Embedded System Design Track

Track Lead

Intel's technology has been at the heart of computing breakthroughs. We are an industry leader, creating world-changing technology that enables global progress and enriches lives. We stand at the brink of several technology inflections—artificial intelligence (AI), 5G network transformation, and the rise of the intelligent edge - that together will shape the future of technology. Silicon and software drive these inflections, and Intel is at the heart of it all.

Embedded System Design Track opens to projects involving embedded system design using IoT or FPGA board. Teams enrolled in the track will be supplied the OpenVINO™ Toolkit or DE1-SoC board. The projects can target various application domains, including agriculture, automotive, consumer, healthcare, industrial, etc.

adjust AIoT Project

The Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence (AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT operations, improve human-machine interactions and enhance data management and analytics. Teams can focus on IoT, visual sensing, or AI-specific projects or combine any of these three areas.

Intel AIOT platform envisions the participants to be part of the revolution! Solve the problem with AI technologies to make a difference and shape the future. The solution can be applied, but not limited to retail, health care, smart city, manufacturing, sports, and autonomous vehicles.

OpenVINO™ Toolkit

OpenVINO™ toolkit (Open Visual Inference and Neural Network Optimization) is a comprehensive toolkit for quickly developing AI applications and solutions that solve various tasks, including emulation of human vision, automatic speech recognition, recommendation systems, and many others. Hence, developers can deploy pre-trained deep learning models through Python or high-level C++ Inference Engine API integrated with the application. The toolkit extends computer vision and non-vision workloads across Intel® hardware, maximizing performance. In addition, it accelerates applications with high-performance, AI, and deep learning inference deployed from edge to cloud.

OpenVINO™ toolkit:

  • Enables CNN-based deep learning inference on the edge
  • Supports heterogeneous execution across an Intel® CPU, Intel® Integrated Graphics, Intel® Neural Compute Stick 2, and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs
  • Easy-to-use library of computer vision functions and pre-optimized kernels
  • Includes optimized calls for computer vision standards, including OpenCV* and OpenCL™

What is the benefit of using the OpenVINO™ toolkit?

  1. OpenVINO™ toolkit includes a set of inference code samples and application demos showing how inference is run and output processed for use in retail environments, classrooms, smart camera applications, and other solutions.
  2. Optimized Inference Engine library enables the developer to call the libraries and develop an application based on a pre-trained model.
  3. Accelerate performance by expediting computer vision workload by enabling simple execution methods across different Intel Processor and accelerator.
  4. Streamline Deep Learning Deployment utilizes Convolutional Neural Network (CNN)-based deep learning functions using one standard API to more than 30 pre-trained models and documentation code samples. With more than 100 public and custom models, OpenVINO™ toolkit streamlines deep learning innovation by providing one centralized method for implementing dozens of deep learning methods.

Pre-requisites

  1. Have basic Python programming or C++ programming knowledge
  2. Have Hardware or Platform that run Intel processor
  3. Have a basic idea of Computer Vision and Artificial Intelligence

Sample Application Based on OpenVINO™

  1. Security barrier camera demo - This demo showcases Vehicle and License Plate Detection network followed by the Vehicle Attributes Recognition and License Plate Recognition networks applied on top of the detection results.
  2. Smart classroom demo - The demo shows an example of joint usage of several neural networks to detect three basic actions (sitting, standing, raising hand) and recognize people by faces in the classroom environment.
  3. Object detection sample - This sample demonstrates how to do inference of object detection networks using Synchronous Inference Request API.

Intel OpenVINO™ toolkit Workshop (AIOT project)

  1. Participants must attend a 2-day OpenVINO™ toolkits workshop that provides hands-on training on the OpenVINO™ toolkit.
  2. Participants are advised to install OpenVINO™ toolkits from installOpenVINO™ Distribution (support Windows 10, Ubuntu, RedHat, MacOS).
  3. Python programming language will be actively used throughout the workshop.

OpenVINO™ toolkit documentation: https://docs.openvinotoolkit.org

adjust FPGA Project

DE1-SoC board is an updated DE1 board. It is useful for learning about digital logic, computer organization, and FPGAs. Featuring a Cyclone® V 5CSEMA5 FPGA which has an integrated dual-core ARM Cortex-A9. The DE1-SoC board is designed for university and college use. It is suitable for a wide range of university projects, from simple tasks to advanced designs.

The track offers the opportunity for students to create FPGA design projects and implement in the Intel FPGA development kit. The projects can target various market segments, e.g. consumer, industrial, medical, automotive, military, computing, ASIC emulation, etc., with the emphasis on creativity, innovation, practicality, and potential for commercialization of the projects.

Students who are more well-verse in hardware description language can choose to use Verilog, VHDL, etc. to create their designs. Students who prefer software programming language like C can use the Nios II soft processor, or the hard processor system available in the Intel SoC FPGA devices. A wide range of IP cores are also available for students to utilize and instantiate in their designs, saving them precious time and accelerating their design development.

The eventual designs are expected to be implemented in Intel FPGA development kits for prototyping or proof of concept. Students can choose to use the Cyclone V DE1 SoC development kits or other Intel FPGA development kits as preferred.

DE1-SoC

  • FPGA
    • Cyclone V SoC 5CSEMA5F31 (85k logic elements)
    • Dual-core ARM Cortex-A9 (HPS)
    • EPCQ256 256-Mbit serial configuration device
  • I/O Devices
    • Built-in USB-Blaster for FPGA configuration
    • Line In/Out, Microphone In (24-bit Audio CODEC)
    • Video Out (VGA 24-bit DAC)
    • Video In (NTSC/PAL/Multi-format)
    • Infrared port
    • 10/100/1000 Ethernet
    • Two Port USB 2.0 Host (Type A)
    • PS/2 dual mouse and keyboard port
    • Line-in, Line-out, microphone-in (24-bit audio CODEC)
    • Expansion headers (two 40-pin headers)
  • Memory
    • 1GB DDR3 SDRAM (HPS)

      • Two Port USB 2.0 Host (Type A)

    • 64 MB SDRAM (FPGA)
    • Micro SD memory card slot
  • Other Devices
    • Six 7-segment displays
    • 10 toggle switches
    • 10 LEDs
    • Four debounced pushbutton switches
    • 50 MHz clock (x4)

Resources for FPGA Board

adjust FPGA Board Resources

adjust Supporting Materials