如何使用 openCV c++ 拍摄 kinect 视频图像和深度图像？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/13876366/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How to take kinect video image and depth image with openCV c++?
提问by Mehmet Zaim
I'm new about opencv(c++) and kinect. I try to take a video image with c++ from kinect. I search everywhere but I didn't find anything. Because people are made using openNI or OpenKinect. I don't want to use this lib. How can I do it??
我是 opencv(c++) 和 kinect 的新手。我尝试使用 kinect 中的 C++ 拍摄视频图像。我到处搜索，但没有找到任何东西。因为人们是使用 openNI 或 OpenKinect 制作的。我不想使用这个库。我该怎么做？？
Thanks!!!
谢谢！！！
采纳答案by étienne
You could use the kinect for windows SDK to grab the frames, and then convert them to an opencv format. See this code example which does that in visual studio (found in this threadon the microsoft forums), unfortunately I don't have a kinect right now to test the code:
您可以使用 kinect for windows SDK 来抓取帧，然后将它们转换为 opencv 格式。请参阅此代码示例，它在 Visual Studio 中执行此操作（在Microsoft 论坛上的此线程中找到），不幸的是我现在没有 kinect 来测试代码：
#include "stdafx.h"
#define COLOR_WIDTH 640
#define COLOR_HIGHT 480
#define DEPTH_WIDTH 320
#define DEPTH_HIGHT 240
#define SKELETON_WIDTH 640
#define SKELETON_HIGHT 480
#define CHANNEL 3
BYTE buf[DEPTH_WIDTH * DEPTH_HIGHT * CHANNEL];
int drawColor(HANDLE h, IplImage* color)
{
const NUI_IMAGE_FRAME * pImageFrame = NULL;
HRESULT hr = NuiImageStreamGetNextFrame(h, 0, &pImageFrame);
if (FAILED(hr))
{
cout << "Get Image Frame Failed" << endl;
return -1;
}
NuiImageBuffer * pTexture = pImageFrame->pFrameTexture;
KINECT_LOCKED_RECT LockedRect;
pTexture->LockRect(0, &LockedRect, NULL, 0);
if (LockedRect.Pitch != 0)
{
BYTE * pBuffer = (BYTE*) LockedRect.pBits;
cvSetData(color, pBuffer, LockedRect.Pitch);
}
cvShowImage("color image", color);
NuiImageStreamReleaseFrame(h, pImageFrame);
return 0;
}
int drawDepth(HANDLE h, IplImage* depth)
{
const NUI_IMAGE_FRAME * pImageFrame = NULL;
HRESULT hr = NuiImageStreamGetNextFrame(h, 0, &pImageFrame);
if (FAILED(hr))
{
cout << "Get Image Frame Failed" << endl;
return -1;
}
// temp1 = depth;
NuiImageBuffer * pTexture = pImageFrame->pFrameTexture;
KINECT_LOCKED_RECT LockedRect;
pTexture->LockRect(0, &LockedRect, NULL, 0);
if (LockedRect.Pitch != 0)
{
USHORT * pBuff = (USHORT*) LockedRect.pBits;
for (int i = 0; i < DEPTH_WIDTH * DEPTH_HIGHT; i++)
{
BYTE index = pBuff[i] & 0x07;
USHORT realDepth = (pBuff[i] & 0xFFF8) >> 3;
BYTE scale = 255 - (BYTE)(256 * realDepth / 0x0fff);
buf[CHANNEL * i] = buf[CHANNEL * i + 1] = buf[CHANNEL * i + 2] = 0;
switch (index)
{
case 0:
buf[CHANNEL * i] = scale / 2;
buf[CHANNEL * i + 1] = scale / 2;
buf[CHANNEL * i + 2] = scale / 2;
break;
case 1:
buf[CHANNEL * i] = scale;
break;
case 2:
buf[CHANNEL * i + 1] = scale;
break;
case 3:
buf[CHANNEL * i + 2] = scale;
break;
case 4:
buf[CHANNEL * i] = scale;
buf[CHANNEL * i + 1] = scale;
break;
case 5:
buf[CHANNEL * i] = scale;
buf[CHANNEL * i + 2] = scale;
break;
case 6:
buf[CHANNEL * i + 1] = scale;
buf[CHANNEL * i + 2] = scale;
break;
case 7:
buf[CHANNEL * i] = 255 - scale / 2;
buf[CHANNEL * i + 1] = 255 - scale / 2;
buf[CHANNEL * i + 2] = 255 - scale / 2;
break;
}
}
cvSetData(depth, buf, DEPTH_WIDTH * CHANNEL);
}
NuiImageStreamReleaseFrame(h, pImageFrame);
cvShowImage("depth image", depth);
return 0;
}
int drawSkeleton(IplImage* skeleton)
{
NUI_SKELETON_FRAME SkeletonFrame;
CvPoint pt[20];
HRESULT hr = NuiSkeletonGetNextFrame(0, &SkeletonFrame);
bool bFoundSkeleton = false;
for (int i = 0; i < NUI_SKELETON_COUNT; i++)
{
if (SkeletonFrame.SkeletonData[i].eTrackingState
== NUI_SKELETON_TRACKED)
{
bFoundSkeleton = true;
}
}
// Has skeletons!
//
if (bFoundSkeleton)
{
NuiTransformSmooth(&SkeletonFrame, NULL);
memset(skeleton->imageData, 0, skeleton->imageSize);
for (int i = 0; i < NUI_SKELETON_COUNT; i++)
{
if (SkeletonFrame.SkeletonData[i].eTrackingState
== NUI_SKELETON_TRACKED)
{
for (int j = 0; j < NUI_SKELETON_POSITION_COUNT; j++)
{
float fx, fy;
NuiTransformSkeletonToDepthImageF(
SkeletonFrame.SkeletonData[i].SkeletonPositions[j],
&fx, &fy);
pt[j].x = (int) (fx * SKELETON_WIDTH + 0.5f);
pt[j].y = (int) (fy * SKELETON_HIGHT + 0.5f);
cvCircle(skeleton, pt[j], 5, CV_RGB(255, 0, 0), -1);
}
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HEAD],
pt[NUI_SKELETON_POSITION_SHOULDER_CENTER],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_SHOULDER_CENTER],
pt[NUI_SKELETON_POSITION_SPINE], CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_SPINE],
pt[NUI_SKELETON_POSITION_HIP_CENTER],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HAND_RIGHT],
pt[NUI_SKELETON_POSITION_WRIST_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_WRIST_RIGHT],
pt[NUI_SKELETON_POSITION_ELBOW_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_ELBOW_RIGHT],
pt[NUI_SKELETON_POSITION_SHOULDER_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_SHOULDER_RIGHT],
pt[NUI_SKELETON_POSITION_SHOULDER_CENTER],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_SHOULDER_CENTER],
pt[NUI_SKELETON_POSITION_SHOULDER_LEFT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_SHOULDER_LEFT],
pt[NUI_SKELETON_POSITION_ELBOW_LEFT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_ELBOW_LEFT],
pt[NUI_SKELETON_POSITION_WRIST_LEFT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_WRIST_LEFT],
pt[NUI_SKELETON_POSITION_HAND_LEFT], CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HIP_CENTER],
pt[NUI_SKELETON_POSITION_HIP_RIGHT], CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HIP_RIGHT],
pt[NUI_SKELETON_POSITION_KNEE_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_KNEE_RIGHT],
pt[NUI_SKELETON_POSITION_ANKLE_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_ANKLE_RIGHT],
pt[NUI_SKELETON_POSITION_FOOT_RIGHT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HIP_CENTER],
pt[NUI_SKELETON_POSITION_HIP_LEFT], CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_HIP_LEFT],
pt[NUI_SKELETON_POSITION_KNEE_LEFT], CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_KNEE_LEFT],
pt[NUI_SKELETON_POSITION_ANKLE_LEFT],
CV_RGB(0, 255, 0));
cvLine(skeleton, pt[NUI_SKELETON_POSITION_ANKLE_LEFT],
pt[NUI_SKELETON_POSITION_FOOT_LEFT], CV_RGB(0, 255, 0));
}
}
}
cvShowImage("skeleton image", skeleton);
return 0;
}
int main(int argc, char * argv[])
{
IplImage* color = cvCreateImageHeader(cvSize(COLOR_WIDTH, COLOR_HIGHT), IPL_DEPTH_8U, 4);
IplImage* depth = cvCreateImageHeader(cvSize(DEPTH_WIDTH, DEPTH_HIGHT),IPL_DEPTH_8U, CHANNEL);
IplImage* skeleton = cvCreateImage(cvSize(SKELETON_WIDTH, SKELETON_HIGHT),IPL_DEPTH_8U, CHANNEL);
cvNamedWindow("color image", CV_WINDOW_AUTOSIZE);
cvNamedWindow("depth image", CV_WINDOW_AUTOSIZE);
cvNamedWindow("skeleton image", CV_WINDOW_AUTOSIZE);
HRESULT hr = NuiInitialize(
NUI_INITIALIZE_FLAG_USES_DEPTH_AND_PLAYER_INDEX
| NUI_INITIALIZE_FLAG_USES_COLOR
| NUI_INITIALIZE_FLAG_USES_SKELETON);
if (hr != S_OK)
{
cout << "NuiInitialize failed" << endl;
return hr;
}
HANDLE h1 = CreateEvent(NULL, TRUE, FALSE, NULL);
HANDLE h2 = NULL;
hr = NuiImageStreamOpen(NUI_IMAGE_TYPE_COLOR, NUI_IMAGE_RESOLUTION_640x480,
0, 2, h1, &h2);
if (FAILED(hr))
{
cout << "Could not open image stream video" << endl;
return hr;
}
HANDLE h3 = CreateEvent(NULL, TRUE, FALSE, NULL);
HANDLE h4 = NULL;
hr = NuiImageStreamOpen(NUI_IMAGE_TYPE_DEPTH_AND_PLAYER_INDEX,
NUI_IMAGE_RESOLUTION_320x240, 0, 2, h3, &h4);
if (FAILED(hr))
{
cout << "Could not open depth stream video" << endl;
return hr;
}
HANDLE h5 = CreateEvent(NULL, TRUE, FALSE, NULL);
hr = NuiSkeletonTrackingEnable(h5, 0);
if (FAILED(hr))
{
cout << "Could not open skeleton stream video" << endl;
return hr;
}
while (1)
{
WaitForSingleObject(h1, INFINITE);
drawColor(h2, color);
WaitForSingleObject(h3, INFINITE);
drawDepth(h4, depth);
WaitForSingleObject(h5, INFINITE);
drawSkeleton(skeleton);
//exit
int c = cvWaitKey(1);
if (c == 27 || c == 'q' || c == 'Q')
break;
}
cvReleaseImageHeader(&depth);
cvReleaseImageHeader(&color);
cvReleaseImage(&skeleton);
cvDestroyWindow("depth image");
cvDestroyWindow("color image");
cvDestroyWindow("skeleton image");
NuiShutdown();
return 0;
}
回答by Evil Closet Monkey
OpenCV does not offer the ability to connect to and process data from the Kinect sensor; unless you treat the Kinect as a regular webcam. You will want to fetch the data using one of the APIs and send it to OpenCV. To get the data from the Kinect you can use:
OpenCV 不提供连接和处理来自 Kinect 传感器的数据的能力；除非您将 Kinect 视为普通网络摄像头。您将希望使用其中一种 API 获取数据并将其发送到 OpenCV。要从 Kinect 获取数据，您可以使用：
If your employer has a problem with one of the APIs, that is there choice. But the use of OpenCV does not eliminate your need to use one of them.
如果您的雇主对其中一个 API 有问题，那么您可以选择。但是使用 OpenCV 并不能消除您使用其中之一的需要。
A quick search on MSDNreveals multiple threads on the the subject. The most straight forward approach I've read about is using cvSetDatato import the data, after converting the image:
一个在MSDN上快速搜索揭示的主题多线程。我读过的最直接的方法是cvSetData在转换图像后使用导入数据：
RGB
RGB
IplImage * ovImage = NULL;
ovImage = cvCreateImage(cvSize(640, 480), 8, 4);
cvSetData(ovImage, pBuffer, ovImage->widthStep);
Depth
深度
ovImage = cvCreateImage(cvSize(640, 480), 8, 1);
I also found the freenomad_visionproject on GitHub that provides libfreenect support with OpenCV and OpenGL. If you dislike using libfreenect, the code can easily serve as reference since the incoming data is all the same and (likely) would be converted the same.
我还在GitHub 上找到了freenomad_vision项目，它提供了对 OpenCV 和 OpenGL 的 libfreenect 支持。如果您不喜欢使用 libfreenect，代码可以很容易地用作参考，因为传入的数据都是相同的，并且（可能）会被相同地转换。
回答by Shubham Batra
In case if someone is redirected here looking for a simpler method for visualizing the Kinect depth stream, I was able to do this in the following way for the KinectV2.
如果有人被重定向到这里寻找更简单的 Kinect 深度流可视化方法，我可以通过以下方式为 KinectV2 执行此操作。
Mat CDepthMap::getFrame()
{
IDepthFrame* frame;
Mat depthImage;
hr = _depth_reader->AcquireLatestFrame(&frame);
if (SUCCEEDED(hr)) {
const UINT imgSize = sDepthWidth*sDepthHeight; //512*424
UINT16 pixelData[imgSize];
hr = frame->CopyFrameDataToArray(imgSize, pixelData);
if (SUCCEEDED(hr)) {
depthImage = Mat(sDepthHeight,sDepthWidth, CV_8U);
for (UINT i = 0; i < imgSize; i++) {
UINT16 depth = pixelData[i];
depthImage.at<UINT8>(i) = LOWORD(depth);
}
}
SafeRelease(frame);
}
return depthImage;
}
