GithubHelp home page GithubHelp logo

fitrialif / intel-movidius-ncs-rpi Goto Github PK

View Code? Open in Web Editor NEW

This project forked from ibrahimsoliman97/intel-movidius-ncs-rpi

0.0 2.0 0.0 3.23 MB

Image classifier using Intel Movidius Neural Compute Stick with Raspberry Pi and ( Pi Camera or Web Camera)

Python 100.00%

intel-movidius-ncs-rpi's Introduction

Intel Movidius NCS RPI

Image classifier and Object detection using Intel Movidius Neural Compute Stick with Raspberry Pi and ( Pi Camera or USB Web Camera)

Required Materials

1- Intel Movidius™ Neural Compute Stick

2- Development computer running Ubuntu 16.04 LTS

3- Raspberry Pi " Raspberry Pi 3 Model B Rev 1.2 has been used in this work "

4- USB Camera

5- Pi Camera

Installation and running your network with USB Camera on RPI

Please follow the installation guide provided by Intel Movidius NCS :

https://ncs-forum-uploads.s3.amazonaws.com/ncsdk/MvNC_SDK_01_07_07/NCS_Getting_Started_1.07.07.pdf

https://www.youtube.com/watch?v=f39NFuZAj6s

Pi Camera Example

Alt text

1- From previous steps, you should have the following files on your Raspberry Pi :

- ncapi folder that include network's floders with each network graph file that has been compiled on your development computer.
- installed GStreamer on your Raspberry Pi

2- Install GStreamer element for the Raspberry Pi camera module (gst-rpicamsrc):

https://github.com/thaytan/gst-rpicamsrc

gst-rpicamsrc testing, run command below on your terminal, you should get a live stream preview from your PiCamera:

gst-launch-1.0 rpicamsrc bitrate=1000000 fullscreen=0 ! video/x-h264,width=640,height=480,framerate=25/1 ! filesink location=test.h264

3- Download and copy the modified python script 'stream_infearnew.py' to '../ncapi/py_examples/stream_infer/'

4- Run stream_infearnew.py

SqueezeNet Inference :

FPS ~= 9 :

description here description here
description here description here
description here

Object Detection [Tiny YOLO V1] :

By using the graph file of tiny YOLO, you will be able to get a result of object detection with [ ~5 FPS using USB 3 port and ~3 FPS using USB 2 port for Intel Movidius NCS]

Single image inference :

python3 yolo_example.py 1 ../images/person.jpg

Alt text Alt text

Camera stream inference :

python3 object_detection_app.py

Alt text

Acknowledgement

The author would like to thank the developers of Intel Movidius NCS, YOLONCS and gst-rpicamsrc.

The equipment used in this work is provided by Machine Learning and Signal Processing Research Lab, Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka (UTeM). description here

intel-movidius-ncs-rpi's People

Watchers

James Cloos avatar Mohd Fitri Alif Bin Mohd Kasai avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.