NVISO announces a milestone release of its Neuro SDK for manufacturers building state-of-the-art AI-enabled human-machine interfaces.
Following on from its announcement in July 2022 of successful neuromorphic interoperability with BrainChip Akida, NVISO is now announcing support for two new high performance AI Apps from its Human Behavior AI App catalogue, Gaze and Facial Action Unit Detection. NVISO is making available a full SDK release for manufacturers looking to provide mission critical human-interaction features meeting the most demanding performance, cost, and power budgets.
Lausanne, Switzerland – Friday 16th December, 2022 – nViso SA (NVISO), the leading Human Behavioural Analytics AI company, is pleased to announce that through the porting of additional AI Apps from its catalogue it has further enhanced the range of Human Behavioural AI Apps that it supports on the BrainChip Akida neuromorphic processing platform. These additions include Facial Action Units, Body Pose and Gesture Recognition on top of the Headpose, Facial Landmarks, Gaze and Emotion AI Apps previously announced. This increased capability supports the further deployment of NVISO Human Behavioural Analytics AI software solutions with target applications include Robotics, Automotive, Telecommunication, Infotainment, and Gaming.
The SDK release supports the latest advancements for holistic platform for the analysis of complex emotions with Gaze and up to 58 Facial Action Units:
This latest release of the SDK for use by solution developers will support performance evaluations and then implementation across an increased range of use case scenarios. As noted this support provides for deployment of a wide selection of NVISO’s existing range of real-time, deep learning-based AI Apps such as those used for face detection, gaze, head pose recognition, facial analysis, emotion recognition, object detection, gesture recognition and body pose analysis along with its new state of the art graph-based facial analysis for the analysis of complex emotions.
Implementation of complex emotion analysis using state-of-the-art graph-based facial analysis: As one of the most important affective signals, facial affect analysis (FAA) is essential for developing human-computer interaction systems. Early methods focused on extracting appearance and geometry features associated with human affects while ignoring the latent semantic information among individual facial changes, leading to limited performance and generalization. Recent work attempts to establish a graph-based representation to model these semantic relationships and develop frameworks to leverage them for various FAA tasks.
Designed for non-mobile / non-cloud devices and neuromorphic interoperable and optimised: NVISO AI Apps are specifically designed for resource constrained low-power and low-memory hardware platforms deployed at the extreme edge. These AI Apps analyse core signals of human behaviour, such as body movements, facial expressions, emotions, identity, head pose, gaze, eye state, gestures, or activities, and identify objects with which users interact. In addition, these AI Apps can be optimised for typically resource constrained, low power and low-cost processing platforms deployed on the edge, as demonstrated with ultra-compact models such as the Emotion Recognition AI App with less than 100KB of memory. Furthermore, NVISO AI Apps can be easily configured to suit a camera system for optimal performance in terms of distance and camera angle, and thanks to NVISO’s large scale proprietary human behaviour databases NVISO’s AI Apps are robust to the imaging conditions often found in real world deployments. Unlike cloud-based solutions, NVISO’s solutions do not require information to be sent off-device for processing elsewhere so user privacy and safety can be protected.
“This announcement of the delivery of a full SDK with an increased range of AI Apps from our catalogue supports our objectives in providing AI solutions on the extreme edge ”, said Tim Llewellynn, CEO of NVISO SA, “Additionally the deployment of the combined technologies of NVISO AI Apps together with embedded neuromorphic processing can provide significant performance improvements for target use cases, in terms of both processing speed and power consumption. This enables delivery on the promise of wide scale deployment of human friendly technologies for an increasing number of applications ranging from consumer products through to medical devices and automated automotive systems. The addition of the latest graph based facial analysis capability opens up the possibilities for the use of a wider range of up to 58 Facial Action Units in both emotion and other human behaviour/condition analysis .”
About NVISO, NVISO is an Artificial Intelligence company founded in 2009 and headquartered at the Innovation Park of the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland. Its mission is to help teach machines to understand people and their behavior to make autonomous machines safe, secure, and personalized for humans. As leader in human behavioral AI, it provides robust embedded software solutions that can sense, comprehend, and act upon human behavior in real-world environments deployed at the deep edge. It achieves this through real-time perception and observation of people and objects in contextual situations combined with the reasoning and semantics of human behavior based on trusted scientific research. NVISO’s technology is made accessible through ready-to-use AI solutions addressing Smart Mobility and Smart Health and Living applications (in-cabin monitoring systems, health assessments, and companion robot sensing) with a key focus on the deep and extreme edge with ultra-low power processing capabilities. With a singular focus on how to apply the most advanced and robust technology to industry and societal problems that matter, NVISO’s solutions help advance human potential through more robust and rich human machine interactions. ir.nviso.ai
More information about NVISO can be found: https://www.ir.nviso.ai/site/investors/investor-fact-sheet