optimized conversion from YUV_420_888 to NV21, see https://stackoverflow.com/a/52740776/192373

YUV_420_888toNV21.java

private static byte[] YUV_420_888toNV21(Image image) {
    // optimized conversion from YUV_420_888 to NV21
    // see https://stackoverflow.com/a/52740776/192373
    
    int width = image.getWidth();
    int height = image.getHeight(); 
    int ySize = width*height;
    int uvSize = width*height/4;

    byte[] nv21 = new byte[ySize + uvSize*2];

    ByteBuffer yBuffer = image.getPlanes()[0].getBuffer(); // Y
    ByteBuffer uBuffer = image.getPlanes()[1].getBuffer(); // U
    ByteBuffer vBuffer = image.getPlanes()[2].getBuffer(); // V

    int rowStride = image.getPlanes()[0].getRowStride();
    assert(image.getPlanes()[0].getPixelStride() == 1);

    int pos = 0;

    if (rowStride == width) { // likely
        yBuffer.get(nv21, 0, ySize);
        pos += ySize;
    }
    else {
        long yBufferPos = width - rowStride; // not an actual position
        for (; pos<ySize; pos+=width) {
            yBufferPos += rowStride - width;
            yBuffer.position(yBufferPos);
            yBuffer.get(nv21, pos, width);
        }
    }

    rowStride = image.getPlanes()[2].getRowStride();
    int pixelStride = image.getPlanes()[2].getPixelStride();

    assert(rowStride == image.getPlanes()[1].getRowStride());
    assert(pixelStride == image.getPlanes()[1].getPixelStride());

    if (pixelStride == 2 && rowStride == width && uBuffer.get(0) == vBuffer.get(1)) {
        // maybe V an U planes overlap as per NV21, which means vBuffer[1] is alias of uBuffer[0]
        byte savePixel = vBuffer.get(1);
        try {
            vBuffer.put(1, (byte)~savePixel);
        if (uBuffer.get(0) == (byte)~savePixel) {
            vBuffer.put(1, savePixel);
            vBuffer.get(nv21, ySize, uvSize);

            return nv21; // shortcut
        }
        catch (ReadOnlyBufferException ex) {
            // unfortunately, we cannot check if vBuffer and uBuffer overlap
        }

        // unfortunately, the check failed. We must save U and V pixel by pixel
        vBuffer.put(1, savePixel);
    }

    // other optimizations could check if (pixelStride == 1) or (pixelStride == 2), 
    // but performance gain would be less significant

    for (int row=0; row<height/2; row++) {
        for (int col=0; col<width/2; col++) {
            int vuPos = col*pixelStride + row*rowStride;
            nv21[pos++] = vBuffer.get(vuPos);
            nv21[pos++] = uBuffer.get(vuPos);
        }
    }

    return nv21;
}