Installing OpenNI in Ubuntu 14.04


Hello everyone,
Few month ago, I saw a video , doing cool staff using Kinect , like object tracking ,  localization etc . So I bought a Kinect from eBay and start to  code. Before going on to detail of  it is really necessary to understand the physics behind the Kinect to get optimum use .
What is a Kinect?
Kinect is a device which was originally build as plug-in device for XBOX gaming. it is use to acquire detail ,color, width, height and also the depth  in the range of 20 inch to 20 feet approximately ,using a  inferred net projecting towards to the front object . height ,width and color details are taken using the RGB camera mounted in it and the depth detail taken using Depth camera which is generating  depth values  for each pixel comparing the inferred net projected and reflected inferred net which has  defected due to the depth and curvature of the facing objects.
                               There are few iteration of Kinect sensor have made. But newer sensors are using different techniques to acquire the depth value. I used xbox360 1414 module (see the bottom of Kinect sensor) which has good compatibility with the OpenNI libraries, if you are purchasing now check before the compatibility of OpenNI or any other library that you planning to use, and also there is a module called xbox360 1413 which is a later iteration as I heard it has some issues with OpenNI library due to hardware change,better check it out before purchasing .

I dig little bit deeper to understand  the hardware level . So I found this video on youtube. Check it out if you are real like to know what inside the casing.
USB power Adapter
Kinect come with its own USB power adapter because Kinect need considerable amount of power which cannot supply through the directly from USB connection. If you try without power adapter you  will probability get error message like,
 No Kinect connected...
Make sure that you have both component with you.
Power adapter has Y connection at the wire end. At one end there is male USB connector head and the other end has female head which is compatible with the Kinect out coming wire head. And also the little LED green indicator on the Y joint of the wire so that you can check the power Adapter and power supply.
Interfacing with computer
As I mention before Kinect was originally build and introduce for Xbox. After few times of release, programmer’s hackers realized that this device could use more than gaming , all kind 3D sensing  they couldn't do before, still at that time there was no drivers compatible with computer . So OpenNI drivers were build  to fill the gap. Few years after windows introduce Kinect Studio for free use to the computer. You can use them also if you are using Windows. Kinect studio easily  interface with VB, I haven’t try that yet although I run example provided in Kinect studio.
You can download Kinect Studio latest version from here.
OpenNI
OpenNI is a one of most powerful 3D vision base middle-ware free available in the Internet. Basically Until 2013,PrimeSense  company had developed open source libraries (OpenNI, NITE) for Kinect  but In 2013, Apple bought  PrimeSense and despite OpenNI is still open source, NITE2 is no more available for developers which is used for applications such as skeleton, hands, object, gesture tracking. Without NITE, just with libraries OpenNI1.5, you can just control utilities like depth view, LED light and camera motor.  But still the last versions of NITE 2.2.0.11 is available in the Internet.
You can check about NITE 2.2.0.11   from below link.
http://openni.ru/files/nite/
Here on wards I will explain  to  install OpenNI  and NITE into the the processing
1)     Installing OpenNI and NITE
(i)                I highly recommend you  to install 32bit version of the OpenNI although you are running on 64bit machine. Because I tried the 64 bit version but it didn't work out for me. I tried to resolve the problem in various way but it path to nowhere. Also checked the issues on various forum and all suggest to  use 32 bit version instead of 64 bit version.
(ii)              First download OpenNI-NITE installer package from here and extract it.                                                            
(iii)            Navigate to the extracted folder  OpenNI-Bin-Dev-Linux-x86-vx.x.x.x then install it using  sudo  ./install.sh command as below. If you are using build command first time  it will probably crash and stop the installation. If so go to the error message. It will probably say missing command or library. First in install  particular library related to the  command  and run it again.

(iv)             Then navigate to the NITE-Bin-Dev-Linux-x86-vx.x.x.x  and install it using sudo ./install.sh
(v)              Finally Kinect folder and then to the Sensor-Bin-Linux-x86-vx.x.x.x and install it also using  sudo ./install.sh
       
       

(vi)            Now necessary library installation is over .
(vii)          To check whether the installation is correct First plug in the Kinect to computer and plug in the power supply and then navigate into the OpenNI-Bin-Dev-Linux-x86-vx.x.x.x  -> Samples -> Bin -> x86-Release run the example NiViewer using ./NiViewer command
 If All steps are done correctly you will see window with depth image and the color image together as following. Also you can try other example also.




2)    Configure with processing
Processing is one of most powerful and simple open source language integrated development environment among visual design communities which can easily be used to analyze and process graphical data Because it is free and tons of free libraries are available for various visual task.
Also there are few library regarding Kinect data processing. In this tutorial what I trying to use is SimpleopenNI library which is actually so far very good. Unfortunately at this time SimpleopenNI does not support later release version of processing. But older version of processing works fine. I actually use processing 2.2.1 version for my projects.
(I) You can download processing 2.2.1 from below link http://download.processing.org/processing-2.2.1-linux32.tgz
If you trying to use later version of processing check whether SimpleopenNI library is supporting for that.
(II) After downloading unzip the downloaded folder and navigate to the inside the folder and run  ./processing
       Processing window will appear 

 (III)  Then goto Sketch > Import Library... >Add Library                                                                        then the below window will appear

(IV) Then search for SimpleOpenNI library
(Because of I already downloaded the library button is appear as Remove  in your case it will be install )
Click the button to install it then it will automatically download necessary files and  it will configure with your processing libraries.

(V) Now configuration is done.
     Now test it.
TEST


   1.  First plug in the Kinect to your computer also power supply to the Kinect.(now green light in front should blink)
   2.  then open processing
    Navigate to File > Examples... > SimpleOpenNI > DepthImage   (You can any of other example under SimpleOpenNI) and Run it



 If you run Depth-image example
Following window with gray scale depth Image and the normal color image will appear



 (3)  now ready to make your first Kinect project..

    

Comments

Post a Comment

Popular posts from this blog

Measuring 3D Distances between points using Kinect

Image
Now time to move on to some simple application from the kinect depth image. As I mentioned , Kinect keep track of depth values of all the pixels related to pixel position.  That points are corresponding to the real world instances of points. So every point on this depth image  can be considered as three dimensional vector as (X, Y, V) as below. X Value, Y Value, Z Value,  from the Cartesian coordinate system. We can demonstrate the point as 3 Dimensional vector  shown below, So if we denote two instant of point as Vector, We can easily calculate distances between them.   C = V1 – U1 Then we can get magnitude of the C, that’s mean the distance between Point1 and Point2. Before  Explaining the How I code , I will show the Code and Result,   Result has pretty good accuracy as I expected. To implement a vector, we can use PVector Data type form the processing with tree argument...
Read more

Implementation - Robot Navigation

Image
 Block Diagram Initialization of Pyro object  robot = Pyro4.Proxy("PYRONAME:example.robot") # use name server object lookup uri shortcut con =connect() #############..............................  Define particles  defining number of particles,initiating particles array and assigning initial position # Generate initial particles. Each particle is (x, y, theta).  number_of_particles = 25 start_state = np.array([500.0, 0.0, 45.0 / 180.0 * pi])  initial_particles = [copy.copy(Particle(start_state)) for _ in xrange(number_of_particles)] Initiating SLAM object fs = FastSLAM(initial_particles, robot_width, scanner_displacement, control_motion_factor, control_turn_factor, measurement_distance_stddev, measurement_angle_stddev, minimum_correspondence_likelihood)   Loop check whether incoming data is valid try :      while True:         ...
Read more

Full stack development of Robot navigation

Image
Hi everyone, Well, Developing a system that can behave intelligently in environment that previously unknown is challenging? because decision, it has to make is totally, well i can say mostly,? unpredictable before hand . Saying totally unpredictable is wrong which leads to unresolvable problem,So? that means every environment should have some way of predictability in order to get confident judgment about next move . As in controlled environment like assembly line next movement is measured and predictable , if we consider a car in the road , judgment of the next set of action can be predicted using the road signs , other vehicle movement , position and destination of the car and etc.. with tolerable perturbations handling . But if you consider the rover in the mars , only what system has is estimated model how environment could be , build using previous observation , that mean system has to predicted the action mostly according to the what it sens. So that sot of Automated...
Read more