Intel® Vision Accelerator Design with Intel® Movidius™ Vision Processing Unit (VPU)
Deep Neural Networks
Optimized for computer vision applications built using deep neural networks for low power, low cost, and small form factors
Power Efficiency
Ultra-low-power demands allow for integration on cameras and edge servers running on power- and size-constrained systems
Easy to Scale
Scalable analytics with minimal software changes for single- to multiple-chip solutions
Overview
Specialized processors designed to deliver high-performance machine vision at ultra-low power.
- Supports up to 16 video streams per device
- Ideal for camera and network video recorder (NVR) use cases with power, size, and cost constraints
- Supports small memory footprint networks
Virtual Testing with Intel® Tiber™ AI Cloud
Quickly prototype and develop AI applications in the cloud using the latest Intel® hardware and software tools.
Who Needs This Product
Information and operational technologists who:
- Are new to IoT commercial platforms and need a simple path without a steep learning curve
- Create solutions that offload deep learning and AI workloads from the CPU or GPU to dedicated accelerator products
- Need a quicker path to deployment
Use Cases
- Smart cities
- Automotive and transportation
- Healthcare
- Retail
- Digital security
Specifications
Intel Vision Accelerator Design
Features | With 1 Intel Movidius VPU | With 2 Intel Movidius VPUs | With 8 Intel Movidius VPUs |
|---|---|---|---|
VPU | 1 - MA2485 | 2 - MA2485 | 8 - MA2485 |
Board dimensions | M.2 2230 Key E & A 22 mm x 30 mm | M-PCIe* 30 mm x 50 mm | Half-height, half-length, single-slot PCIe* 68.90 mm x 167.65 mm |
VPU memory | 4 GB LPDDR4 POP | 4 GB LPDDR4 POP | 4 GB LPDDR4 POP |
Minimum system configuration
| Intel Atom® x7 processor E3950 8 GB LPDDR4, 64 GB eMMC USB 3.0, M.2 2230 connector | Intel Atom x7 processor E3950 8 GB LPDDR4, 64 GB eMMC USB 3.0, M-PCIe connector | Intel® Core™ i5 processor 6500TE 8 GB RAM, 500 GB HDD USB 3.0 2 - PCIe x4 x8 x16 connectors |
Typical operating system
| Ubuntu* 16.04 LTS 64 bit | Ubuntu 16.04 LTS 64 bit | Ubuntu 16.04 LTS 64 bit |
Tools | Intel® Distribution of OpenVINO™ toolkit | Intel Distribution of OpenVINO toolkit | Intel Distribution of OpenVINO toolkit |
Supported Streams
Typically supports 1 to 16 video streams per device (depends on desired frame rate and algorithm complexity)
Efficiency
High efficiency
Precision
Supports FP16 precision networks
Customization
Hardware optimized for generic cases
Software
Intel® Distribution of OpenVINO™ Toolkit
- Enable deep learning inference on the edge based on convolutional neural networks.
- Support for heterogeneous execution across various accelerators—CPU, GPU, Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU), and FPGA—using a common API.
- Speed up time to market via a library of functions and preoptimized kernels.
- Preinstalled models are included with release 5.
Overview | Training | Documentation | Forum | Get Started
Hardware
IoT Developer Kits Supporting Intel® Movidius™ Vision Processing Unit (VPU)
Developer Kits Based on 8th Generation Intel® Core™ Processors
IEI* TANK AIoT Developer Kit (Intel Core Processor)
IEI TANK AIoT Developer Kit (Intel® Xeon® Processor)
Suppliers
Purchase or review documentation from the following suppliers.
Intel Vision Accelerator Design
Suppliers | With 1 Intel Movidius VPU | With 2 Intel Movidius VPUs | With 8 Intel Movidius VPUs |
|---|---|---|---|
AAEON* | |||
ADLINK* |
|
| |
Advantech* |
| ||
IEI | |||
JWIPC* |
|
| |
NEXCOM* |
|
|