1

我已经安装了 openni2.2、nite2.2 和 kinect SDK 1.6 以及用于处理的 Simpleopenni 库。除了红外图像外,一切正常 - 它根本不存在。这真的很奇怪,因为同时我可以清楚地看到深度图像(并且深度图像在逻辑上需要红外摄像机和投影仪才能运行)。所以我认为驱动程序或软件有问题?我想将kinect用作红外相机。请帮忙,下面我附上我的测试代码:

/* --------------------------------------------------------------------------
 * SimpleOpenNI IR Test
 * --------------------------------------------------------------------------
 * Processing Wrapper for the OpenNI/Kinect library
 * http://code.google.com/p/simple-openni
 * --------------------------------------------------------------------------
 * prog:  Max Rheiner / Interaction Design / zhdk / http://iad.zhdk.ch/
 * date:  02/16/2011 (m/d/y)
 * ----------------------------------------------------------------------------
 */

import SimpleOpenNI.*;


SimpleOpenNI  context;

void setup()
{
  context = new SimpleOpenNI(this);

  // enable depthMap generation 
  if(context.enableDepth() == false)
  {
     println("Can't open the depthMap, maybe the camera is not connected!"); 
     exit();
     return;
  }

  // enable ir generation
  if(context.enableIR() == false)
  {
     println("Can't open the depthMap, maybe the camera is not connected!"); 
     exit();
     return;
  }

  background(200,0,0);
  size(context.depthWidth() + context.irWidth() + 10, context.depthHeight()); 
}

void draw()
{
  // update the cam
  context.update();

  // draw depthImageMap
  image(context.depthImage(),0,0);

  // draw irImageMap
  image(context.irImage(),context.depthWidth() + 10,0);
}
4

4 回答 4

2

这可以完成工作:

context.enableIR(1,1,1);
于 2014-04-18T20:01:12.730 回答
0

您是否能够捕获红外流,但您只是看不到它?

那么问题可能是RANGE(它应该在 [0, 255] 中)。

我在 Python 和 C++ 中遇到了这个问题;我通过将数组除以范围(最大值-最小值)然后将所有条目乘以 255 来解决它。

于 2014-06-04T00:07:51.190 回答
0

user3550091 是对的!以下是我完整的工作代码(Processing+OpenNI)供参考:

import SimpleOpenNI.*;
SimpleOpenNI  context;
void setup(){
  size(640 * 2 + 10, 480);
  context = new SimpleOpenNI(this);
  if(context.isInit() == false){
     println("fail"); 
     exit();
     return;
  }
  context.enableDepth();

  // enable ir generation
  //context.enableIR(); old line 
  context.enableIR(1,1,1); //new line

  background(200,0,0);
}

void draw(){
  context.update();
  image(context.depthImage(),context.depthWidth() + 10,0);

  image(context.irImage(),0,0);
}
于 2014-06-24T11:09:22.467 回答
0

我有完全相同的问题。这不是一个解决方案,但我能从 kinect 获得红外图像的最接近方法是从深度图像中获取点云

import SimpleOpenNI.*;

import processing.opengl.*;

SimpleOpenNI kinect;

void setup()
{

  size( 1024, 768, OPENGL);

  kinect = new SimpleOpenNI( this );

  kinect.enableDepth();

}

void draw()
{

  background( 0);

  kinect.update();
  image(kinect.depthImage(),0,0,160,120);//check depth image

  translate( width/2,  height/2, -1000);

  rotateX( radians(180));

  stroke(255);

  PVector[] depthPoints = kinect.depthMapRealWorld();

  //the program get stucked in the for loop it loops 307200 times and I don't have any points output

  for( int i = 0; i < depthPoints.length ; i+=4)//draw point for every 4th pixel
  {

    PVector currentPoint = depthPoints[i];
    if(i == 0) println(currentPoint);
    point(currentPoint.x,  currentPoint.y, currentPoint.z );
  }

}
于 2014-03-11T15:25:48.720 回答