vp9 encoder returns a null packet - c++

i using this code to encode video stream using vp8 and i decided to give vp9 a try so i changed every thing with starts with vp_* from 8 to 9.
but the vp9 encoder always return a null packet although the encoder doesn't return any error.
here is the code i'am using for configuring.
vpx_codec_err_t error = vpx_codec_enc_config_default(vpx_codec_vp9_cx(), &enc_cfg, 0);
if(error != VPX_CODEC_OK)
return error;
enc_cfg.g_timebase.den = fps;
enc_cfg.rc_undershoot_pct = 95;
enc_cfg.rc_target_bitrate = bitrate;
enc_cfg.g_error_resilient = 1;
enc_cfg.kf_max_dist = 999999;
enc_cfg.rc_buf_initial_sz = 4000;
enc_cfg.rc_buf_sz = 6000;
enc_cfg.rc_buf_optimal_sz = 5000;
enc_cfg.rc_end_usage = VPX_CBR;
enc_cfg.g_h = height;
enc_cfg.g_w = width;
enc_cfg.rc_min_quantizer = 4;
enc_cfg.rc_max_quantizer = 56;
enc_cfg.g_threads = 4;
enc_cfg.g_pass = VPX_RC_ONE_PASS;
error = vpx_codec_enc_init(&codec, vpx_codec_vp9_cx(), &enc_cfg, 0);
if(error != VPX_CODEC_OK)
return error;
vpx_img_alloc(&vpx_image,VPX_IMG_FMT_I420 , width, height, 1);
configured = true;
return VPX_CODEC_OK;
and the code for the encoding
libyuv::RAWToI420(frame, vpx_image.d_w * 3, vpx_image.planes[VPX_PLANE_Y],vpx_image.stride[VPX_PLANE_Y],
vpx_image.planes[VPX_PLANE_U], vpx_image.stride[VPX_PLANE_U], vpx_image.planes[VPX_PLANE_V],
vpx_image.stride[VPX_PLANE_V], vpx_image.d_w, vpx_image.d_h);
const vpx_codec_cx_pkt_t *pkt;
vpx_codec_err_t error = vpx_codec_encode(&codec, &vpx_image, 0, 1, 0, VPX_DL_GOOD_QUALITY);
if(error != VPX_CODEC_OK)
return vector<byte>();
vpx_codec_iter_t iter = NULL;
if((pkt = vpx_codec_get_cx_data(&codec, &iter)))//always return null ?
{
if(pkt->kind == VPX_CODEC_CX_FRAME_PKT)
{
int length = pkt->data.frame.sz;
byte* buf = (byte*) pkt->data.frame.buf;
vector<byte> data(buf, buf + length);
return data;
}
return vector<byte>();
}
return vector<byte>();
the code is fully working if i'am using vp8 instead of 9, any help is welcomed

Just came across this post because I faced the same problem. Just for other to know: I solved it with setting
enc_cfg.g_lag_in_frames = 0;
This basically disallows the encoder to consume up to default 25 frames until it produces any output.

Related

How to send data simultaneously to 2 HID device which have the same VendorID and ProductID with HID API?

1. About the problem
I'm trying to send data store in a array called UxbTx[64] to 2 Hid devices that have the same VendorID(VID) and ProductID(PID) but differ in SerialNum (this differnce help me to enumerate 2 devices) and connect to PC via Usb Hub . I have successfully recognized two device and use hid_write() to send data but just 1 device acting right with my data config. For example, i want to turn on 2 devices but device 1 ON whereas the device 2 still remain OFF.
2. What I have tried
At first I thought that I have failed to send to the second device but it not. I use res=hid_write() and it return 0 which means successfully send for both devices.
This is the code that i use:
static hid_device** id_device;
static int max_size;
int res;
struct device_info
{
wchar_t* serial_num;
int id;
};
std::vector<device_info> devEnum(unsigned short vendor_id, unsigned short product_id)
{
std::vector<device_info> device;
int count = 0, total = 0, res = 0,i=0;
hid_device_info* dev = NULL, * cur_dev = NULL;
hid_device* temp_handle = NULL;
std::vector<wchar_t*> string;
wchar_t wstr[MAX_STR], temp[MAX_STR];
device_info inf;
hid_enumerate(vendor_id, product_id);
res = hid_init();
dev = hid_enumerate(0x461, 0x20);
for (cur_dev = dev; cur_dev != NULL; cur_dev = cur_dev->next)
{
memcpy(temp, cur_dev->serial_number, MAX_STR);
wcsncpy(temp, cur_dev->serial_number, MAX_STR);
temp[MAX_STR - 1] = L'\0';
string.push_back(temp);
inf.serial_num = cur_dev->serial_number;
inf.id = count;
device.push_back(inf);
count++;
}
max_size = device.size();
return device;
}
int NhgIsOpen(wchar_t* Manufacturer, wchar_t* Product, wchar_t* SerialNumber, std::vector<device_info> devices) {
int length = devices.size();
int res = 0;
id_device = new hid_device * [length];
wchar_t KeyManufacturer[MAX_STR] = L"test";
wchar_t KeyProduct[MAX_STR] = L"device test";
for (int i = 0; i < length; i++)
{
id_device[i] = hid_open(0x123, 0x15, devices[i].serial_num);
if (!id_device[i])
return -2;
hid_set_nonblocking(id_device[i], 0);
res = hid_get_manufacturer_string(id_device[i], Manufacturer, MAX_STR);
if (wcscmp(Manufacturer, KeyManufacturer) != 0)
return -3; //Manufacturer not match
res = hid_get_product_string(id_device[i], Product, MAX_STR);
if (wcscmp(Product, KeyProduct) != 0)
return -4; // KeyProdeuct not match
}
return 0;
}
INT32 IoControl(UINT16 IoState, int axis_id) {
UINT8 UsbTx[64];
//clear TX buffer
std::fill_n(UsbTx, 64, 0);
//report byte
UsbTx[0] = 0x01;
//USB user define cmd
UsbTx[1] = 0x00;
UsbTx[2] = 0x15; // turn on device
UsbTx[11] = 0x00;
UsbTx[12] = (0xFF) & IoState;
res = hid_write(id_device[axis_id], UsbTx, 64);
if (res < 0)
return -5; //can't write
return 0;
}
3. Question
If i can enumerate 2 devices does it means i can talk to 2 devices simultaneously?
Does the Report ID in firmware is the problem? I mean does i have to re-config Report ID in the Descriptor of the device so they can read the data at the same time?

iOS AVCaptureSession stream micro audio Objective-C++

I am currently messing the first time with iOS and Objective-C++. Im coming from C/C++ so please excuse my bad coding in the below examples.
I am trying to live stream the microphone audio of my iOS device over tcp, the iOS device is acting as server and sends the data to all clients that connect.
To do so, I am first using AVCaptureDevice and requestAccessForMediaType:AVMediaTypeAudio to request access to the microphone (along with the needed entry in the Info.plist).
Then I create a AVCaptureSession* using the below function:
AVCaptureSession* createBasicARecordingSession(aReceiver* ObjectReceivingAudioFrames){
AVCaptureSession* s = [[AVCaptureSession alloc] init];
AVCaptureDevice* aDevice = [AVCaptureDevice defaultDeviceWithMediaType:AVMediaTypeAudio];
AVCaptureDeviceInput* aInput = NULL;
if([aDevice lockForConfiguration:NULL] == YES && aDevice){
aInput = [AVCaptureDeviceInput deviceInputWithDevice:aDevice error:nil];
[aDevice unlockForConfiguration];
}
else if(!aDevice){
fprintf(stderr, "[d] could not create device. (%p)\n", aDevice);
return NULL;
}
else{
fprintf(stderr, "[d] could not lock device.\n");
return NULL;
}
if(!aInput){
fprintf(stderr, "[d] could not create input.\n");
return NULL;
}
AVCaptureAudioDataOutput* aOutput = [[AVCaptureAudioDataOutput alloc] init];
dispatch_queue_t aQueue = dispatch_queue_create("aQueue", NULL);
if(!aOutput){
fprintf(stderr, "[d] could not create output.\n");
return NULL;
}
[aOutput setSampleBufferDelegate:ObjectReceivingAudioFrames queue:aQueue];
// the below line does only work on macOS
//aOutput.audioSettings = settings;
[s beginConfiguration];
if([s canAddInput:aInput]){
[s addInput:aInput];
}
else{
fprintf(stderr, "[d] could not add input.\n");
return NULL;
}
if([s canAddOutput:aOutput]){
[s addOutput:aOutput];
}
else{
fprintf(stderr, "[d] could not add output.\n");
return NULL;
}
[s commitConfiguration];
return s;
}
The aReceiver* class (?) is defined below and receives the audio frames provided by the AVCaptureAudioDataOutput* object. The frames are stored inside a std::vector.
(im adding the code as image as I could not get it formatted right...)
Then I start the AVCaptureSession* using [audioSession start]
When a tcp client connects I first create a AudioConverterRef and two AudioStreamBasicDescription to convert the audio frames to AAC, see below:
AudioStreamBasicDescription asbdIn, asbdOut;
AudioConverterRef converter;
asbdIn.mFormatID = kAudioFormatLinearPCM;
//asbdIn.mFormatFlags = kLinearPCMFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked;
asbdIn.mFormatFlags = 12;
asbdIn.mSampleRate = 44100;
asbdIn.mChannelsPerFrame = 1;
asbdIn.mFramesPerPacket = 1;
asbdIn.mBitsPerChannel = 16;
//asbdIn.mBytesPerFrame = (asbdIn.mBitsPerChannel / 8) * asbdIn.mBitsPerChannel;
asbdIn.mBytesPerFrame = 2;
asbdIn.mBytesPerPacket = asbdIn.mBytesPerFrame;
asbdIn.mReserved = 0;
asbdOut.mFormatID = kAudioFormatMPEG4AAC;
asbdOut.mFormatFlags = 0;
asbdOut.mSampleRate = 44100;
asbdOut.mChannelsPerFrame = 1;
asbdOut.mFramesPerPacket = 1024;
asbdOut.mBitsPerChannel = 0;
//asbdOut.mBytesPerFrame = (asbdOut.mBitsPerChannel / 8) * asbdOut.mBitsPerChannel;
asbdOut.mBytesPerFrame = 0;
asbdOut.mBytesPerPacket = asbdOut.mBytesPerFrame;
asbdOut.mReserved = 0;
OSStatus err = AudioConverterNew(&asbdIn, &asbdOut, &converter);
Then I create a AudioBufferList* to store the encoded frames:
while(audioInput.locked){ // audioInput is my aReceiver*
usleep(0.2 * 1000000);
}
audioInput.locked = true;
UInt32 RequestedPackets = 8192;
//AudioBufferList* aBufferList = (AudioBufferList*)malloc(sizeof(AudioBufferList));
AudioBufferList* aBufferList = static_cast<AudioBufferList*>(calloc(1, offsetof(AudioBufferList, mBuffers) + (sizeof(AudioBuffer) * 1)));
aBufferList->mNumberBuffers = 1;
aBufferList->mBuffers[0].mNumberChannels = asbdIn.mChannelsPerFrame;
aBufferList->mBuffers[0].mData = static_cast<void*>(calloc(RequestedPackets, asbdIn.mBytesPerFrame));
aBufferList->mBuffers[0].mDataByteSize = asbdIn.mBytesPerFrame * RequestedPackets;
Then I go through the frames stored in the std::vector mentioned earlier and pass them to AudioConverterFillComplexBuffer(). After conversion, i concat all encoded frames into one NSMutableData which I then write() to the socket connected to the client.
long aBufferListSize = audioInput.aBufferList.size();
while(aBufferListSize > 0){
err = AudioConverterFillComplexBuffer(converter, feedAFrames, static_cast<void*>(&audioInput.aBufferList[audioInput.aBufferList.size() - aBufferListSize]), &RequestedPackets, aBufferList, NULL);
NSMutableData* encodedData = [[NSMutableData alloc] init];
long encodedDataLen = 0;
for(int i = 0; i < aBufferList->mNumberBuffers; i++){
Float32* frame = (Float32*)aBufferList->mBuffers[i].mData;
[encodedData appendBytes:frame length:aBufferList->mBuffers[i].mDataByteSize];
encodedDataLen += aBufferList->mBuffers[i].mDataByteSize;
}
unsigned char* encodedDataBytes = (unsigned char*)[encodedData bytes];
fprintf(stderr, "[d] got %li encoded bytes to send...\n", encodedDataLen);
long bytes = write(Client->GetFD(), encodedDataBytes, encodedDataLen);
fprintf(stderr, "[d] written %li of %li bytes.\n", bytes, encodedDataLen);
usleep(0.2 * 1000000);
aBufferListSize--;
}
audioInput.aBufferList.clear();
audioInput.locked = false;
Below is the feedAFrames() callback used in the AudioConverterFillComplexBuffer() call:
(again this is an image of the code, same reason as above)
Step 5 to 7 are repeated until the tcp connection is closed.
Each step runs without any noticeable error (I know I could include way better error handling here), and I do get data out of step 3 and 7. However it does not seem to be AAC what comes out at the end.
As im rather new to all of this, im really not sure what my error is, im sure there are several things I made wrong. It is kind of hard to find suitable example code of what I am trying to do, and the above is the best I could come up with until now with all that I have found paired with the apple dev documentation.
I hope someone might take some time to explain me what I did wrong and how I can get this to work. Thanks for reading until here!

How is possible get only the device to capture or playback using pjsua2

I trying get the devices from pjsua2 , I got it get all devices, but do not got split in capture device and playback device.
void AudioController::load(){
Endpoint ep;
ep.libCreate();
// Initialize endpoint
EpConfig ep_cfg;
ep.libInit( ep_cfg );
AudDevManager &manager = ep.audDevManager();
manager.refreshDevs();
this->input.clear();
const AudioDevInfoVector &list = manager.enumDev();
for(unsigned int i = 0;list.size() != i;i++){
AudioDevInfo * info = list[i];
GtAudioDevice * a = new GtAudioDevice();
a->name = info->name.c_str();
a->deviceId = i;
qDebug() << info->name.c_str();
qDebug() << info->driver.c_str();
qDebug() << info->caps;
this->input.append(a);
}
ep.libDestroy();
}
This is my output:
Wave mapper
WMME
23
Microfone (Dispositivo de High
WMME
3
Alto-falantes (Dispositivo de H
WMME
21
You can check the fields inputCount and outputCount inside AudioDevInfo.
According the documentation:
unsigned inputCount
Maximum number of input channels supported by this device. If the
value is zero, the device does not support input operation (i.e. it is
a playback only device).
And
unsigned outputCount
Maximum number of output channels supported by this device. If the
value is zero, the device does not support output operation (i.e. it
is an input only device).
So you could do something like this:
for(unsigned int i = 0;list.size() != i;i++){
AudioDevInfo * info = list[i];
GtAudioDevice * a = new GtAudioDevice();
a->name = info->name.c_str();
a->deviceId = i;
if (info->inputCount > 0) {
a->captureDevice = true;
}
if (info->outputCount > 0) {
a->playbackDevice = true;
}
this->input.append(a);
}
Reference: http://www.pjsip.org/pjsip/docs/html/structpj_1_1AudioDevInfo.htm
Another way, you can check the field caps (capabilities). Something like this:
for (int i = 0; i < list.size(); i++)
{
AudioDevInfo * info = list[i];
if ((info.caps & (int)pjmedia_aud_dev_cap.PJMEDIA_AUD_DEV_CAP_OUTPUT_LATENCY) != 0)
{
// Playback devices come here
}
if ((info.caps & (int)pjmedia_aud_dev_cap.PJMEDIA_AUD_DEV_CAP_INPUT_LATENCY) != 0)
{
// Capture devices come here
}
}
caps is combined from these possible values:
enum pjmedia_aud_dev_cap {
PJMEDIA_AUD_DEV_CAP_EXT_FORMAT = 1,
PJMEDIA_AUD_DEV_CAP_INPUT_LATENCY = 2,
PJMEDIA_AUD_DEV_CAP_OUTPUT_LATENCY = 4,
PJMEDIA_AUD_DEV_CAP_INPUT_VOLUME_SETTING = 8,
PJMEDIA_AUD_DEV_CAP_OUTPUT_VOLUME_SETTING = 16,
PJMEDIA_AUD_DEV_CAP_INPUT_SIGNAL_METER = 32,
PJMEDIA_AUD_DEV_CAP_OUTPUT_SIGNAL_METER = 64,
PJMEDIA_AUD_DEV_CAP_INPUT_ROUTE = 128,
PJMEDIA_AUD_DEV_CAP_INPUT_SOURCE = 128,
PJMEDIA_AUD_DEV_CAP_OUTPUT_ROUTE = 256,
PJMEDIA_AUD_DEV_CAP_EC = 512,
PJMEDIA_AUD_DEV_CAP_EC_TAIL = 1024,
PJMEDIA_AUD_DEV_CAP_VAD = 2048,
PJMEDIA_AUD_DEV_CAP_CNG = 4096,
PJMEDIA_AUD_DEV_CAP_PLC = 8192,
PJMEDIA_AUD_DEV_CAP_MAX = 16384
}

C++ - EncryptMessage not encrypting the correct data

I've been following this tutorial for SSL/TLS online (well its more of reading the guys source code and following along) but I've hit a bumpy road with this EncryptMessage part because it pushes the data out of the way and encrypts the wrong info.
The pbloBuffer that I send it is:
GET / HTTP/1.1\r\n
HOST: www.google.com\r\n\r\n
But when I do pbMessage = pbloBuffer + Sizes.cbHeader; I end up with (even the microsoft websites says to do this)
1\r\n
HOST: www.google.com\r\n\r\n
Now pbMessage is the code above, and that's inserted under SECBUFFER_DATA so it's not even getting the full data. From what I understand SECBUFFER_DATA is the "user" data that the Webserver will decode and process.
Can you find out how to fix this and properly send the encrypted data?
Full source: (This code is experimental as I am trying to understand it before I makes changes)
int Adaptify::EncryptSend(PBYTE pbloBuffer, int Size) {
SECURITY_STATUS scRet{ 0 };
SecBufferDesc Message{ 0 };
SecBuffer Buffers[4]{ 0 };
DWORD cbMessage = 0, cbData = 0;
PBYTE pbMessage = nullptr;
SecPkgContext_StreamSizes Sizes = { 0 };
QueryContextAttributesW(&hContext, SECPKG_ATTR_STREAM_SIZES, &Sizes);
pbMessage = pbloBuffer + Sizes.cbHeader;
cbMessage = (DWORD)strlen((const char*)pbMessage);
Buffers[0].BufferType = SECBUFFER_STREAM_HEADER;
Buffers[0].cbBuffer = Sizes.cbHeader;
Buffers[0].pvBuffer = pbloBuffer;
Buffers[1].BufferType = SECBUFFER_DATA;
Buffers[1].pvBuffer = pbMessage;
Buffers[1].cbBuffer = cbMessage;
Buffers[2].BufferType = SECBUFFER_STREAM_TRAILER;
Buffers[2].cbBuffer = Sizes.cbTrailer;
Buffers[2].pvBuffer = pbMessage + cbMessage;
Buffers[3].BufferType = SECBUFFER_EMPTY;
Buffers[3].cbBuffer = SECBUFFER_EMPTY;
Buffers[3].pvBuffer = SECBUFFER_EMPTY;
Message.cBuffers = 4;
Message.pBuffers = Buffers;
Message.ulVersion = SECBUFFER_VERSION;
scRet = EncryptMessage(&hContext, 0, &Message, 0);
if (send(hSocket, (const char*)pbloBuffer, Buffers[0].cbBuffer + Buffers[1].cbBuffer + Buffers[2].cbBuffer, 0) < 0) {
MessageBox(0, L"Send error", 0, 0);
}
return 0;
}
first - you need call QueryContextAttributesW only once after InitializeSecurityContextW return SEC_E_OK - no sense call it every time, when you need send data. and save result. say inherit your class from SecPkgContext_StreamSizes - class Adaptify : SecPkgContext_StreamSizes; and call on end handshake (once) QueryContextAttributesW(&hContext, SECPKG_ATTR_STREAM_SIZES, this);
about send send data - in your case Buffers[1].pvBuffer of course must point to your actual data pbloBuffer but not to pbloBuffer + Sizes.cbHeader code can be like this:
int Adaptify::EncryptSend(PBYTE pbloBuffer, int Size) {
SECURITY_STATUS ss = SEC_E_INSUFFICIENT_MEMORY;
if (PBYTE Buffer = new BYTE[cbHeader + Size + cbTrailer]) {
memcpy(Buffer + cbHeader, pbloBuffer, Size);
SecBuffer sb[4] = {
{ cbHeader, SECBUFFER_STREAM_HEADER, Buffer},
{ Size, SECBUFFER_DATA, Buffer + cbHeader},
{ cbTrailer, SECBUFFER_STREAM_TRAILER, Buffer + cbHeader + Size},
};
SecBufferDesc sbd = {
SECBUFFER_VERSION, 4, sb
};
if (SEC_E_OK == (ss = ::EncryptMessage(this, 0, &sbd, 0)))) {
if (SOCKET_ERROR == send(hSocket, (const char*)Buffer, sb[0].cbBuffer+sb[1].cbBuffer+sb[2].cbBuffer+sb[3].cbBuffer, 0))
ss = WSAGetLastError();
}
delete [] Buffer;
}
return ss;
}
so you need allocate new buffer with cbHeader + Size + cbTrailer size (wher Size is your actual message Size and copy your message at Buffer + cbHeader

How to write a Live555 FramedSource to allow me to stream H.264 live

I've been trying to write a class that derives from FramedSource in Live555 that will allow me to stream live data from my D3D9 application to an MP4 or similar.
What I do each frame is grab the backbuffer into system memory as a texture, then convert it from RGB -> YUV420P, then encode it using x264, then ideally pass the NAL packets on to Live555. I made a class called H264FramedSource that derived from FramedSource basically by copying the DeviceSource file. Instead of the input being an input file, I've made it a NAL packet which I update each frame.
I'm quite new to codecs and streaming, so I could be doing everything completely wrong. In each doGetNextFrame() should I be grabbing the NAL packet and doing something like
memcpy(fTo, nal->p_payload, nal->i_payload)
I assume that the payload is my frame data in bytes? If anybody has an example of a class they derived from FramedSource that might at least be close to what I'm trying to do I would love to see it, this is all new to me and a little tricky to figure out what's happening. Live555's documentation is pretty much the code itself which doesn't exactly make it easy for me to figure out.
Ok, I finally got some time to spend on this and got it working! I'm sure there are others who will be begging to know how to do it so here it is.
You will need your own FramedSource to take each frame, encode, and prepare it for streaming, I will provide some of the source code for this soon.
Essentially throw your FramedSource into the H264VideoStreamDiscreteFramer, then throw this into the H264RTPSink. Something like this
scheduler = BasicTaskScheduler::createNew();
env = BasicUsageEnvironment::createNew(*scheduler);
framedSource = H264FramedSource::createNew(*env, 0,0);
h264VideoStreamDiscreteFramer
= H264VideoStreamDiscreteFramer::createNew(*env, framedSource);
// initialise the RTP Sink stuff here, look at
// testH264VideoStreamer.cpp to find out how
videoSink->startPlaying(*h264VideoStreamDiscreteFramer, NULL, videoSink);
env->taskScheduler().doEventLoop();
Now in your main render loop, throw over your backbuffer which you've saved to system memory to your FramedSource so it can be encoded etc. For more info on how to setup the encoding stuff check out this answer How does one encode a series of images into H264 using the x264 C API?
My implementation is very much in a hacky state and is yet to be optimised at all, my d3d application runs at around 15fps due to the encoding, ouch, so I will have to look into this. But for all intents and purposes this StackOverflow question is answered because I was mostly after how to stream it. I hope this helps other people.
As for my FramedSource it looks a little something like this
concurrent_queue<x264_nal_t> m_queue;
SwsContext* convertCtx;
x264_param_t param;
x264_t* encoder;
x264_picture_t pic_in, pic_out;
EventTriggerId H264FramedSource::eventTriggerId = 0;
unsigned H264FramedSource::FrameSize = 0;
unsigned H264FramedSource::referenceCount = 0;
int W = 720;
int H = 960;
H264FramedSource* H264FramedSource::createNew(UsageEnvironment& env,
unsigned preferredFrameSize,
unsigned playTimePerFrame)
{
return new H264FramedSource(env, preferredFrameSize, playTimePerFrame);
}
H264FramedSource::H264FramedSource(UsageEnvironment& env,
unsigned preferredFrameSize,
unsigned playTimePerFrame)
: FramedSource(env),
fPreferredFrameSize(fMaxSize),
fPlayTimePerFrame(playTimePerFrame),
fLastPlayTime(0),
fCurIndex(0)
{
if (referenceCount == 0)
{
}
++referenceCount;
x264_param_default_preset(&param, "veryfast", "zerolatency");
param.i_threads = 1;
param.i_width = 720;
param.i_height = 960;
param.i_fps_num = 60;
param.i_fps_den = 1;
// Intra refres:
param.i_keyint_max = 60;
param.b_intra_refresh = 1;
//Rate control:
param.rc.i_rc_method = X264_RC_CRF;
param.rc.f_rf_constant = 25;
param.rc.f_rf_constant_max = 35;
param.i_sps_id = 7;
//For streaming:
param.b_repeat_headers = 1;
param.b_annexb = 1;
x264_param_apply_profile(&param, "baseline");
encoder = x264_encoder_open(&param);
pic_in.i_type = X264_TYPE_AUTO;
pic_in.i_qpplus1 = 0;
pic_in.img.i_csp = X264_CSP_I420;
pic_in.img.i_plane = 3;
x264_picture_alloc(&pic_in, X264_CSP_I420, 720, 920);
convertCtx = sws_getContext(720, 960, PIX_FMT_RGB24, 720, 760, PIX_FMT_YUV420P, SWS_FAST_BILINEAR, NULL, NULL, NULL);
if (eventTriggerId == 0)
{
eventTriggerId = envir().taskScheduler().createEventTrigger(deliverFrame0);
}
}
H264FramedSource::~H264FramedSource()
{
--referenceCount;
if (referenceCount == 0)
{
// Reclaim our 'event trigger'
envir().taskScheduler().deleteEventTrigger(eventTriggerId);
eventTriggerId = 0;
}
}
void H264FramedSource::AddToBuffer(uint8_t* buf, int surfaceSizeInBytes)
{
uint8_t* surfaceData = (new uint8_t[surfaceSizeInBytes]);
memcpy(surfaceData, buf, surfaceSizeInBytes);
int srcstride = W*3;
sws_scale(convertCtx, &surfaceData, &srcstride,0, H, pic_in.img.plane, pic_in.img.i_stride);
x264_nal_t* nals = NULL;
int i_nals = 0;
int frame_size = -1;
frame_size = x264_encoder_encode(encoder, &nals, &i_nals, &pic_in, &pic_out);
static bool finished = false;
if (frame_size >= 0)
{
static bool alreadydone = false;
if(!alreadydone)
{
x264_encoder_headers(encoder, &nals, &i_nals);
alreadydone = true;
}
for(int i = 0; i < i_nals; ++i)
{
m_queue.push(nals[i]);
}
}
delete [] surfaceData;
surfaceData = NULL;
envir().taskScheduler().triggerEvent(eventTriggerId, this);
}
void H264FramedSource::doGetNextFrame()
{
deliverFrame();
}
void H264FramedSource::deliverFrame0(void* clientData)
{
((H264FramedSource*)clientData)->deliverFrame();
}
void H264FramedSource::deliverFrame()
{
x264_nal_t nalToDeliver;
if (fPlayTimePerFrame > 0 && fPreferredFrameSize > 0) {
if (fPresentationTime.tv_sec == 0 && fPresentationTime.tv_usec == 0) {
// This is the first frame, so use the current time:
gettimeofday(&fPresentationTime, NULL);
} else {
// Increment by the play time of the previous data:
unsigned uSeconds = fPresentationTime.tv_usec + fLastPlayTime;
fPresentationTime.tv_sec += uSeconds/1000000;
fPresentationTime.tv_usec = uSeconds%1000000;
}
// Remember the play time of this data:
fLastPlayTime = (fPlayTimePerFrame*fFrameSize)/fPreferredFrameSize;
fDurationInMicroseconds = fLastPlayTime;
} else {
// We don't know a specific play time duration for this data,
// so just record the current time as being the 'presentation time':
gettimeofday(&fPresentationTime, NULL);
}
if(!m_queue.empty())
{
m_queue.wait_and_pop(nalToDeliver);
uint8_t* newFrameDataStart = (uint8_t*)0xD15EA5E;
newFrameDataStart = (uint8_t*)(nalToDeliver.p_payload);
unsigned newFrameSize = nalToDeliver.i_payload;
// Deliver the data here:
if (newFrameSize > fMaxSize) {
fFrameSize = fMaxSize;
fNumTruncatedBytes = newFrameSize - fMaxSize;
}
else {
fFrameSize = newFrameSize;
}
memcpy(fTo, nalToDeliver.p_payload, nalToDeliver.i_payload);
FramedSource::afterGetting(this);
}
}
Oh and for those who want to know what my concurrent queue is, here it is, and it works brilliantly http://www.justsoftwaresolutions.co.uk/threading/implementing-a-thread-safe-queue-using-condition-variables.html
Enjoy and good luck!
The deliverFrame method lacks the following check at its start:
if (!isCurrentlyAwaitingData()) return;
see DeviceSource.cpp in LIVE