Movidius#Neural Compute Stick

{{Short description|American computer processor chip design company}}

{{Multiple issues|

}}

{{Infobox company

| name = Movidius Ltd.

| image =

| logo = File:Movidius logo.png

| type = Private

| fate = Acquired by Intel

| predecessor =

| successor =

| founded = {{Start date and age|2005}}

| founder =

| defunct = {{end date and age|2016|09}}

| hq_location_city = San Mateo, California, U.S.

| key_people =

| products = Computer vision and deep-learning processor chips

| owner = Intel

| num_employees =

| num_employees_year =

| parent =

| website = {{URL|https://www.intel.com/content/www/us/en/products/details/processors/movidius-vpu.html}}

}}

Movidius Ltd. was a company based in San Mateo, California, that designed low-power processor chips for computer vision. The company was acquired by Intel in September 2016, who continues to sell the company's products under the Movidius line.{{Cite web |last=Staff |first=Fora |title=Movidius founder after €300m sale to Intel: 'Losing control of the company is difficult' |url=https://www.thejournal.ie/sean-mitchell-movidius-intel-sold-2-3291231-Mar2017/ |access-date=2022-03-30 |website=TheJournal.ie |date=19 March 2017 |language=en}}

Company history

File:Intel Movidius 2020 logo.svg

Movidius was co-founded in 2005 by Sean Mitchell, David Moloney, and Val Muresan in Dublin, Ireland. {{cite news |last1=Hongquan |first1=Jiang |date=12 October 2016 |title=Movidius: a classic example of faith in new technology |url=https://globalventuring.com/movidius-a-classic-example-of-faith-in-new-technology/ |accessdate=12 October 2016 |newspaper=Global Venturing}}{{cite web |last=Caulfield |first=Brian |date=9 September 2016 |title=Movidius - A Story of Vision and Resilience |url=https://www.linkedin.com/pulse/movidius-story-vision-resilience-brian-caulfield/ |accessdate=9 September 2016 |website=Linkedin}} Between 2006 and 2016, it raised nearly $90 million in capital funding.{{Cite news | url=https://www.economist.com/technology-quarterly/2016-03-12/after-moores-law#section-3 | title=After Moore's law | Technology Quarterly| newspaper=The Economist}} In May 2013, the company appointed Remi El-Ouazzane as CEO.{{cite news|title=Movidius Raises $16 Million to Boost Augmented Reality Portfolios|url=http://siliconangle.com/blog/2013/07/10/movidius-raises-16-million-to-boost-augmented-reality-portfolios/|accessdate=4 August 2016|publisher=SiliconAngle|date=July 10, 2013}} In January 2016, the company announced a partnership with Google.{{cite web|last1=Weckler|first1=Adrian|title=Dublin tech firm Movidius to power Google's new virtual reality headset|url=http://www.independent.ie/business/technology/news/dublin-tech-firm-movidius-to-power-googles-new-virtual-reality-headset-34449883.html|website=Independent.ie|date=14 February 2016 |accessdate=15 March 2016}} Movidius has been active in Google's Project Tango,{{Cite web|url=https://www.theverge.com/2016/3/16/11242578/movidius-myriad-2-chip-computer-vision-dji-phantom-4|title=The chipmaker behind Google's project Tango is powering DJI's autonomous drone|last=Popper|first=Ben|date=2016-03-16|website=The Verge|access-date=2017-07-22}} and in September 2016 it was announced that Intel planned to acquire the company.{{Cite web | url=http://www.movidius.com/news/ceo-post-september-2016 |title = Movidius + Intel = Vision for the Future of Autonomous Devices | Machine Vision Technology | Movidius}}

Products

File:MA2485.jpg

=Myriad 2=

The company's Myriad 2 chip is a manycore vision processing unit that can function on power-constrained devices.{{cn|date=May 2018}} The Fathom is a USB stick containing a Myriad 2 processor, allowing a vision accelerator to be added to devices using ARM processors including PCs, drones, robots, IoT devices and video surveillance for tasks such as identifying people or objects. It can run at between 80 and 150 GFLOPS on 1W of power.{{Cite web|url=http://www.tomshardware.com/news/movidius-fathom-neural-compute-stick,31694.html|title=Deep Learning On A Stick: Movidius' 'Fathom' Neural Compute Stick (Updated)|date=2016-04-28|website=Tom's Hardware|access-date=2016-05-28}}

=Myriad X=

Intel's Myriad X VPU (vision processing unit) is the third generation VPU from Movidius. It uses a Neural Compute Engine, a dedicated hardware accelerator—for neural network deep-learning inferences.

Neural Compute Stick

{{Multiple image|direction=horizontal|total_width=220

|image1=Intel NCS2 PCB front.jpg|alt1=Intel NCS2 PCB front|caption1=Intel NCS2 PCB front

|image2=Intel NCS2 PCB back.jpg|alt2=Intel NCS2 PCB back|caption2=Intel NCS2 PCB back

}}

The Intel Movidius Neural Compute Stick (NCS) is a compact device designed to facilitate the development of deep learning applications at the network edge. It utilizes the Intel Movidius Myriad 2 Vision Processing Unit (VPU), which is also found in various smart devices like security cameras, gesture-controlled drones, and industrial machine vision systems. The NCS supports frameworks such as TensorFlow and Caffe for developing neural network models.

The second iteration, the Intel Neural Compute Stick 2 (NCS 2), was introduced on November 14, 2018, at the AI DevCon event in Beijing. This version is based on the Myriad X VPU, which significantly improves performance over the original, providing up to eight times the processing capability for AI inference tasks. The NCS 2 is designed to work seamlessly with the Intel Distribution of OpenVINO toolkit, which helps developers optimize and deploy their models efficiently.

The NCS connects to a host machine via a USB interface, allowing developers to rapidly prototype and deploy deep neural network applications without the need for cloud connectivity. This makes it suitable for various real-time, low-power applications where efficient on-device processing is essential.

Uses

Google Clips camera uses Myriad 2 VPU.{{Cite web|last=Vincent|first=James|date=2017-10-06|title=Google's Clips camera is powered by a tailor-made AI chip|url=https://www.theverge.com/circuitbreaker/2017/10/6/16434834/google-clips-camera-ai-movidius-myriad-vpu|access-date=2020-11-25|website=The Verge|language=en}}
The Intel RealSense Tracking Camera T265 uses the Myriad 2.{{Cite web|title=Robust Visual-Inertial Tracking with Tracking Camera T265|url=https://www.intelrealsense.com/visual-inertial-tracking-case-study/|access-date=2020-11-25|website=Intel RealSense Depth and Tracking Cameras|language=en-US}}
In 2016, Mavic incorporated the Myriad 2 VPU in all its consumer drones.{{Cite press release|title=Movidius Supplies Myriad 2 Vision Processing Unit for Newest DJI Drone, the Mavic Pro

|date=29 September 2016 |url=https://www.globenewswire.com/news-release/2016/09/29/1001781/0/en/Movidius-Supplies-Myriad-2-Vision-Processing-Unit-for-Newest-DJI-Drone-the-Mavic-Pro.html|access-date=2020-12-28|language=en-US}}

The Ryze Tello affordable programmable drone, licensing Mavic Software, uses the Myriad 2 VPU.{{Cite web|title=Cool New Tello Toy Drone Soars into CES 2018

|url=https://www.ryzerobotics.com/news/launch_news_page_en|access-date=2020-12-28|language=en-US}}