Skip to content

Latest commit

 

History

History
221 lines (179 loc) · 6.98 KB

README.md

File metadata and controls

221 lines (179 loc) · 6.98 KB
Raw

[English] MobileNet-SSD

Ultra-fast MobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) than YoloV2 + Explosion speed by RaspberryPi.
Multiple moving object detection with high accuracy.
Video playback and object detection are executed asynchronously.
In order to realize high speed rendering with multi stick, it is implemented in multithreading/OpenGL.
【Warning】 This repository does not support NCS2.

【Japanese Article】
https://qiita.com/PINTO/items/b97b3334ed452cb555e2

【USB Camera + MultiProcessing High performance version】
Below, when using multiple sticks, it is more than three times the performance of this repository program.
I recommend that you refer to the following repository.
https://github.com/PINTO0309/MobileNet-SSD-RealSense.git

Change history

[July 19, 2018]　Corresponds to NCSDK v2.05.00.02 / OpenCV 3.4.2 / FPS View
[July 27, 2018]　Add an unnecessary version of OpenGL (USBCamera / MultiStick / MultiProcessing / RealSense)

Image of motion

MobileNet-SSD + Neural Compute Stick + RaspberryPi3 / MultiStick(3 Stick / Hard Motion)

Youtube: https://youtu.be/sQnFbRSqIA8

Riders MultiStick

MobileNet-SSD + Neural Compute Stick(1 Stick) + RaspberryPi3 + USB Camera(640x480)
Youtube: https://youtu.be/_Cbt0gI8niQ
Goku

Environment

・RaspberryPi 3 + Raspbian Stretch

・NCSDK v2.08.01 (It does not work with NCSDK v1　v1 version is here)

・Intel Movidius Neural Compute Stick　1 piece

・OpenCV 3.4.2

・OpenGL

・numpy

・(UVC)USB-Web Camera

Building environment

  1. Temporary extension of SWAP area
$ sudo nano /etc/dphys-swapfile
CONF_SWAPSIZE=2048

$ sudo /etc/init.d/dphys-swapfile restart swapon -s
  1. Installing packages
$ sudo apt-get update
$ sudo apt-get upgrade
$ sudo apt-get install python3-pip python3-numpy git cmake libqtgui4 libqt4-test
  1. Installing NCSDK
$ cd ~
$ git clone -b ncsdk2 https://github.com/movidius/ncsdk.git
$ cd ncsdk
$ make install
  1. Installation of OpenCV
$ cd ~
$ wget https://github.com/PINTO0309/OpenCVonARMv7/raw/master/libopencv3_3.4.2-20180709.1_armhf.deb
$ sudo apt install -y ./libopencv3_3.4.2-20180709.1_armhf.deb
$ sudo ldconfig
  1. Installing OpenGL
$ sudo apt-get install python-opengl
$ sudo -H pip3 install pyopengl
$ sudo -H pip3 install pyopengl_accelerate
$ sudo raspi-config

  1. 「7.Advanced Options」-「A7 GL Driver」-「G2 GL (Fake KMS)」 and Activate Raspberry Pi's OpenGL Driver

  2. Reboot

$ sudo reboot
  1. Download complete set of resources
$ cd ~
$ git clone https://github.com/PINTO0309/MobileNet-SSD.git

  1. Connect USB-WEB camera (UVC compatible) and Neural Compute Stick to RaspberryPi's USB port (self power USB-Hub required due to insufficient voltage when using Neural Compute Stick in multiple)

  2. Connect RaspberryPi and display with HDMI cable

  3. Running MobileNet-SSD

$ cd MobileNet-SSD
$ python3 MultiStickSSD.py
  1. Reducing the SWAP area
$ sudo nano /etc/dphys-swapfile
CONF_SWAPSIZE=100

$ sudo /etc/init.d/dphys-swapfile restart swapon -s

Procedure for generating original learning data

https://github.com/movidius/ncappzoo/tree/master/caffe/SSD_MobileNet
https://github.com/FreeApe/VGG-or-MobileNet-SSD
https://github.com/chuanqi305/MobileNet-SSD
https://github.com/avBuffer/MobilenetSSD_caffe
　 　

[Japanese] MobileNet-SSD

YoloV2 より超速 MobileNetSSD(MobileNetSSD)+Neural Compute Stick(NCS)+Raspberry Piによる爆速・高精度の複数動体検知
映像再生と物体検出は非同期実行。
マルチスティックを実現するために、マルチスレッド かつ OpenGL で実装している。
【Qiita記事】 https://qiita.com/PINTO/items/b97b3334ed452cb555e2
【RealSense D435 + MultiProcessing対応版】 https://github.com/PINTO0309/MobileNet-SSD-RealSense.git

変更履歴

[2018/07/19]　NCSDK v2.05.00.02対応 / OpenCV 3.4.2対応 / FPS View対応

動作イメージ

MobileNet-SSD + Neural Compute Stick + RaspberryPi3 / MultiStick(3本/Hard)

Youtube: https://youtu.be/sQnFbRSqIA8

Riders MultiStick

MobileNet-SSD + Neural Compute Stick(1 Stick) + RaspberryPi3 + USB Camera(640x480)
Youtube: https://youtu.be/_Cbt0gI8niQ
Goku

環境

・RaspberryPi 3 + Raspbian Stretch

・NCSDK v2.08.01 (NCSDK v1では動作しません　v1バージョンはこちら)

・Intel Movidius Neural Compute Stick　１本

・OpenCV 3.4.2

・OpenGL

・numpy

・UVC対応のUSB-Webカメラ

環境構築

  1. SWAP領域の一時的な拡張
$ sudo nano /etc/dphys-swapfile
CONF_SWAPSIZE=2048

$ sudo /etc/init.d/dphys-swapfile restart swapon -s
  1. パッケージのインストール
$ sudo apt-get update
$ sudo apt-get upgrade
$ sudo apt-get install python3-pip python3-numpy git cmake libqtgui4 libqt4-test
  1. NCSDKのインストール
$ cd ~
$ git clone https://github.com/movidius/ncsdk.git
$ cd ncsdk
$ make install
  1. OpenCVのインストール
$ wget https://github.com/PINTO0309/OpenCVonARMv7/raw/master/libopencv3_3.4.2-20180709.1_armhf.deb
$ sudo apt install -y ./libopencv3_3.4.2-20180709.1_armhf.deb
$ sudo ldconfig
  1. OpenGLのインストール
$ sudo apt-get install python-opengl
$ sudo -H pip3 install pyopengl
$ sudo -H pip3 install pyopengl_accelerate
$ sudo raspi-config

  1. 「7.Advanced Options」-「A7 GL Driver」-「G2 GL (Fake KMS)」の順に選択し、Raspberry Pi のOpenGL Driver を有効化

  2. 再起動

$ sudo reboot
  1. リソース一式のダウンロード
$ cd ~
$ git clone https://github.com/PINTO0309/MobileNet-SSD.git

  1. USB-WEBカメラ(UVC対応) と Neural Compute Stick をRaspberryPiのUSBポートへ接続(Neural Compute Stickをマルチで使用する場合は電圧が不足するためセルフパワーUSB-Hub必須)

  2. RaspberryPiとディスプレイをHDMIケーブルで接続

  3. MobileNet-SSDの実行

$ cd MobileNet-SSD
$ python3 MultiStickSSD.py
  1. SWAP領域の縮小
$ sudo nano /etc/dphys-swapfile
CONF_SWAPSIZE=100

$ sudo /etc/init.d/dphys-swapfile restart swapon -s

独自学習データの生成手順

https://github.com/movidius/ncappzoo/tree/master/caffe/SSD_MobileNet
https://github.com/FreeApe/VGG-or-MobileNet-SSD
https://github.com/chuanqi305/MobileNet-SSD
https://github.com/avBuffer/MobilenetSSD_caffe