How to display a raw YUV frame in a Cocoa OpenGL program

Question

I have been assigned wit the task to write a program that takes a sample raw YUV file and display it in a Cocoa OpenGL program.

I am an intern at my job and I have l

Answer 1

I've done this with YUV frames captured from a CCD camera. Unfortunately, there are a number of different YUV formats. I believe the one that Apple uses for the GL_YCBCR_422_APPLE texture format is technically 2VUY422. To convert an image from a YUV422 frame generated by an IIDC Firewire camera to 2VUY422, I've used the following:

void yuv422_2vuy422(const unsigned char *theYUVFrame, unsigned char *the422Frame, const unsigned int width, const unsigned int height) 
{
    int i =0, j=0;
    unsigned int numPixels = width * height;
    unsigned int totalNumberOfPasses = numPixels * 2;
    register unsigned int y0, y1, y2, y3, u0, u2, v0, v2;

    while (i < (totalNumberOfPasses) )
    {
        u0 = theYUVFrame[i++]-128;
        y0 = theYUVFrame[i++];
        v0 = theYUVFrame[i++]-128;
        y1 = theYUVFrame[i++];
        u2 = theYUVFrame[i++]-128;
        y2 = theYUVFrame[i++];
        v2 = theYUVFrame[i++]-128;
        y3 = theYUVFrame[i++];

        // U0 Y0 V0 Y1 U2 Y2 V2 Y3

        // Remap the values to 2VUY (YUYS?) (Y422) colorspace for OpenGL
        // Y0 U Y1 V Y2 U Y3 V

        // IIDC cameras are full-range y=[0..255], u,v=[-127..+127], where display is "video range" (y=[16..240], u,v=[16..236])

        the422Frame[j++] = ((y0 * 240) / 255 + 16);
        the422Frame[j++] = ((u0 * 236) / 255 + 128);
        the422Frame[j++] = ((y1 * 240) / 255 + 16);
        the422Frame[j++] = ((v0 * 236) / 255 + 128);
        the422Frame[j++] = ((y2 * 240) / 255 + 16);
        the422Frame[j++] = ((u2 * 236) / 255 + 128);
        the422Frame[j++] = ((y3 * 240) / 255 + 16);
        the422Frame[j++] = ((v2 * 236) / 255 + 128);
    }
}

For efficient display of a YUV video source, you may wish to use Apple's client storage extension, which you can set up using something like the following:

glEnable(GL_TEXTURE_RECTANGLE_EXT);
glBindTexture(GL_TEXTURE_RECTANGLE_EXT, 1);

glTextureRangeAPPLE(GL_TEXTURE_RECTANGLE_EXT, videoImageWidth * videoImageHeight * 2, videoTexture);
glTexParameteri(GL_TEXTURE_RECTANGLE_EXT, GL_TEXTURE_STORAGE_HINT_APPLE , GL_STORAGE_SHARED_APPLE);
glPixelStorei(GL_UNPACK_CLIENT_STORAGE_APPLE, GL_TRUE);

glTexParameteri(GL_TEXTURE_RECTANGLE_EXT, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_RECTANGLE_EXT, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_RECTANGLE_EXT, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_RECTANGLE_EXT, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
glPixelStorei(GL_UNPACK_ROW_LENGTH, 0);

glTexImage2D(GL_TEXTURE_RECTANGLE_EXT, 0, GL_RGBA, videoImageWidth, videoImageHeight, 0, GL_YCBCR_422_APPLE, GL_UNSIGNED_SHORT_8_8_REV_APPLE, videoTexture);    

This lets you quickly change out the data stored within your client-side video texture before each frame to be displayed on the screen.

To draw, you could then use code like the following:

glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);         
glEnable(GL_TEXTURE_2D);

glViewport(0, 0, [self frame].size.width, [self frame].size.height);

glMatrixMode(GL_PROJECTION);
glLoadIdentity();
NSRect bounds = NSRectFromCGRect([self bounds]);
glOrtho( (GLfloat)NSMinX(bounds), (GLfloat)NSMaxX(bounds), (GLfloat)NSMinY(bounds), (GLfloat)NSMaxY(bounds), -1.0, 1.0);

glBindTexture(GL_TEXTURE_RECTANGLE_EXT, 1);
glTexSubImage2D (GL_TEXTURE_RECTANGLE_EXT, 0, 0, 0, videoImageWidth, videoImageHeight, GL_YCBCR_422_APPLE, GL_UNSIGNED_SHORT_8_8_REV_APPLE, videoTexture);

glMatrixMode(GL_TEXTURE);
glLoadIdentity();

glBegin(GL_QUADS);
    glTexCoord2f(0.0f, 0.0f);
    glVertex2f(0.0f, videoImageHeight);

    glTexCoord2f(0.0f, videoImageHeight);
    glVertex2f(0.0f, 0.0f);

    glTexCoord2f(videoImageWidth, videoImageHeight);
    glVertex2f(videoImageWidth, 0.0f);

    glTexCoord2f(videoImageWidth, 0.0f);
    glVertex2f(videoImageWidth, videoImageHeight);      
glEnd();