Prelude
My initial design was to build a set of robots around the raspberry Pi and use other components in the kit to build the control systems. Since I am yet to receive the kit, I have moved to researching the Image capture and recognition part of the project.
Introduction
OpenCV (Open Source Computer Vision) is a library of programming functions mainly aimed at real-time computer vision, developed by Intel Russia research center in Nizhny Novgorod, and now supported by Willow Garage and Itseez. It is free for use under the open-source BSD license. The library is cross-platform. It focuses mainly on real-time image processing. If the library finds Intel's Integrated Performance Primitives on the system, it will use these proprietary optimized routines to accelerate itself.
OpenCV has gained a lot of attention for the last few years with the advent of the RPi and other single board computers, it is now possible to have simpler Image Manipulation tasks executed on DIY systems. One module in my scifi design is to use gesture recognition and for that I intend to use an RPI 2 dedicated to Image processing and sensing.
I am going to start with installing OpenCV on the RPI and then using it to simply acquiring an image. I will be using C++ for more advanced stuff since I am more comfortable with it as compared to Python but I will do the initial stuff using Python 2.7.
Lets get started...
Installing OpenCV
Now there are a LOT of guides out there for this BUT I am giving you the details of "my way” of doing the install. If I make a mistake and you have a better way, please leave a comment and I will update it here.
The first thing is to download the OpenCV library for Raspberry Pi and to do that we go to http://opencv.org/downloads.html
I chose the last stable version which was 2.4.10 and I think that should work for the most part.
We also need to install some dependencies run the following commands
sudo apt-get -y install build-essential cmake cmake-curses-gui pkg-config libpng12-0 libpng12-dev libpng++-dev libpng3 libpnglite-dev zlib1g-dbg zlib1g zlib1g-dev pngtools libtiff4-dev libtiff4 libtiffxx0c2 libtiff-tools libeigen3-dev
and then
sudo apt-get -y install libjpeg8 libjpeg8-dev libjpeg8-dbg libjpeg-progs ffmpeg libavcodec-dev libavcodec53 libavformat53 libavformat-dev libgstreamer0.10-0-dbg libgstreamer0.10-0 libgstreamer0.10-dev libxine1-ffmpeg libxine-dev libxine1-bin libunicap2 libunicap2-dev swig libv4l-0 libv4l-dev python-numpy libpython2.6 python-dev python2.6-dev libgtk2.0-dev
Next unzip it using
unzip opencv-2.4.10.zip cd opencv-2.4.10 mkdir release cd release ccmake ../
press ‘c’ to configure and toggle the options you want. I did the following.
ANT_EXECUTABLE ANT_EXECUTABLE-NOTFOUND BUILD_DOCS ON BUILD_EXAMPLES ON BUILD_JASPER ON BUILD_JPEG ON BUILD_OPENEXR ON BUILD_PACKAGE ON BUILD_PERF_TESTS ON BUILD_PNG ON BUILD_SHARED_LIBS ON BUILD_TBB OFF BUILD_TESTS ON BUILD_TIFF ON BUILD_WITH_DEBUG_INFO ON BUILD_ZLIB ON BUILD_opencv_apps ON BUILD_opencv_calib3d ON BUILD_opencv_contrib ON BUILD_opencv_core ON BUILD_opencv_features2d ON BUILD_opencv_flann ON BUILD_opencv_gpu ON BUILD_opencv_highgui ON BUILD_opencv_imgproc ON BUILD_opencv_legacy ON BUILD_opencv_ml ON BUILD_opencv_nonfree ON BUILD_opencv_objdetect ON BUILD_opencv_ocl ON BUILD_opencv_photo ON BUILD_opencv_python ON BUILD_opencv_stitching ON BUILD_opencv_superres ON BUILD_opencv_ts ON BUILD_opencv_video ON BUILD_opencv_videostab ON BUILD_opencv_world OFF CLAMDBLAS_INCLUDE_DIR CLAMDBLAS_INCLUDE_DIR-NOTFOUND CLAMDBLAS_ROOT_DIR CLAMDBLAS_ROOT_DIR-NOTFOUND CLAMDFFT_INCLUDE_DIR CLAMDFFT_INCLUDE_DIR-NOTFOUND CLAMDFFT_ROOT_DIR CLAMDFFT_ROOT_DIR-NOTFOUND CMAKE_BUILD_TYPE Release CMAKE_CONFIGURATION_TYPES Debug;Release CMAKE_INSTALL_PREFIX /usr/local CMAKE_VERBOSE OFF CUDA_BUILD_CUBIN OFF CUDA_BUILD_EMULATION OFF CUDA_HOST_COMPILER /usr/bin/gcc CUDA_SDK_ROOT_DIR CUDA_SDK_ROOT_DIR-NOTFOUND CUDA_SEPARABLE_COMPILATION OFF CUDA_TOOLKIT_ROOT_DIR CUDA_TOOLKIT_ROOT_DIR-NOTFOUND CUDA_VERBOSE_BUILD OFF EIGEN_INCLUDE_PATH /usr/include/eigen3 ENABLE_NEON OFF ENABLE_NOISY_WARNINGS OFF ENABLE_OMIT_FRAME_POINTER ON ENABLE_PRECOMPILED_HEADERS ON ENABLE_PROFILING OFF ENABLE_SOLUTION_FOLDERS OFF ENABLE_VFPV3 OFF EXECUTABLE_OUTPUT_PATH /home/pi/opencv-2.4.8/release/bin GIGEAPI_INCLUDE_PATH GIGEAPI_INCLUDE_PATH-NOTFOUND GIGEAPI_LIBRARIES GIGEAPI_LIBRARIES-NOTFOUND INSTALL_CREATE_DISTRIB OFF INSTALL_C_EXAMPLES OFF INSTALL_PYTHON_EXAMPLES OFF INSTALL_TO_MANGLED_PATHS OFF OPENCV_CONFIG_FILE_INCLUDE_DIR /home/pi/opencv/opencv-2.4.8/release OPENCV_EXTRA_MODULES_PATH OPENCV_WARNINGS_ARE_ERRORS OFF OPENEXR_INCLUDE_PATH OPENEXR_INCLUDE_PATH-NOTFOUND PVAPI_INCLUDE_PATH PVAPI_INCLUDE_PATH-NOTFOUND PYTHON_NUMPY_INCLUDE_DIR /usr/lib/pymodules/python2.7/numpy/core/include PYTHON_PACKAGES_PATH lib/python2.7/dist-packages SPHINX_BUILD SPHINX_BUILD-NOTFOUND WITH_1394 OFF WITH_CUBLAS OFF WITH_CUDA OFF WITH_CUFFT OFF WITH_EIGEN ON WITH_FFMPEG ON WITH_GIGEAPI OFF WITH_GSTREAMER ON WITH_GTK ON WITH_JASPER ON WITH_JPEG ON WITH_LIBV4L ON WITH_NVCUVID OFF WITH_OPENCL ON WITH_OPENCLAMDBLAS ON WITH_OPENCLAMDFFT ON WITH_OPENEXR ON WITH_OPENGL ON WITH_OPENMP OFF WITH_OPENNI OFF WITH_PNG ON WITH_PVAPI ON WITH_QT OFF WITH_TBB OFF WITH_TIFF ON WITH_UNICAP OFF WITH_V4L ON WITH_XIMEA OFF WITH_XINE OFF
For the most part I just left things to the default except for enabling stuff with Jpeg, Png and TBB.
press c again to configure and then g to generate the make file.
This should drop you back to the command prompt.
Next build with
make
I did this whole thing on a RPi 2 with a class 10 card. Yes it makes a difference since class 10 cards have faster access rates.
It took around 3.5 hours and if you happen to do something wrong, do a
make clean make
Lastly do a
make install
and then reboot. This should have you up and running.
Testing everything
I am assuming that you are using the RPi Camera and that you have enabled the RPi Camera using raspi-config. If not, then please refer- (https://www.raspberrypi.org/help/camera-module-setup/)
You need to either attach a monitor to the RPi or access it via vnc as we did in the last post. Start the windows manager by typing
startx
You should now have the windows system running and should be able to see the desktop. Start a new terminal and create a new folder by typing
mkdir opencv_tests
Next create a new file by typing
cd opencv_tests leafpad test1.py
I am using leafpad as its just simple when using the windows env.
Type the following lines
# import the necessary packages
from picamera.array import PiRGBArray
from picamera import PiCamera
import time
import cv2
# initialize the camera and grab a reference to the raw camera capture
camera = PiCamera()
rawCapture = PiRGBArray(camera)
# allow the camera to warmup
time.sleep(0.1)
# grab an image from the camera
camera.capture(rawCapture, format="bgr")
image = rawCapture.array
# display the image on screen and wait for a keypress
cv2.imshow("Image", image)
cv2.waitKey(0)
Save the file and close LeaftPad which will drop you back to the LX Terminal
Now just type
python test1.py
And that should display an image in a new windows. Press any key and it will close the windows and return you to the command prompt.
Conclusion
This was a lot of fun and I think to start with you should use python even if you have used OpenCV in C in the past. Its much simpler and with the power of the RPI2 the lag is almost gone. I will be implementing some gesture recognition while I wait for the Kit to be delivered.
See you next time...
Top Comments
-
jlopez2022
-
Cancel
-
Vote Up
0
Vote Down
-
-
Sign in to reply
-
More
-
Cancel
-
ipv1
in reply to jlopez2022
-
Cancel
-
Vote Up
0
Vote Down
-
-
Sign in to reply
-
More
-
Cancel
Comment-
ipv1
in reply to jlopez2022
-
Cancel
-
Vote Up
0
Vote Down
-
-
Sign in to reply
-
More
-
Cancel
Children