classification and tracking technology
- Teach-by-example technology
- Lower false alarm rates
- Broad variety of devices
- Integrated with Avigilon Control Center (ACC)™
- Compatible with IP or analog cameras
- Idle scene mode
- Powerful forensics
- Cost effective
- No licensing required
Avigilon’s self-learning analytics extends the effectiveness of your security personnel by providing effective monitoring and enabling proactive, real-time response from your team. Built from the ground up to manage high-definition video, Avigilon offers analytics embedded in Avigilon cameras up to 5K (16 MP) resolution.
ADVANCED PATTERN-BASED ANALYTICS
Avigilon’s advanced video pattern detection technology is able to accurately recognize the movements of people and vehicles while ignoring motion not relevant to a scene. Embedded into cameras up to 5K (16 MP), the system’s ability to constantly learn reduces false positives and helps ensure alerts are meaningful, which avoids wasted time and improves efficiencies.
Our teach-by-example object classifier technology enables users to provide feedback about the accuracy of alarm events generated by Avigilon devices. Rather than decreasing analytics sensitivity to reduce false alarms, the feedback trains the device, increasing the accuracy of the analytics used to determine which alarms are real and which are false to further improve a low false-positive alarm rate. Over time, the system learns the scene and is able to prioritize important events based on user feedback. This increases sensitivity to conditions that are of concern while reducing false alarms to keep the focus on what matters
Unusual Activity Detection (UAD)
Unusual Activity Detection (UAD) provides new edge-based intelligence that uses advanced AI technology. It is designed to enable the detection of atypical activities, such as people and vehicles traveling at faster speeds or are in unusual locations and alert operators.
FOCUS OF ATTENTION INTERFACE
Focus of Attention (FOA) is a cutting-edge user interface for live video monitoring that leverages AI and video analytics technology such as UAD to help increase operator effectiveness. By visually highlighting the unanticipated, it provides an overview of anomalous activity so you can verify the event and quickly determine the appropriate response.
FILTERED RECORDED TIMELINE SEARCH
Helps you quickly review large amounts of video by filtering ACC’s timeline to only highlight the periods where Unusual Activity Detection (UAD) events have occurred.
EMBEDDED ON H5A PLATFORM CAMERAS
UAD technology is embedded in the Avigilon H5A camera line, offering high-powered AI capabilities on our flagship line of cameras.
UNUSUAL ACTIVITY DETECTION AND UNUSUAL MOTION DETECTION – WHAT’S THE DIFFERENCE?
Both are edge-based, intelligent technologies that distinguish between typical and atypical events by continuously learning from observation of scenes over time. Where Unusual Activity Detection (UAD) is object-aware and detects the atypical behavior of learned objects like people and vehicles, Unusual Motion Detection (UMD) technology continuously learns what a typical scene looks like, then detects and flags unusual motions that deviate from that model.
|UNUSUAL ACTIVITY DETECTION (UAD)||UNUSUAL MOTION DETECTION (UMD)|
|Object aware with the ability to determine if behaviors are usual on a per-object type basis|
Presents unusual activity for classified objects (people or vehicles)
Highlights atypical behavior such as unusual speed or location
|Highlights anomalous motion based on learned models of what a typical scene looks like|
Offers edge-intelligence on budget-friendly cameras
Highlights atypical motions such as speed, direction, or location
Unusual Motion Detection (UMD)
Unusual Motion Detection (UMD) is an advanced AI technology that brings a new level of automation to security. Without any predefined rules or setup, UMD technology is able to continuously learn what typical activity in a scene looks like, and then detect and flag unusual motion. This allows operators to filter through large amounts of recorded video faster when using Avigilon Control Center (ACC) video management software, as it flags atypical events that may need further investigation, helping to reduce hours of work to minutes.
FOCUS OF ATTENTION
A new ACC™ 7 interface that leverages AI-powered deep learning video analytics and UMD technology to determine actionable information and help ensure critical events don’t go unnoticed.
Helps you quickly search through large amounts of video when using ACC™ software by flagging events that may need further investigation, helping to reduce hours of work to minutes.
EMBEDDED ON H4 PLATFORM CAMERAS
Next-Generation Video Analytics
Our most advanced analytics technology uses neural networks to power self-learning video analytics, delivering improved accuracy in both perimeter protection and in crowded, indoor environments.
IMPROVED DETECTION SPEED AND ACCURACY
Added processing power enables the tracking and classification of over 50 objects. Previous analytics classified objects only when they were moving, now objects are additionally classified if they remain stationary.
EXPANDED OBJECT CLASSIFICATION
Avigilon video analytics go beyond people and vehicles to include car, truck, bus, motorcycle, and bicycle.
IMPROVED ANALYTIC EVENT GENERATION AND APPEARANCE SEARCH RESULTS
More processing power enhances Avigilon Appearance Search™ technology by expanding the ability to search for a person or vehicle in both crowded and indoor environments.
CREATED TO EVOLVE
In the future, Avigilon’s Next-Generation Video Analytics will be enhanced to support more classifications, unusual object activity and face applications.