The age of autonomous machines and intelligent IoT devices is upon us. They will affect many aspects of our lives. They will bring about a new generation of diagnostic instruments to clinics, improve cars and transportation, and create new consumer experiences, while being embedded into the networks that power and inform society underpinning the efficient provision of public and private services. Increasingly they sense their surroundings, operate autonomously and collaborate with other devices seamlessly.

Improving the safety, security, and quality of life of humans that interact with such intelligent systems will be critical to their operation. To interact efficiently and effectively, sensing and interpreting human behaviour will become mission critical to connecting the human user with automated systems. Multiple core horizontal topics are necessary to teaching machines to sense and understand humans and use cases where “AI at the Extreme Edge” is not only critical but transformative.

How does it work? NVISO’s Human Behaviour AI uses computers to learn from examples opposed to being manually programmed. Using NVISO's Neuro Models™ based on convolutional neural networks (CNNs) and state-of-the-art machine learning to understand human behaviors depicted in images and videos, it can achieve accuracy levels that surpass human performance in many narrowly defined tasks.

Accurate and Robust

CNNs scale to learn from billions of examples resulting in an extraordinary capacity to learn highly complex behaviors and thousands of categories. NVISO can train powerful and highly accurate and robust models for use in the toughest environments thanks to its proprietary datasets captured in real-world environments.

Easy to Integrate

Where AI is fragmented and difficult-to-navigate at the edge, NVISO AI Apps are simple to use, develop, and deploy, with easy software portability across a variety of hardware and architectures.​ It reduces the high barriers-to-entry into the edge AI space through cost-effective standardized AI Apps that are future proof and work optimally at the extreme edge.

Ethical and Trustworthy

AI systems need to be resilient and secure. They need to be safe, ensuring a fall back plan in case something goes wrong, as well as being accurate, reliable and reproducible. Additionally unfair bias must be avoided, as it could could have multiple negative implications. NVISO adopts Trustworthy AI frameworks and state-of-the-art policies and practices to ensure its AI Apps are "fit-for-purpose".

Extreme Edge Computing
No Cloud Required

Privacy Preserving

By processing video and audio sensor data locally it does not have to be sent over a network to remote servers for processing. This improves data security and privacy as it can perform all processing disconnected from the central server, which is a more secure and private architecture decreasing security risks.

Lower Energy Usage

The more we move data, the more energy we use. Processing data first on-device opposed to sending it to the cloud uses a lot of less energy. As the amount and rate of data exchange with the cloud is minimised, the power consumption of the device is reduced thus improving battery lifetime, which is critical for many edge devices.

Higher Availability

Decentralisation and offline capabilities make edge AI more robust since internet access is not required for processing data. This results in higher availability and reliability as weak WiFi signals do not impact the device performance.


NVISO Neuro Models™ are purpose built for a new class of ultra-efficient machine learning processors designed for ultra-low power edge devices. Supporting a wide range of heterogenous computing platforms ranging from CPU, GPU, DSP, NPU, and neuromorphic computing they reduce the high barriers-to-entry into the AI space through cost-effective standardized AI Apps which work optimally at the extreme edge (low power, on-device, without requiring an internet connection). NVISO uses low and mixed precision activations and weights data types (1 to 8-bit) combined with state-of-the-art unstructured sparsity to reduce memory bandwidth and power consumption. Proprietary compact network architectures can be fully sequential suitable for ultra-low power mixed signal inference engines and fully interoperable with both GPUs and neuromorphic processors


NVISO Neuro Models™ use proprietary datasets and modern machine learning to learn from billions of examples resulting in an extraordinary capacity to learn highly complex behaviors and thousands of categories. Thanks to high quality datasets and low-cost access to powerful computing resources, NVISO can train powerful and highly accurate deep learning models.


NVISO Neuro Models™ store their knowledge in a single network, making them easy to deploy in any environment and can adapt to the available hardware resources. There is no need to store any additional data when new data is analysed. This means that NVISO Human Behaviour AI can run on inexpensive devices with no internet connectivity providing response times in milliseconds not seconds.


NVISO Neuro Models™ are scalable across heterogeneous AI hardware processors being interoperable and optimised for CPUs, GPUs, DSPs, NPUs, and the latest neuromorphic processors using in-memory computing, analog processing, and spiking neural networks. NVISO Neuro Models™ maximise hardware performance while providing seamless cross-platform support on any device.


Consumer Robots

Human–robot interaction plays a crucial role in the burgeoning market for intelligent personal-service and entertainment robots.

Automotive Interior Sensing

Next generation mobility requires AI, from self-driving cars to new ways to engage customers. Build and deploy robust AI-powered interior monitoring systems.

Gaming and Avatars

The gaming industry (computer, console or mobile) is about to make extensive use of the camera input to deliver entertainment value.


Get Our Whitepaper