Ipsotek’s AIVA Engine takes a leap forward with natural language search

Ipsotek, an Eviden business, and a foremost provider of AI-powered video analytics, announced a significant advancement in its core Artificial Intelligence Video Analytics (AIVA) engine.

This groundbreaking development empowers users of the VISuite platform to search and identify objects within videos using Natural Language Search (NLS).

VISuite and NLS

VISuite AI, also known as Eviden Computer Vision platform software stack, provides users with the ability to enhance safety, security, operations, and business intelligence through real-time alerts and a dashboard.

Natural Language Search (NLS) is a technology that empowers users to search for information using everyday spoken language. In contrast, AI models within computer vision platforms rely on predefined criteria and options for detecting objects and behaviours. By leveraging NLS, VISuite users can now broaden their detection criteria to include keywords and descriptions of their choice, providing enhanced flexibility and coverage for their use cases.

Improving video analytics

“We are thrilled to announce this major step forward for AIVA,” said Dr. Boghos Boghossian; Chief Technology Officer, and Global Sales Director at Ipsotek.

“The AIVA engine has always been at the forefront of video analytics, and this capability marks a significant leap forward. Users can now leverage the power of natural language to search videos, fulfilling a key aspect of our original vision of AIVA; when it understands our spoken words.”

Beneficial updates to AIVA

This update to AIVA within Ipsotek’s VISuite offers a multitude of benefits for users including:

• Effortless Object Search: Users can instantly search and locate objects within videos by simply providing a natural language description, such as “find the red car” or “a person holding a black bag.”
• Enhanced Scenario-Based Rules: Ipsotek’s patented Scenario Based Rule engine is further enhanced with AIVA’s new natural language capabilities. Users can now create intricate video analysis in seconds, without any prior training required.
• Human-like Object Detection: The advanced capabilities of AIVA allow for the identification of objects that might be difficult for the human eye to perceive, particularly in crowded or complex scenes.
• Unlocking New Use Cases: This revolutionary development in AIVA opens doors to a vast array of potential applications, empowering users to address unforeseen challenges and optimise video analytics across diverse industries.

Innovation of AI and computer vision

“This update to AIVA within VISuite exemplifies Ipsotek's dedication to continuous innovation and pushing the boundaries of AI, computer vision, and big data.’’ said Dr. Boghossian. “By leveraging the ever-evolving power of AIVA, Ipsotek empowers its clients to unlock the true potential of computer vision.’’