BRS Labs - Products

AISight™

The Next Generation of Video Analytics Software

The AISight™ Cognitive Video Analytics™ software takes visual input from either a live camera or recorded video, learns what activities and behaviors are normal, and generates real-time alerts that notify appropriate security personnel of potentially threatening behaviors. Unlike rules-based video-analytics software, the intelligent AISight solution identifies threats and behaviors that were not previously defined or anticipated, and it does so with fewer false positives. In test after test, AISight has achieved a false-positive rate and overall accuracy previously unseen in the video-analytics industry.

AISight™ consists of the following modular components:

The Video Analysis Engine (VAE) uses input from multiple sources to create a 2.5D visual model of the scene without the need for security personnel to define “trip lines,” newly defined threats, and other criteria required by current video-analytics software. The VAE continuously refines its model over time, allowing it to detect, track, and classify more behaviors and threats with greater accuracy.
The Machine Learning Engine (MLE) uses advanced learning technology based on human cognition to build behavior pattern models called hypocepts™, or hypothetical concepts. No human operator is required to define or train the software to recognize objects, terrain, or scenarios or to detect anomalous behavior.
The System Manager provides administrative functionality for multiple AISight™ analysis servers, controls how AISight™ issues alerts and to whom, and displays archived alerts.
The Operator Console provides operators with real-time views and notifications of alerts, displays live feeds for closer analysis, and manages the frame-by-frame observations of objects and behaviors from any standard desktop computer.

Easily Integrates Into Existing Video Environments

The standards-based AISight™ software seamlessly integrates with existing video-surveillance environments by providing compatibility with a wide range of third-party surveillance applications, data sources, and video-management software and devices. AISight™ supports the Real Time Streaming Protocol (RTSP) for video streaming and a plethora of application and device interfaces, including XML, SOAP, Web Services, JAVA, and Windows.

Adaptive Learning Capabilities Deliver Even More Value over Time

In addition to the cost and scalability benefits derived from automatically learning any new environment without requiring human input or guidance, AISight™ continues to deliver superior value over time because of its capability to adapt to changes in the scene or changes in behaviors over time. AISight™ is constantly self-calibrating and self-improving to continuously provide the best analysis of potentially threatening behaviors and to keep security personnel as accurately informed and proactive as possible.

Click Here to Learn more about Cognitive Video Analytics™, the technology powering AISight™.

		AISight™ The Next Generation of Video Analytics Software The AISight™ Cognitive Video Analytics™ software takes visual input from either a live camera or recorded video, learns what activities and behaviors are normal, and generates real-time alerts that notify appropriate security personnel of potentially threatening behaviors. Unlike rules-based video-analytics software, the intelligent AISight solution identifies threats and behaviors that were not previously defined or anticipated, and it does so with fewer false positives. In test after test, AISight has achieved a false-positive rate and overall accuracy previously unseen in the video-analytics industry. AISight™ consists of the following modular components: The Video Analysis Engine (VAE) uses input from multiple sources to create a 2.5D visual model of the scene without the need for security personnel to define “trip lines,” newly defined threats, and other criteria required by current video-analytics software. The VAE continuously refines its model over time, allowing it to detect, track, and classify more behaviors and threats with greater accuracy. The Machine Learning Engine (MLE) uses advanced learning technology based on human cognition to build behavior pattern models called hypocepts™, or hypothetical concepts. No human operator is required to define or train the software to recognize objects, terrain, or scenarios or to detect anomalous behavior. The System Manager provides administrative functionality for multiple AISight™ analysis servers, controls how AISight™ issues alerts and to whom, and displays archived alerts. The Operator Console provides operators with real-time views and notifications of alerts, displays live feeds for closer analysis, and manages the frame-by-frame observations of objects and behaviors from any standard desktop computer. Easily Integrates Into Existing Video Environments The standards-based AISight™ software seamlessly integrates with existing video-surveillance environments by providing compatibility with a wide range of third-party surveillance applications, data sources, and video-management software and devices. AISight™ supports the Real Time Streaming Protocol (RTSP) for video streaming and a plethora of application and device interfaces, including XML, SOAP, Web Services, JAVA, and Windows. Adaptive Learning Capabilities Deliver Even More Value over Time In addition to the cost and scalability benefits derived from automatically learning any new environment without requiring human input or guidance, AISight™ continues to deliver superior value over time because of its capability to adapt to changes in the scene or changes in behaviors over time. AISight™ is constantly self-calibrating and self-improving to continuously provide the best analysis of potentially threatening behaviors and to keep security personnel as accurately informed and proactive as possible. Click Here to Learn more about Cognitive Video Analytics™, the technology powering AISight™.
Home \| Careers \| Contact \| Products \| Solutions \| Advantages ©2008 Behavioral Recognition Systems