close

AI Accelerator -
Case Study

Synopsis

Xailient Detectum™ was created to fulfill the need for fast deep learning model inference at the Edge. Xailient with Movidius on Raspberry 3B+ gives you 70 fps with better software and an AI accelerator.

Key Outcomes

1Xailient outperforms the state-of-the-art MobileNet v2 model with and without the use of hardware accelerators.

2Xailient Detectum was created to fulfill the same real-time demands, making deep learning algorithms more efficient. The result is 4 times higher frame rate than the state-of-the-art MobileNet accelerated with the Movidius™ Neural Compute Stick.

Problem Statement

MobileNet v2 is a state-of-the-art architecture for mobile and embedded computer vision applications. Traditional AI models, like MobileNet v1 and MobileNet v2, are computationally intensive and require computational resources beyond the capabilities of low-power and low-cost devices.

Activity

01

We trained MobileNet v2 and Xailient Detectum using an open-source training dataset to create face detectors. These face detectors perform both localization and classification of faces in an image (i.e., generate bounding box data).

02

These models provided the baseline of state-of-the-art Edge-optimized AI, and their performance was measured in terms of inference speed in frames per second on Raspberry Pi 3B+

03

Four different experiments were run: MobileNet v2 Face Detector without Movidius, MobileNet v2 Face Detector with Movidius, Xailient Face Detector without Movidius, and Xailient Face Detector with Movidius.

Results

The Baseline MobileNet v2 without Movidius NCS had an inference speed of 1 frame per second, and MobileNet v2 with Movidius NCS had an inference speed of 5 frames per second. At the same time, the Xailient model processed 20 frames per second without the Movidius NCS and processed 70 frames per second with Movidius.

Next Steps

To meet the demand to run such deep learning models providing real-time, on-device inferences, AI hardware accelerators such as Movidius™ and Neural Compute Stick significantly improve inference times.

Discussion

The results were unprecedented when the Xailient Detectum™ algorithm was combined with the Movidius™ Neural Compute Stick hardware accelerator. Xailient achieved 70x faster inference than MobileNet v2 and 14x faster inference with MobileNet v2 combined with Movidius™ Neural Compute Stick.

Press releases

September 27, 2024

Konami and Xailient to unveil new facial recognition solution for table games at G2E

by Newsdesk Fri 27 Sep 2024 at 05:39 Global industry supplier Konami Gaming is set to unveil new technology at Global Gaming Expo (G2E) in Las Vegas next month that brings its player facial recognition solution for Electronic Game Machines to table games. The expanded offering, in partnership with Xailient, follows the launch of SYNK Vision […]

July 13, 2024

Konami Gaming, Inc. and Xailient, Inc. Join Forces to Introduce SYNK Vision, Revolutionizing Casino Experience with Secure Identity Management and Enhanced Harm Minimization

NEWS PROVIDED BY Xailient Inc  Nov 05, 2023, 22:24 ET Konami Gaming and Xailient partnering to replace magnetic player tracking cards with facial recognition technology at slots and tables for the casino industry LAS VEGAS, Nov. 3, 2023 /PRNewswire/ — Konami Gaming, Inc. and Xailient Inc. announced a strategic partnership to introduce SYNK Vision™ to the casino industry. This revolutionary collaboration […]

Explore our blogs

We see things differently in the dynamic field of computer vision AI

All

Casino and Gaming

AI Act and Casinos: What Casino Operators Need to Know About AI Governance and Compliance

Lars Oleson
August 31, 2024

All

Edge Computing

How Edge Computing is Transforming Enterprises

Shandra Earney
April 13, 2023

All

Edge Computing

What Are the Top 7 Edge Computing Use Cases?

Shandra Earney
March 30, 2023

Get started with Xailient

We empower companies to bring computer vision AI products to market
faster and with less investment

OnEdge Newsletter

A weekly newsletter with the best hand-picked resources about Edge AI and Computer Vision

OnEdge is a free weekly newsletter that keeps you ahead of the curve on low-powered Edge devices and computer vision AI.

 

You’ll get insights and resources into:

  • Edge computing use cases.
  • Market trends in Edge computing.
  • Computer Vision AI at the Edge.
  • Machine learning at the Edge.
Cookie Policy