How to do a face detection with kinect and opencv?

i have kinect running with openni and opencv. i have done facedetection with haarcascade with a webcam but i'm not able to do it with kinect

int main( int argc, char* argv[] ){
    try
    {
        ... // call OpenCV
    VideoCapture capture( CV_CAP_OPENNI );
   CvHaarClassifierCascade* cascade=0;
    CvMemStorage* storage=0;
    CvSeq* face;
    storage=cvCreateMemStorage(0);
    cascade=(CvHaarClassifierCascade *)cvLoad("haarcascade_profileface.xml",0,0,0);*/
    if(cascade){
    for(;;)
    {
        Mat depthMap;


        if( !capture.grab() )
        {
            cout << "Can not grab images." << endl;
            return -1;
        }
        else
        {
            if(  capture.retrieve( depthMap,CV_CAP_OPENNI_BGR_IMAGE) )

            {
                /*IplImage* img = new IplImage(depthMap);
                face=cvHaarDetectObjects(img,cascade,storage,1.1,3,CV_HAAR_DO_CANNY_PRUNING,cvSize(0,0));
                for(int i=0;i<(face?face->total:0);i++)
                {

                        CvRect* r=(CvRect*)cvGetSeqElem(face,i);
                        CvPoint pt1={r->x,r->y};
                        CvPoint pt2={r->x+r->width,r->y+r->height};
                        cvRectangle(img,pt1,pt2,CV_RGB(0,255,0),3,4,0);
                         //imshow( "depth map", depthMap);
                }*/
                const float开发者_StackOverflow社区 scaleFactor = 0.05f;
                //Mat show; depthMap.convertTo( show, CV_8UC3, scaleFactor );
                imshow( "depth map", depthMap);
  //          }



        }

        if( waitKey( 30 ) >= 0 )
            break;
    }
}

    }
    catch( cv::Exception& e )
    {
        const char* err_msg = e.what();
        std::cout << "exception caught: " << err_msg << std::endl;
    }
    return 0;
}

...somebody please help me out

cvHaarDetectObjects only works for gray scale images, or Matrix of the type CV_8U.
So you must do the conversion after retrieving RGB image from Kinect.

cvtColor( frame, frame_gray, CV_BGR2GRAY );

Also I see you naming depthMap to an RGB image, it might be confusing.