nViso SA (NVISO), the Human Behavioural Analytics AI company, is pleased to announce it has released an Evaluation Kit (EVK) for its Human Behavioural AI SDK running on the BrainChip Akida™ neuromorphic processing platform. NVISO will release commercially its Human Behaviour AI as both as an Evaluation Kit (EVK) and Software Development Kit (SDK) optimized for neuromorphic processors targeting innovators looking to adopt AI-driven human machine interfaces to detect human behaviour in real-time at the edge. Both companies will jointly promote the EVK and SDK and a first evaluation with a semiconductor manufacturer in Japan has started. This deployment of NVISO’s Human Behavioural AI exploits the superior performance capabilities of BrainChip Akida neuromorphic processor IP with latencies under 10ms and model storage requirements under 1MB for a complete target solution. Targeting next generation of low-power SOC devices with embedded neuromorphic capabilities, target applications include Robotics, Automotive, Telecommunication, Infotainment, and Gaming.
NVISO’s Neuro EVK will support performance evaluations within use case scenarios using a live camera feed and will soon be followed by an SDK for solution developers which will support 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 recognition, emotion recognition, object detection and body pose analysis. A 30-day PC-based evaluation of the EVK is available for order online. Companies interested in a full evaluation on BrainChip neuromorphic hardware should contact BrainChip.
NVISOAI App benchmark performance data running on the BrainChip neuromorphic AIplatform
NVISOHuman Behaviour AI Model Throughput (FPS) Performance Comparison by Platform
NVISOHuman Behaviour AI Model Storage (KB) Performance Comparison by Model Format
“NVISO’s first neuromorphic optimised EVK was achieved in record time and exceeded all expectations”, said Tim Llewellynn, CEO of NVISO, “BrainChip has delivered an excellent development environment for AI software specialists like NVISO, and the maturity of their tools really show why they are first commercial neuromorphic processor IP to market. Deployment of the combined technologies of NVISO AI Apps together with embedded neuromorphic processing can provide game changing performance improvements for our most demanding customers and a wide range of use cases. We are really excited that the neuromorphic revolution is now upon us and could finally deliver on the promise of wide scale deployment of human centric technologies from consumer products through to medical devices and automotive ADAS systems that will have a profound impact on our lives.”
“We are delighted with the progress of our partner NVISO reinforcing the performance and efficiency gains of BrainChip’s Akida neuromorphic processor design with compelling results demonstrated with NVISO’s behavioural AI software”, said Jerome Nadel, CMO at BrainChip. “Our uniquely differentiated AI acceleration provides equivalent performance benefits to any edge AI software; high inference performance, low latency, and ultra-low power consumption”.
NVISO delivers solutions for a wide range of use cases including those in the areas of Smart Living, Smart Mobility and Smart Health. This is achieved through a range of AI Apps providing visual observation, perception and semantic reasoning capabilities, the results of which can be used in identifying issues, in decision making processes and in supporting autonomous “human like” interactions. 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.