Develop Reference

Custom byteArray data to WebRTC videoTrack

I need to use WebRTC for android to send specific cropped(face) video to the videoChannel. I was able manipulate Camera1Session class of WebRTC to get the face cropped. Right now I am setting it to an ImageView.
listenForBytebufferFrames() of Camera1Session.java
private void listenForBytebufferFrames() {
this.camera.setPreviewCallbackWithBuffer(new PreviewCallback() {
public void onPreviewFrame(byte[] data, Camera callbackCamera) {
Camera1Session.this.checkIsOnCameraThread();
if(callbackCamera != Camera1Session.this.camera) {
Logging.e("Camera1Session", "Callback from a different camera. This should never happen.");
} else if(Camera1Session.this.state != Camera1Session.SessionState.RUNNING) {
Logging.d("Camera1Session", "Bytebuffer frame captured but camera is no longer running.");
} else {
mFrameProcessor.setNextFrame(data, callbackCamera);
long captureTimeNs = TimeUnit.MILLISECONDS.toNanos(SystemClock.elapsedRealtime());
if(!Camera1Session.this.firstFrameReported) {
int startTimeMs = (int)TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - Camera1Session.this.constructionTimeNs);
Camera1Session.camera1StartTimeMsHistogram.addSample(startTimeMs);
Camera1Session.this.firstFrameReported = true;
}
ByteBuffer byteBuffer1 = ByteBuffer.wrap(data);
Frame outputFrame = new Frame.Builder()
.setImageData(byteBuffer1,
Camera1Session.this.captureFormat.width,
Camera1Session.this.captureFormat.height,
ImageFormat.NV21)
.setTimestampMillis(mFrameProcessor.mPendingTimeMillis)
.setId(mFrameProcessor.mPendingFrameId)
.setRotation(3)
.build();
int w = outputFrame.getMetadata().getWidth();
int h = outputFrame.getMetadata().getHeight();
SparseArray<Face> detectedFaces = mDetector.detect(outputFrame);
if (detectedFaces.size() > 0) {
Face face = detectedFaces.valueAt(0);
ByteBuffer byteBufferRaw = outputFrame.getGrayscaleImageData();
byte[] byteBuffer = byteBufferRaw.array();
YuvImage yuvimage = new YuvImage(byteBuffer, ImageFormat.NV21, w, h, null);
ByteArrayOutputStream baos = new ByteArrayOutputStream();
//My crop logic to get face co-ordinates
yuvimage.compressToJpeg(new Rect(left, top, right, bottom), 80, baos);
final byte[] jpegArray = baos.toByteArray();
Bitmap bitmap = BitmapFactory.decodeByteArray(jpegArray, 0, jpegArray.length);
Activity currentActivity = getActivity();
if (currentActivity instanceof CallActivity) {
((CallActivity) currentActivity).setBitmapToImageView(bitmap); //face on ImageView is set just fine
}
Camera1Session.this.events.onByteBufferFrameCaptured(Camera1Session.this, data, Camera1Session.this.captureFormat.width, Camera1Session.this.captureFormat.height, Camera1Session.this.getFrameOrientation(), captureTimeNs);
Camera1Session.this.camera.addCallbackBuffer(data);
} else {
Camera1Session.this.events.onByteBufferFrameCaptured(Camera1Session.this, data, Camera1Session.this.captureFormat.width, Camera1Session.this.captureFormat.height, Camera1Session.this.getFrameOrientation(), captureTimeNs);
Camera1Session.this.camera.addCallbackBuffer(data);
}
}
}
});
}
jpegArray is the final byteArray that I need to stream via WebRTC, which I tried with something like this:
Camera1Session.this.events.onByteBufferFrameCaptured(Camera1Session.this, jpegArray, (int) face.getWidth(), (int) face.getHeight(), Camera1Session.this.getFrameOrientation(), captureTimeNs);
Camera1Session.this.camera.addCallbackBuffer(jpegArray);
Setting them up like this gives me following error:
../../webrtc/sdk/android/src/jni/androidvideotracksource.cc line 82
Check failed: length >= width * height + 2 * uv_width * ((height + 1) / 2) (2630 vs. 460800)
Which I assume is because androidvideotracksource does not get the same length of byteArray that it expects, since the frame is cropped now.
Could someone point me in the direction of how to achieve it? Is this the correct way/place to manipulate the data and feed into the videoTrack?
Edit:bitmap of byteArray data does not give me a camera preview on ImageView, unlike byteArray jpegArray. Maybe because they are packed differently?

Can we use WebRTC's Datachannel to exchang custom data ie cropped face "image" in your case and do the respective calculation at receiving end using any third party library ie OpenGL etc? Reason I am suggesting is that the WebRTC Video feed received from channel is a stream in real time not a bytearray . WebRTC Video by its inherent architecture isn't meant to crop video at other hand. If we want to crop or augment video we have to use any ar library to fulfill this job.
We can always leverage WebRTC's Data channel to exchange customized data. Using Video channel for the same is not recommended because it's real time stream not the bytearray.Please revert in case of any concern.

WebRTC in particular and video streaming in general presumes that the video has fixed dimensions. If you want to crop the detected face, your options are either to have pad the cropped image with e.g. black pixels (WebRTC does not use transparency), and crop the video on the receiver side, or, if you don't have control over the receiver, resize the cropped region to fill the expected width * height frame (you should also keep the expected aspect ratio).
Note that JPEG compress/decompress that you use to crop the original is far from efficient. Some other options can be found in Image crop and resize in Android.

Okay, this was definitely a problem of how the original byte[] data was packed and the way byte[] jpegArray was packed. Changing the way of packing this and scaling it as AlexCohn suggested worked for me. I found help from other post on StackOverflow on way to pack it. This is the code for it:
private byte[] getNV21(int left, int top, int inputWidth, int inputHeight, Bitmap scaled) {
int [] argb = new int[inputWidth * inputHeight];
scaled.getPixels(argb, 0, inputWidth, left, top, inputWidth, inputHeight);
byte [] yuv = new byte[inputWidth*inputHeight*3/2];
encodeYUV420SP(yuv, argb, inputWidth, inputHeight);
scaled.recycle();
return yuv;
}
private void encodeYUV420SP(byte[] yuv420sp, int[] argb, int width, int height) {
final int frameSize = width * height;
int yIndex = 0;
int uvIndex = frameSize;
int a, R, G, B, Y, U, V;
int index = 0;
for (int j = 0; j < height; j++) {
for (int i = 0; i < width; i++) {
a = (argb[index] & 0xff000000) >> 24; // a is not used obviously
R = (argb[index] & 0xff0000) >> 16;
G = (argb[index] & 0xff00) >> 8;
B = (argb[index] & 0xff) >> 0;
// well known RGB to YUV algorithm
Y = ( ( 66 * R + 129 * G + 25 * B + 128) >> 8) + 16;
U = ( ( -38 * R - 74 * G + 112 * B + 128) >> 8) + 128;
V = ( ( 112 * R - 94 * G - 18 * B + 128) >> 8) + 128;
// NV21 has a plane of Y and interleaved planes of VU each sampled by a factor of 2
// meaning for every 4 Y pixels there are 1 V and 1 U. Note the sampling is every other
// pixel AND every other scanline.
yuv420sp[yIndex++] = (byte) ((Y < 0) ? 0 : ((Y > 255) ? 255 : Y));
if (j % 2 == 0 && index % 2 == 0) {
yuv420sp[uvIndex++] = (byte)((V<0) ? 0 : ((V > 255) ? 255 : V));
yuv420sp[uvIndex++] = (byte)((U<0) ? 0 : ((U > 255) ? 255 : U));
}
index ++;
}
}
}`
I pass this byte[] data to onByteBufferFrameCaptured and callback:
Camera1Session.this.events.onByteBufferFrameCaptured(
Camera1Session.this,
data,
w,
h,
Camera1Session.this.getFrameOrientation(),
captureTimeNs);
Camera1Session.this.camera.addCallbackBuffer(data);
Prior to this, I had to scale the bitmap which is pretty straight forward:
int width = bitmapToScale.getWidth();
int height = bitmapToScale.getHeight();
Matrix matrix = new Matrix();
matrix.postScale(newWidth / width, newHeight / height);
Bitmap scaledBitmap = Bitmap.createBitmap(bitmapToScale, 0, 0, bitmapToScale.getWidth(), bitmapToScale.getHeight(), matrix, true);

Convert android.media.Image (YUV_420_888) to Bitmap

I'm trying to implement camera preview image data processing using camera2 api as proposed here: Camera preview image data processing with Android L and Camera2 API.
I successfully receive callbacks using onImageAvailableListener, but for future processing I need to obtain bitmap from YUV_420_888 android.media.Image. I searched for similar questions, but none of them helped.
Could you please suggest me how to convert android.media.Image (YUV_420_888) to Bitmap or maybe there's a better way of listening for preview frames?

You can do this using the built-in Renderscript intrinsic, ScriptIntrinsicYuvToRGB. Code taken from Camera2 api Imageformat.yuv_420_888 results on rotated image:
#Override
public void onImageAvailable(ImageReader reader)
{
// Get the YUV data
final Image image = reader.acquireLatestImage();
final ByteBuffer yuvBytes = this.imageToByteBuffer(image);
// Convert YUV to RGB
final RenderScript rs = RenderScript.create(this.mContext);
final Bitmap bitmap = Bitmap.createBitmap(image.getWidth(), image.getHeight(), Bitmap.Config.ARGB_8888);
final Allocation allocationRgb = Allocation.createFromBitmap(rs, bitmap);
final Allocation allocationYuv = Allocation.createSized(rs, Element.U8(rs), yuvBytes.array().length);
allocationYuv.copyFrom(yuvBytes.array());
ScriptIntrinsicYuvToRGB scriptYuvToRgb = ScriptIntrinsicYuvToRGB.create(rs, Element.U8_4(rs));
scriptYuvToRgb.setInput(allocationYuv);
scriptYuvToRgb.forEach(allocationRgb);
allocationRgb.copyTo(bitmap);
// Release
bitmap.recycle();
allocationYuv.destroy();
allocationRgb.destroy();
rs.destroy();
image.close();
}
private ByteBuffer imageToByteBuffer(final Image image)
{
final Rect crop = image.getCropRect();
final int width = crop.width();
final int height = crop.height();
final Image.Plane[] planes = image.getPlanes();
final byte[] rowData = new byte[planes[0].getRowStride()];
final int bufferSize = width * height * ImageFormat.getBitsPerPixel(ImageFormat.YUV_420_888) / 8;
final ByteBuffer output = ByteBuffer.allocateDirect(bufferSize);
int channelOffset = 0;
int outputStride = 0;
for (int planeIndex = 0; planeIndex < 3; planeIndex++)
{
if (planeIndex == 0)
{
channelOffset = 0;
outputStride = 1;
}
else if (planeIndex == 1)
{
channelOffset = width * height + 1;
outputStride = 2;
}
else if (planeIndex == 2)
{
channelOffset = width * height;
outputStride = 2;
}
final ByteBuffer buffer = planes[planeIndex].getBuffer();
final int rowStride = planes[planeIndex].getRowStride();
final int pixelStride = planes[planeIndex].getPixelStride();
final int shift = (planeIndex == 0) ? 0 : 1;
final int widthShifted = width >> shift;
final int heightShifted = height >> shift;
buffer.position(rowStride * (crop.top >> shift) + pixelStride * (crop.left >> shift));
for (int row = 0; row < heightShifted; row++)
{
final int length;
if (pixelStride == 1 && outputStride == 1)
{
length = widthShifted;
buffer.get(output.array(), channelOffset, length);
channelOffset += length;
}
else
{
length = (widthShifted - 1) * pixelStride + 1;
buffer.get(rowData, 0, length);
for (int col = 0; col < widthShifted; col++)
{
output.array()[channelOffset] = rowData[col * pixelStride];
channelOffset += outputStride;
}
}
if (row < heightShifted - 1)
{
buffer.position(buffer.position() + rowStride - length);
}
}
}
return output;
}

For a simpler solution see my implementation here:
Conversion YUV 420_888 to Bitmap (full code)
The function takes the media.image as input, and creates three RenderScript allocations based on the y-, u- and v-planes. It follows the YUV_420_888 logic as shown in this Wikipedia illustration.
However, here we have three separate image planes for the Y, U and V-channels, thus I take these as three byte[], i.e. U8 allocations. The y-allocation has size width * height bytes, while the u- and v-allocatons have size width * height/4 bytes each, reflecting the fact that each u-byte covers 4 pixels (ditto each v byte).

I write some code about this, and it's the YUV datas preview and chang it to JPEG datas ,and I can use it to save as bitmap ,byte[] ,or others.(You can see the class "Allocation" ).
And SDK document says: "For efficient YUV processing with android.renderscript: Create a RenderScript Allocation with a supported YUV type, the IO_INPUT flag, and one of the sizes returned by getOutputSizes(Allocation.class), Then obtain the Surface with getSurface()."
here is the code, hope it will help you:https://github.com/pinguo-yuyidong/Camera2/blob/master/camera2/src/main/rs/yuv2rgb.rs

QCom Decoder Output YUV Buffer Distrubed

I'm trying to get images from HD Live Stream. Getting OMX Decoder YUV Streams and converting them into JPG. JPEG is completely disturbed. Tried some suggestions from group but not working.
My resolution is 320x240.
i will get buffer length is (386 * 256 * 1.5) for configured 320 * 240 resolution. I'm not getting how to get this new width and height information.
JPG conversion code i have in Java and using OMXCodec is in Native. Please help me.
final int frameSize = width * height;
final int qFrameSize = frameSize/4;
int padding = 0;/*(width*height + 2047) & ~2047;
if ((width % 32) != 0) {
padding = (width*height) % 1024;
} else {
padding = (width*height) % 2048;
}
System.arraycopy(input, 0, output, 0, frameSize); // Y
for (int i = 0; i < qFrameSize; i++) {
output[frameSize + i*2 + padding] = input[frameSize + i + qFrameSize ]; // Cb (U)
output[frameSize + i*2 + 1 + padding] = input[frameSize + i ]; // Cr (V)
}
return ;
}
thank you,
Raghu

The output of QCom video decoder is usually a specific custom color format which is typically known as tiled format. Please refer to these questions which have more inputs on how to convert the data to a more cleaner frame
QOMX_COLOR_FormatYUV420PackedSemiPlanar64x32Tile2m8ka converter
QOMX_COLOR_FormatYUV420PackedSemiPlanar64x32Tile2m8ka color format

32 bpp monochrome bitmap to 1 bpp TIFF

My android app uses an external lib that makes some image treatments. The final output of the treatment chain is a monochrome bitmap but saved has a color bitmap (32bpp).
The image has to be uploaded to a cloud blob, so for bandwidth concerns, i'd like to convert it to 1bpp G4 compression TIFF. I successfully integrated libTIFF in my app via JNI and now i'm writing the conversion routine in C. I'm a little stuck here.
I managed to produce a 32 BPP TIFF, but impossible to reduce to 1bpp, the output image is always unreadable. Did someone succeded to do similar task ?
More speciffically :
What should be the value of SAMPLE_PER_PIXEL and BITS_PER_SAMPLE
parameters ?
How to determine the strip size ?
How to fill each strip ? (i.e. : How to convert 32bpp pixel lines to 1 bpp pixels strips ?)
Many thanks !
UPDATE : The code produced with the precious help of Mohit Jain
int ConvertMonochrome32BppBitmapTo1BppTiff(char* bitmap, int height, int width, int resx, int resy, char const *tifffilename)
{
TIFF *tiff;
if ((tiff = TIFFOpen(tifffilename, "w")) == NULL)
{
return TC_ERROR_OPEN_FAILED;
}
// TIFF Settings
TIFFSetField(tiff, TIFFTAG_RESOLUTIONUNIT, RESUNIT_INCH);
TIFFSetField(tiff, TIFFTAG_XRESOLUTION, resx);
TIFFSetField(tiff, TIFFTAG_YRESOLUTION, resy);
TIFFSetField(tiff, TIFFTAG_COMPRESSION, COMPRESSION_CCITTFAX4); //Group4 compression
TIFFSetField(tiff, TIFFTAG_IMAGEWIDTH, width);
TIFFSetField(tiff, TIFFTAG_IMAGELENGTH, height);
TIFFSetField(tiff, TIFFTAG_ROWSPERSTRIP, 1);
TIFFSetField(tiff, TIFFTAG_SAMPLESPERPIXEL, 1);
TIFFSetField(tiff, TIFFTAG_BITSPERSAMPLE, 1);
TIFFSetField(tiff, TIFFTAG_ORIENTATION, ORIENTATION_TOPLEFT);
TIFFSetField(tiff, TIFFTAG_PLANARCONFIG, PLANARCONFIG_CONTIG);
TIFFSetField(tiff, TIFFTAG_PHOTOMETRIC, PHOTOMETRIC_MINISWHITE);
tsize_t tbufsize = (width + 7) / 8; //Tiff ScanLine buffer size for 1bpp pixel row
//Now writing image to the file one row by one
int x, y;
for (y = 0; y < height; y++)
{
char *buffer = malloc(tbufsize);
memset(buffer, 0, tbufsize);
for (x = 0; x < width; x++)
{
//offset of the 1st byte of each pixel in the input image (is enough to determine is black or white in 32 bpp monochrome bitmap)
uint32 bmpoffset = ((y * width) + x) * 4;
if (bitmap[bmpoffset] == 0) //Black pixel ?
{
uint32 tiffoffset = x / 8;
*(buffer + tiffoffset) |= (0b10000000 >> (x % 8));
}
}
if (TIFFWriteScanline(tiff, buffer, y, 0) != 1)
{
return TC_ERROR_WRITING_FAILED;
}
if (buffer)
{
free(buffer);
buffer = NULL;
}
}
TIFFClose(tiff);
tiff = NULL;
return TC_SUCCESSFULL;
}

To convert 32 bpp to 1 bpp, extract RGB and convert it into Y (luminance) and use some threshold to convert to 1 bpp.
Number of samples and bits per pixel should be 1.

FFmpeg encoding in c

I have been working on a project about video summarization on android platfrom. and I am stuck in encoding. I think;
first I must convert my frame into RGB Frame, then convert that RGB FRame into YUV Frame. Then encode the frame. After this operations, The output video was so weird. I think I missed something. Here is my las optimized code. Maybe someone has an experiement in this subject.
Its syntax is changed according to android ndk syntax:
jint Java_com_test_Test_encodeVideo(JNIEnv* env, jobject javaThis)
{
char *flname, *err, *info;
AVCodec *codec;
AVCodecContext *c= NULL;
int i,out_size, size, x, y,z, outbuf_size;
int frameCount=99;
FILE *f;
AVFrame *picture, *yuvFrame;
uint8_t *outbuf, *picture_buf;
PPMImage *img;
const char *destfilename = "/sdcard/new.mp4";
int numBytes;
uint8_t *buffer;
av_register_all();
// must be called before using avcodec lib
avcodec_init();
// register all the codecs
avcodec_register_all();
log_message("Video encoding\n");
// find the H263 video encoder
codec = avcodec_find_encoder(CODEC_ID_H263);
if (!codec) {
sprintf(err, "codec not found\n");
log_message(err);
}
c= avcodec_alloc_context();
picture= avcodec_alloc_frame();
yuvFrame= avcodec_alloc_frame();
// get first ppm context. it is because I need width and height values.
img = getPPM("/sdcard/frame1.ppm");
c->bit_rate = 400000;
// resolution must be a multiple of two
c->width = img->x;
c->height = img->y;
free(img);
// frames per second
c->time_base= (AVRational){1,25};
c->gop_size = 10; // emit one intra frame every ten frames
//c->max_b_frames=1;
c->pix_fmt = PIX_FMT_YUV420P;
// open it
if (avcodec_open(c, codec) < 0){
log_message("codec couldn't open");
return -1;
}
//destfilename = (*env)->GetStringUTFChars(env, dst, 0);
f = fopen(destfilename, "wb");
log_message(destfilename);
if (!f) {
sprintf(err, "could not open %s", destfilename);
log_message(err);
}
log_message("after destination file opening");
// alloc image and output buffer
outbuf_size = 100000;
outbuf = malloc(outbuf_size);
size = c->width * c->height;
picture_buf = malloc(size * 3); // size for RGB
picture->data[0] = picture_buf;
picture->data[1] = picture->data[0] + size;
picture->data[2] = picture->data[1] + size / 4;
picture->linesize[0] = c->width;
picture->linesize[1] = c->width / 2;
picture->linesize[2] = c->width / 2;
numBytes=avpicture_get_size(PIX_FMT_YUV420P, c->width,
c->height);
buffer=malloc(numBytes);
// Assign appropriate parts of buffer to image planes in FrameYUV
avpicture_fill((AVPicture *)yuvFrame, buffer, PIX_FMT_YUV420P,
c->width, c->height);
// encode the video
log_message("before for loop");
for(z=1;z<frameCount;z++) {
sprintf(flname,"/sdcard/frame%d.ppm",z);
// read the ppm file
img = getPPM(flname);
picture->data[0] = img->data;
// convert the rgb frame into yuv frame
rgb2yuv(picture,yuvFrame,c);
log_message("translation completed.");
// encode the image
out_size = avcodec_encode_video(c, outbuf, outbuf_size, yuvFrame);
sprintf(info,"encoding frame %3d (size=%5d)\n", z, out_size);
log_message(info);
fwrite(outbuf, 1, out_size, f);
free(img);
}
// get the delayed frames
for(; out_size; i++) {
//fflush(stdout);
out_size = avcodec_encode_video(c, outbuf, outbuf_size, NULL);
sprintf(info,"write frame %3d (size=%5d)\n", i, out_size);
log_message(info);
fwrite(outbuf, 1, out_size, f);
}
// add sequence end code to have a real mpeg file
outbuf[0] = 0x00;
outbuf[1] = 0x00;
outbuf[2] = 0x01;
outbuf[3] = 0xb7;
fwrite(outbuf, 1, 4, f);
fclose(f);
free(picture_buf);
free(outbuf);
avcodec_close(c);
av_free(c);
av_free(picture);
av_free(yuvFrame);
}
int rgb2yuv(AVFrame *frameRGB, AVFrame *frameYUV, AVCodecContext *c)
{
char *err;
static struct SwsContext *img_convert_ctx;
log_message("conversion starts");
// Convert the image into YUV format from RGB format
if(img_convert_ctx == NULL) {
int w = c->width;
int h = c->height;
img_convert_ctx = sws_getContext(w, h, PIX_FMT_RGB24,w, h, c->pix_fmt, SWS_BICUBIC,NULL, NULL, NULL);
if(img_convert_ctx == NULL) {
sprintf(err, "Cannot initialize the conversion context!\n");
log_message(err);
return -1;
}
}
int ret = sws_scale(img_convert_ctx,frameRGB->data, frameRGB->linesize , 0,c->height,frameYUV->data, frameYUV->linesize );
return;
}