Artificial Intelligence in Edge Devices

It is reasonable and growing easier, to run AI and machine learning with analytics at the edge now, depending on the volume and scale of the edge site and the distinct system being used. While edge site computing systems are much more petite than those found in central data centres, they have matured, and now, fortunately, run many workloads due to tremendous growth in the processing power of today’s x86 stock servers. It’s quite astounding how many workloads can now run triumphantly at the edge.

Artificial intelligence (AI) processing now is frequently done in a cloud-based data centre. The preponderance of AI processing is overlooked by training of deep learning models, which needs heavy compute capacity. In the last 6 years, we have seen a 300,000X growth in computing elements, with graphics processing units (GPUs) implementing most of that horsepower. AI inference, which is conducted post-training, and is proportionately less compute-intensive, has been largely overlooked from an AI processing standpoint. Like training, the inference has also been principally done in the data centre. However, as the heterogeneity of AI applications grows, the centralized, cloud-based training and inferring administration are coming into question.

AI edge processing today is concentrated on moving the inference section of the AI workflow to the device, keeping data compelled to the device. There are various distinct reasons why AI processing is prompting to the edge device, depending on the application. Privacy, security, cost, latency, and bandwidth all require to be regarded when evaluating cloud versus edge processing. The consequence of model compression techniques like Google’s Learn2Compress that permits squeezing large AI models into base hardware form factors is also contributing to the rise of AI edge processing. Federated training and blockchain-based decentralized AI architectures are also part of the relay of AI processing to the edge with part of the practice likely to sway to the edge. Depending on the AI application and device category, there are manifold hardware options for performing AI edge processing. These prospects include CPUs, GPUs, ASICs, FPGAs, and SoC accelerators.

This report provides a quantitative and qualitative evaluation of the market opportunity for AI edge processing across several user and enterprise device markets. The device classifications include automotive, consumer and enterprise robots, drones, head-mounted displays, mobile phones, PCs/tablets, security cameras, and smart speakers. The report includes segmentation by processor type, power consumption, compute capacity, and training versus inference for each device classification, with unit shipment and earnings forecasts for the period from 2017 to 2025.

StrataHive’s Edge-based AI Solutions for Computer Vision

At StrataHive, we have Ready-to-Deploy Computer Vision Deep Learning Models, with world-class efficiency levels in the fields of Object Detection, Face Detection and Recognition, Brand Logo Detection, Display Execution, Shelf Execution, Shelf Inspection, Shelf Insights, Reading Text within Character Recognition.

With a Strategic thrust, we are continuing the above AI & Computer Vision offerings to the Edge-based Devices. The prime drivers of these offerings are:

  • Cost-Effectiveness
  • Compact and Standalone Processing
  • Ready-to-deploy Models
  • Integration capabilities with NVR’s, PLC’s, IOT and IIOT devices

What’s in it for Our Clients?

  • Faster real-time decisions at scale: By running on-premise image recognition also analyzing images/video streams in real-time, we provide significantly more agile insights, compliance levels, which are addressed at the highest availability and scale.
  • Improved operational reliability: Our solution allows Businesses to regionally process images and receive actionable penetrations from relevant devices without worrying about connectivity issues in the Manufacturing / Retail Premises
  • Increased security for devices and data: By analyzing images locally on edge devices instead of sending raw data to the cloud, the solution helps Businesses by eliminating the need to send large and potentially sensitive data to the cloud

Pre-eminent Players offering AI on the Edge

The AI edge hardware market ecosystem is a mixture of established semiconductor companies like NVIDIA, Intel, Qualcomm, ARM, etc. In-house hardware development is another trend to watch out for with Google leading the market with its tensor processing unit (TPU) chipset, including Edge TPU

The Top 3 Products are essential:

  • Nvidia Jetson Nano
  • Intel Neural Compute Stick 2
  • Google Edge TPU Dev Board

Some Applications of AI deployed on the Edge

  • AI is powering a lot of visual and audio intelligence and enables new interesting and valuable use cases. Some examples include:
  • Security and home camera: Smart detection for when important activities are happening and not requiring 24/7 video streaming (for example, detect a person rather than a smart vacuum cleaner robot).
  • Virtual assistant (smart speaker, phone, etc.): Personalization for natural and intuitive conversations and visual interfaces.
  • Phones: Naturally, the smartphone is the pervasive platform for AI. Your phone will detect your context, such as if you are in the car. You can also apply machine learning to smartphones for better user experience, such as improved power management for better battery life, enhanced photography, and on-device malware detection. And many other examples.
  • Smart transportation: On-device AI is beneficial, for example, for sending fewer data to the cloud to know how many seats are available on a bus.
  • Industrial IoT: Automating the factory of the future will require lots of AI, from visual inspection for defects and intricate robotic control for assembly.
  • Drones/robots: Self-navigation in the unknown environment as well as coordination with other drones/robots.
  • Auto: Machine learning for passenger safety, scene understanding, sensor fusion, path planning, etc. The huge, real benefit of autonomous driving is saving lives and time.


Organizations will continue to address AI data management challenges by architecting powerful and highly available edge computing systems, which will lower customer costs. New technologies that were previously cost-prohibitive will become more viable over time, and find uses in new markets.

Previously, powerful AI apps required large, expensive data centre-class systems to operate. But edge computing devices can reside anywhere. AI at the edge offers endless opportunities that can help society in ways never before imagined.

Edge-based inferencing will become a foundation of all AI-infused applications in the Internet of Things and People and the majority of new IoT application-development projects will involve building the AI-driven smarts for deployment to edge devices for various levels of local sensor-driven inferencing.