tim-pl-m / cir-autodj

CIR-AutoDJ (WIP!)

local Prototyp

Requirements: -Virtualbox -debian-VM http://debian.uvigo.es/debian-cd/9.2.1/multi-arch/iso-cd/

-install openCV: find the installation script here: http://milq.github.io/install-opencv-ubuntu-debian/ https://github.com/milq/milq/blob/master/scripts/bash/install-opencv.sh

% TODO check if needed (apt-get install build-essential module-assistant m-a prepare) https://virtualboxes.org/doc/installing-guest-additions-on-debian/

% guest additions einlegen sh /media/cdrom/VBoxLinuxAdditions.run % reboot % optional: guvcview installieren um kamera zu testen

Used repositories: https://github.com/LukashenkoEvgeniy/People-Counter

mac Dev-Env

https://www.learnopencv.com/install-opencv3-on-macos/

mkvirtualenv cvp3 -p python3 workon cvp3 pip install numpy ipython (pip install numpy scipy matplotlib scikit-image scikit-learn ipython) deactivate

brew search opencv brew install opencv

python3 --version which python3

(python2 --version which python2

echo /usr/local/opt/opencv/lib/python2.7/site-packages >> /usr/local/lib/python2.7/site-packages/opencv3.pth)

echo /usr/local/opt/opencv/lib/python3.6/site-packages >> /usr/local/lib/python3.6/site-packages/opencv3.pth

find /usr/local/opt/opencv@3/lib/ -name cv2*.so /usr/local/opt/opencv@3/lib//python3.6/site-packages/cv2.cpython-36m-darwin.so

ls ~/.virtualenvs/cvp3/lib/python3.6/site-packages/ cd ~/.virtualenvs/cvp3/lib/python3.6/site-packages/ ln -s /usr/local/opt/opencv@3/lib/python3.6/site-packages/cv2.cpython-36m-darwin.so cv2.so

workon cvp3

ipython

import cv2 print(cv2.version)

(print cv2.version)

(brew install opencv -- with-contrib)

(brew install homebrew/science/opencv3 brew install homebrew/science/opencv3 -- with-contrib)

workon cv ... deactivate

https://www.pyimagesearch.com/2016/12/05/macos-install-opencv-3-and-python-3-5/

ls /usr/local/Cellar/python3/3./Frameworks/Python.framework/Versions/3 ls /usr/local/Cellar/python3/3./Frameworks/Python.framework/Versions/3.5/lib/python3.5/config-3.5m/libpython3.5.dylib ls /usr/local/Cellar/python3/3.5.2_3/Frameworks/Python.framework/Versions/3.5/lib/python3.5/config-3.5m/libpython3.5.dylib ls -d /usr/local/Cellar/python3/3.*/Frameworks/Python.framework/Versions/3.5/include/python3.5m/ ls -d /usr/local/Cellar/python3/3.5.2_3/Frameworks/Python.framework/Versions/3.5/include/python3.5m/

cmake -D CMAKE_BUILD_TYPE=RELEASE
-D CMAKE_INSTALL_PREFIX=/usr/local
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules
-D PYTHON3_LIBRARY=/usr/local/Cellar/python3/3.5.2_3/Frameworks/Python.framework/Versions/3.5/lib/python3.5/config-3.5m/libpython3.5.dylib
-D PYTHON3_INCLUDE_DIR=/usr/local/Cellar/python3/3.5.2_3/Frameworks/Python.framework/Versions/3.5/include/python3.5m/
-D PYTHON3_EXECUTABLE=$VIRTUAL_ENV/bin/python
-D BUILD_opencv_python2=OFF
-D BUILD_opencv_python3=ON
-D INSTALL_PYTHON_EXAMPLES=ON
-D INSTALL_C_EXAMPLES=OFF
-D BUILD_EXAMPLES=ON ..

without replacement: $ cmake -D CMAKE_BUILD_TYPE=RELEASE
-D CMAKE_INSTALL_PREFIX=/usr/local
-D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules
-D PYTHON3_LIBRARY=YYY
-D PYTHON3_INCLUDE_DIR=ZZZ
-D PYTHON3_EXECUTABLE=$VIRTUAL_ENV/bin/python
-D BUILD_opencv_python2=OFF
-D BUILD_opencv_python3=ON
-D INSTALL_PYTHON_EXAMPLES=ON
-D INSTALL_C_EXAMPLES=OFF
-D BUILD_EXAMPLES=ON ..

Source: https://grantwinney.com/how-to-create-a-raspberry-pi-virtual-machine-vm-in-virtualbox/

q-learning: source: https://github.com/rlcode/reinforcement-learning/

---

mac:

python3 --version python3 -m pip install -r requirements.txt sudo python3 -m pip uninstall numpy python3 -m pip install numpy==1.12. python3 -m pip install numpy

python3 -m pip list

---

python3 q_learning_agent.py

errors: ModuleNotFoundError: No module named 'imutils'

sources: https://vevurka.github.io/dsp17/python/cs/graph_in_python_matrix/ https://en.wikipedia.org/wiki/Q-learning#Discount_factor

idee für verififikation: ?

cir-autodj's Issues

Human Detection and Tracking

make
https://github.com/ITCoders/Human-detection-and-Tracking
work on rPi-Dev-Env

Issue #7 auf RaspberryPi testen

Abnahmekritieren:
-Alles nötige im Git eingecheckt und in der Readme dokumentiert
-Stand von Ticket #7 läuft auf RaspberryPi ohne anschluss an einen Rechner
d.h.
-Internet auf RPi

-Review durch jemand anderes

Zeit: 2h

Musik anbinden

Abnahmekritieren:
-"virtueller"(?) RapsberryPi spielt Musik Songs aus dem Internet ab
-Alles nötige im Git eingecheckt und in der Readme dokumentiert
-Review durch jemand anderes

Zeit: 4h

Movement Detection

Github/Paper for implementation/theory. especially with ideas to identify ppl and measure location-changes.

Zeit: never ending Story

Kamera anbinden

Abnahmekritieren:
-"virtueller"(?) RapsberryPi nimmt Bilder auf und kann diese speichern/verarbeiten
-Alles nötige im Git eingecheckt und in der Readme dokumentiert
-Review durch jemand anderes

Zeit: 4h

fastforward-Solution for changing Music

Abnahmekritieren:
-Falls Standbild: keine Änderung der Playlist
-Falls sich in der Kamerauafnahme IRGENDETWAS bewegt -> Playlist wird irgendwie geändert
-Alles nötige im Git eingecheckt und in der Readme dokumentiert
-Review durch jemand anderes

Zeit: 8h

neuen Namen überlegen xD

prepare local RaspBerryPi-Development Environment

Abnahmekritieren:
-Auf dem Laptop wird ein RaspberryPi simuliert
-Alles nötige im Git eingecheckt und in der Readme dokumentiert
-Review durch jemand anderes

Zeit: 4h

Audio Detection

Github/Paper for implementation/theory. especially with ideas for at least compute the difference between audio and analog signal. advanced: some ideas for identifying human sounds that are promising.

Zeit: never ending Story

Reinforcement Learning

Github/Paper for implementation/theory. especially with ideas for expressing the state for the music.

Zeit: never ending Story