IEI logo
Search
English
Choose your language

Explore AI Workloads with IEI x Intel® DevCloud Solution

No hardware setup is required at your end

The IEI x Intel® DevCloud for the Edge allows you to actively prototype and experiment with AI workloads for computer vision on Intel hardware. You have full access to hardware platforms hosted in Intel® cloud environment, designed specifically for deep learning.

Develop your computer vision applications using the IEI x Intel® DevCloud, which includes a preinstalled and preconfigured version of the Intel® Distribution of OpenVINO™ toolkit. Access reference implementations and pretrained models to help explore real-world workloads and hardware acceleration solutions.

Improve the AI solution developer experience

Mature ecosystem enhancements

New innovative products and features/service

Growth Factors & Trends in the Future

Data stored, analyzed and acted on at the edge

AI tasks taking place on edge device

Growth in devices with edge AI capabilities

Accelerate Time to Production with IEI x Intel® DevCloud for the Edge

Run AI applications from anywhere in the world

Prototype on the Latest Hardware and Software

Benchmark your Customized AI Application

Quickly find the right compute for your edge solution

Reduce Development Time and Cost

>> Get Started

Deep Learning for computer vision

Traditional computer vision

Intel® hardware acceleration

Inference performance comparisons

Intel® Distribution of OpenVINO™ toolkit

Intel® Distribution of OpenVINO™ toolkit is based on convolutional neural networks (CNN), the toolkit extends workloads across multiple types of Intel® platforms and maximizes performance.

It can optimize pre-trained deep learning models such as Caffe, MXNET, and ONNX Tensorflow. The tool suite includes more than 20 pre-trained models, and supports 100+ public and custom models (includes Caffe*, MXNet, TensorFlow*, ONNX*, Kaldi*) for easier deployments across Intel® silicon products (CPU, GPU/Intel® Processor Graphics, FPGA, VPU).

OpenVINO™-toolkit-process
FLEX-BX210AI Performance

IEI AI Ready Solution Accelerates Your AI Initiative

IEI AI ready embedded systems are ideal for deep learning inference computing to help you get faster, deeper insights into your customers and your business. Our AI-based embedded systems support graphics cards, Intel® FPGA acceleration cards, and Intel® Vision Accelerator Card with Intel® Movidius™ VPU, and provide additional computational power plus end-to-end solution to run your tasks more efficiently. With the Intel® DevCloud for the Edge solutions and Intel® Distribution of OpenVINO™ toolkit , it can help you deploy your solutions faster than ever.

GRAND-C422

TANK-870AI

HTB-200

FLEX-BX200

ITG-100AI

RACK-500AI

PAC-400AI
GRAND-C422 TANK-870AI HTB-200 ITG-100AI FLEX-BX200 RACK-500AI PAC-400AI
Training GPGPUs O O
Inference Mustang-F100-A10 O O O O O O
Mustang-V100-MX8 O O O O O O
Mustang-V100-MX4 O O O O O O
Mustang-MPCIE-MX2 O O
Mustang-M2BM-MX2 O
NVIDIA® Tesla T4 GPU Card O
Applications Image Classification O O O O O O O
Object Detection O O O O O O O
Image Segmentation O O O O O O O
Features Energy efficient O O
Compact size O O O O O

Applications

Agricultural products are valued by their appearance. The color indicates parameters like ripeness, defects, etc. The quality decisions vary among the graders and are often inconsistent. Machine vision technology offers the solution for all these problems.

The FLEX series designed for machine vision market has four PCIe 3.0 expansion slots for installing motion controller cards, GPU/FPGA/VPU cards and the PoE Ethernet card which is developed by IEI and has four GbE Power over Ethernet (PoE) ports compliant with IEEE 802.3af for direct connection to CCTV cameras without needing separate power.

machine_vision_object_recognition

During the manufacturing process, defects could be introduced and harmful to the quality. It is necessary to classify the defects detected by AOI machine appropriately especially appearance defects. The higher accuracy to classify defects, the less cost spent on review and repair station.

The TANK AIoT Dev. Kit features rich I/O and dual PCIe x8 signals to support add-ons like the Acceleration cards (Mustang-F100-A10 & Mustang-V100-MX8) or the PoE to enhance the defects detected performance.

AOI_Defect_Classification

Mustang series solutions help enable intelligent factories to be more efficient on work order schedule arrangements. In today's production line, sticking to manufacturing schedules is becoming more and more important for business efficiency. From raw material storage to fabrication and complete products, all information from factory such as manufacturing equipment process time and warehouse storage status are essential to achieve production goals.

Solutions based on AI technology can produce more detailed, accurate, and meaningful digital models of equipment and processes for product management.

industrial_automation

Because colon cancer could occur everywhere in the large intestine, the medical personnel need to be very cautious when doing colonoscopy. This application assists the doctor to pay more attention when inflammation, infections, ulcers, polyps or any other abnormal tissues are detected in a gastrointestinal tract inspection. We try to reduce the human error resulting from fatigue or distraction in the daily clinical work

AI Inference in Colonoscopy

Age-related macular degeneration is a leading cause of vision loss. It destroys the macular, the part of the eye that provides sharp, central vision needed for seeing objects clearly.

Video

Eye Related Disease

Normal

Eye Related Disease

Macula Aging

Eye Related Disease

The HTB-100, a high-performance and reliable medical grade embedded system developed by IEI, can be used as a device for AI inference in brain tumor diagnosis by adding a VPU & GPU accelerator card, benefiting from its flexible expansion feature.

In brain tumor treatment, cyberknife is one of the common methods currently used. It is equipped with a linear accelerator on a robotic arm with two X-ray cameras to precisely position and delivers radiation beams to destroy tumor cells.

In traditional process, to create a brain tumor treatment plan, at least two doctors have to manually mark and shape the brain tumor in every picture. It usually takes a whole day to get only one case done due to its complex and sophisticated process. After using the AI inference application, identifying brain tumor becomes automatic, taking only a few seconds to analyze. It is more time saving and more precise while reducing workload of doctors and avoiding errors.

Brain_Tumor_Treatment

AI in the Healthcare｜IEI x QNAP Partner Day

Efficient road tolling and parking reduces fraud related to non-payment, makes charging effective, and reduces required manpower to process. Vehicle license plate analysis can be deployed on highways for electronic toll collection, and can be implemented as a method of cataloguing the movement of traffic as well as provide enhanced security by establishing data on suspicious vehicles in a more efficient way.

self-driving
raffic management
license_plate_recognition_and_analysis
LPR

Using the Mustang series for computer vision solutions at the edge of retail sites can quickly recognize the gender and age of the customers and provide relevant product information through digital signage display to improve product sales and inventory control. Self-checkout can reduce human resource cost so that retail owners can spend more resources on promoting products and understanding business patterns.

In addition, it can help to analyze customer’s in-store behavior, and provide customer information based on gender and age to facilitate product positioning. Quickly converting the business intelligence gained and help build better business practices and increase profitability.

interactive_digital_signage
Interactive digital signage
smart_retail
Smart Retail
self-checkout
Self-checkout