FFmpeg是一个最有名的开源的编解码库,实现了通常的编解码逻辑。它还能够根据平台特性,与平台自有的硬件编解码器进行适配。经过一段时间的学习后,我使用FFmpeg在Android上实现了一个简单的支持硬件解码的视频播放器。在此写下这篇博客记录关键知识点。
代码在此:Android-VideoPlayer
整体上,该工程是基于FFmpeg的,不仅是基于FFmpeg的解码能力,而且一些标志位等直接使用FFmpeg的,不再另外包装。
要使用FFmpeg,需要先将FFmpeg库本身以及它所需要的一些第三方库编译成Android平台库。具体编译脚本和库我已经完成并放到了github上,相关build下面都有readme,记录了编译的事项和相关步骤。
./configure --list-decoders
可以看到FFmpeg支持的所有的decoder。这个编译版本开启了非免费第三方库,不可用来商用,并且由于是练习,为了支持尽可能多的格式,没有进行过多裁切。目前,在Android系统中,支持的解码器就是那明确的几个。如果要使用硬件解码器,必须以名字来查询而不是codec_id。
#define HW_DEC_COUNT 7
#define HW_DEC_H264 "h264_mediacodec"
#define HW_DEC_HEVC "hevc_mediacodec"
#define HW_DEC_VP8 "vp8_mediacodec"
#define HW_DEC_VP9 "vp9_mediacodec"
#define HW_DEC_AV1 "av1_mediacodec"
#define HW_DEC_MPEG2 "mpeg2_mediacodec"
#define HW_DEC_MPEG4 "mpeg4_mediacodec"
const static AVCodecID HW_DECODERS[HW_DEC_COUNT] = {
AVCodecID::AV_CODEC_ID_H264,
AVCodecID::AV_CODEC_ID_HEVC,
AVCodecID::AV_CODEC_ID_VP8,
AVCodecID::AV_CODEC_ID_VP9,
AVCodecID::AV_CODEC_ID_AV1,
AVCodecID::AV_CODEC_ID_MPEG2VIDEO,
AVCodecID::AV_CODEC_ID_MPEG4
};
const static const char* HW_DECODER_NAMES[HW_DEC_COUNT] = {
HW_DEC_H264,
HW_DEC_HEVC,
HW_DEC_VP8,
HW_DEC_VP9,
HW_DEC_AV1,
HW_DEC_MPEG2,
HW_DEC_MPEG4
};
static bool supportHWDec(AVCodecID codecId) {
for (AVCodecID id : HW_DECODERS) {
if (id == codecId) {
return true;
}
}
return false;
}
static const char* getHWDecName(AVCodecID codecId) {
for (int i = 0; i < HW_DEC_COUNT; i++) {
if (HW_DECODERS[i] == codecId) {
return HW_DECODER_NAMES[i];
}
}
return nullptr;
}
// 根据参数查找相应的decoder
bool FFmpegDecoder::init(AVCodecParameters *params, PreferCodecType preferType) {
AVCodecID ffCodecID = AV_CODEC_ID_NONE;
try {
ffCodecID = AVCodecID(params->codec_id);
} catch (...) {
LOGE(TAG, "failed to convert %d to AVCodecID", params->codec_id);
return false;
}
// 可以支持指定解码器类型。如果未指定,那就优先查找硬件解码器,找不到再去找软件解码器
if (preferType == PreferCodecType::HW) {
return findHWDecoder(params, ffCodecID);
} else if (preferType == PreferCodecType::SW) {
return findSWDecoder(params, ffCodecID);
} else {
if (findHWDecoder(params, ffCodecID)) {
return true;
}
if (findSWDecoder(params, ffCodecID)) {
return true;
}
return false;
}
}
// 查找硬件解码器
bool FFmpegDecoder::findHWDecoder(AVCodecParameters *params, AVCodecID codecId) {
release();
int ret;
const char *hwDecName = getHWDecName(codecId);
if (hwDecName == nullptr) {
return false;
}
const AVCodec * aCodec = avcodec_find_decoder_by_name(hwDecName);
if (aCodec == nullptr) {
LOGE(TAG, "Can't find hw decoder for codec: {id = %d, hw_name = %s}", codecId, hwDecName);
return false;
} else {
codec = const_cast<AVCodec *>(aCodec);
}
codecCtx = avcodec_alloc_context3(codec);
if (!codecCtx) {
LOGE(TAG, "failed to alloc codec context");
return false;
}
ret = avcodec_parameters_to_context(codecCtx, params);
if (ret < 0) {
LOGE(TAG, "copy decoder params failed, err = %d", ret);
return false;
}
for (int i = 0;;i++) {
const AVCodecHWConfig *config = avcodec_get_hw_config(codec, i);
if (config == nullptr) {
LOGE(TAG, "%s hw config is null", codec->name);
break;
}
if ((config->methods & AV_CODEC_HW_CONFIG_METHOD_HW_DEVICE_CTX) &&
config->device_type == AVHWDeviceType::AV_HWDEVICE_TYPE_MEDIACODEC) {
// 该解码器支持硬件解码
out_hw_pix_format = config->pix_fmt;
hwPixFormat = config->pix_fmt;
codecCtx->get_format = get_hw_format;
if (initHWDecoder(codecCtx, AVHWDeviceType::AV_HWDEVICE_TYPE_MEDIACODEC) < 0) {
LOGE(TAG, "initHWDecoder failed");
return false;
} else {
break;
}
}
}
ret = avcodec_open2(codecCtx, codec, nullptr);
if (ret < 0) {
char buf[100];
av_make_error_string(buf, 100, ret);
LOGE(TAG, "open codec failed for %s, err = %s", codec->name, buf);
return false;
}
codecType = CodecType::HW;
return true;
}
// 查找软件解码器
bool FFmpegDecoder::findSWDecoder(AVCodecParameters *params, AVCodecID codecId) {
release();
int ret;
const AVCodec * aCodec = avcodec_find_decoder(codecId);
if (aCodec == nullptr) {
LOGE(TAG, "Can't find decoder for codecID %d", codecId);
return false;
}
codec = const_cast<AVCodec *>(aCodec);
codecCtx = avcodec_alloc_context3(codec);
if (!codecCtx) {
LOGE(TAG, "failed to alloc codec context");
return false;
}
ret = avcodec_parameters_to_context(codecCtx, params);
if (ret < 0) {
LOGE(TAG, "copy decoder params failed, err = %d", ret);
return false;
}
ret = avcodec_open2(codecCtx, codec, nullptr);
if (ret < 0) {
char buf[100];
av_make_error_string(buf, 100, ret);
LOGE(TAG, "open codec failed for %s, err = %s", codec->name, buf);
return false;
}
codecType = CodecType::SW;
return true;
}
解码其实很简单。首先是先创建方便使用的音频和视频帧结构体,这两个结构体分别是AudioFrame和VideoFrame。其实也就是额外包含了一些属性方便访问和使用,内容物还是AVFrame。
对于解码,其实流程比较固定。
音视频同步逻辑:在视频播放的过程中,音频是连续不断的,而视频却有不同帧率,所以同步是基于音频的时间戳。当然有些视频没有音频内容,此时就需要独立时钟来作为同步时间戳。
对于seek功能的支持:当用户进行seek时,置一个seekFlag为true。在解复用阶段,如果seekFlag为true,那解复用就对文件进行seek。同时对音视频AVPacket同步队列都清空,并向其中各存放一个seek标志的AVPacket。然后继续从seek点开始解复用。解码阶段在读取解复用存放的特殊AVPacket时,就对解码器进行reset,清空其内部缓存,然后存放两个seek标志分别到AVFrame的同步队列。在同步阶段,如果同步线程读取到任何一个具有seek标志的AVFrame,就停止输送到输出,并等待另一个同步队列读取到具有seek标志的AVFrame。在音视频都读取到seek标志之前,所有的AVFrame都弃用。读取到之后,重新进行同步。
解复用:
/*
* Read packet data from source.
* If the packet has some flags like STREAM_FLAG_SOUGHT, this packet won't
* contain data.
* */
void Player::readStreamLoop() {
if (!formatCtx) {
LOGE(TAG, "no format context");
return;
}
int ret;
bool pushSuccess = false;
while (!stopReadFlag) {
AVPacket *packet = av_packet_alloc();
if (!packet) {
LOGE(TAG, "av_packet_alloc failed");
return;
}
if (seekFlag) {
int64_t pts = (int64_t) (seekPtsMS / 1000.0f * AV_TIME_BASE);
LOGD(TAG, "meet seek, time = %lld", pts);
int streamIndex = -1;
// if (audioStreamIndex >= 0) {
// pts = (int64_t)(seekPtsMS / av_q2d(formatCtx->streams[audioStreamIndex]->time_base));
// streamIndex = audioStreamIndex;
// } else if (videoStreamIndex >= 0) {
// pts = (int64_t)(seekPtsMS / av_q2d(formatCtx->streams[videoStreamIndex]->time_base));
// streamIndex = videoStreamIndex;
// }
av_seek_frame(formatCtx, streamIndex, pts, AVSEEK_FLAG_BACKWARD);
// put a empty packet width flag STREAM_FLAG_SOUGHT
if (enableAudio) {
audioPacketQueue.clear();
PacketWrapper *p = playerContext.getEmptyPacketWrapper();
p->flags = STREAM_FLAG_SOUGHT;
audioPacketQueue.forcePush(p);
// audioDecodeSeekFlag = true;
}
if (enableVideo) {
videoPacketQueue.clear();
PacketWrapper *p = playerContext.getEmptyPacketWrapper();
p->flags = STREAM_FLAG_SOUGHT;
videoPacketQueue.forcePush(p);
// videoDecodeSeekFlag = true;
}
// syncSeekFlag = true;
seekFlag = false;
}
ret = av_read_frame(formatCtx, packet);
if (ret == 0) {
if (packet->stream_index == audioStreamIndex && enableAudio) {
PacketWrapper *pw = playerContext.getEmptyPacketWrapper();
pw->setParams(packet);
if (videoPacketQueue.getSize() == 0) {
audioPacketQueue.forcePush(pw);
} else {
pushSuccess = audioPacketQueue.push(pw);
if (!pushSuccess) {
audioPacketQueue.forcePush(pw);
}
}
} else if (packet->stream_index == videoStreamIndex && enableVideo) {
PacketWrapper *pw = playerContext.getEmptyPacketWrapper();
pw->setParams(packet);
if (audioPacketQueue.getSize() == 0) {
videoPacketQueue.forcePush(pw);
} else {
pushSuccess = videoPacketQueue.push(pw);
if (!pushSuccess) {
videoPacketQueue.forcePush(pw);
}
}
} else {
av_packet_unref(packet);
av_packet_free(&packet);
}
} else if (ret == AVERROR_EOF) {
av_packet_free(&packet);
packet = nullptr;
if (enableAudio) {
PacketWrapper *pw = playerContext.getEmptyPacketWrapper();
audioPacketQueue.forcePush(pw);
}
if (enableVideo) {
PacketWrapper *pw = playerContext.getEmptyPacketWrapper();
videoPacketQueue.forcePush(pw);
}
} else if (ret < 0) {
LOGE(TAG, "av_read_frame failed");
av_packet_free(&packet);
packet = nullptr;
return;
}
}
}
音频解码:
void Player::decodeAudioLoop() {
if (!formatCtx) {
return;
}
if (!audioDecoder) {
LOGE(TAG, "audio decoder is null");
return;
}
int ret;
optional<PacketWrapper *> packetOpt;
PacketWrapper *pw = nullptr;
AVFrame *frame = nullptr;
AudioFrame *audioFrame = nullptr;
while (!stopDecodeAudioFlag && enableAudio) {
packetOpt = audioPacketQueue.pop();
if (!packetOpt.has_value()) {
LOGE(TAG, "audio packetOpt has no value");
break;
}
pw = packetOpt.value();
if ((pw->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT) {
LOGD(TAG, "decode audio, meet a seek frame");
playerContext.recyclePacketWrapper(pw);
pw = nullptr;
audioFrameQueue.clear();
audioDecoder->flush();
audioFrame = playerContext.getEmptyAudioFrame();
audioFrame->flags |= STREAM_FLAG_SOUGHT;
audioFrameQueue.forcePush(audioFrame);
audioFrame = nullptr;
continue;
}
ret = audioDecoder->sendPacket(pw->avPacket);
if (ret < 0) {
LOGE(TAG, "audio decoder send packet failed, err = %d", ret);
break;
}
while (true) {
frame = av_frame_alloc();
ret = audioDecoder->receiveFrame(frame);
if (ret < 0) {
av_frame_unref(frame);
av_frame_free(&frame);
frame = nullptr;
break;
}
audioFrame = playerContext.getEmptyAudioFrame();
audioFrame->setParams(frame, audioStreamMap[audioStreamIndex].sampleFormat,
formatCtx->streams[audioStreamIndex]->time_base);
if (!audioFrameQueue.push(audioFrame)) {
audioFrameQueue.push(audioFrame, false);
}
// DON'T delete AVFrame here, it will be carried to output by AudioFrame
audioFrame = nullptr;
frame = nullptr;
}
if (ret == AVERROR(EAGAIN)) {
// LOGD(TAG, "audio stream again");
continue;
} else if (ret == AVERROR_EOF) {
// LOGD(TAG, "audio stream meets eof");
break;
} else {
// LOGE(TAG, "audio decoder error: %d", ret);
break;
}
}
if (pw) {
playerContext.recyclePacketWrapper(pw);
}
if (frame) {
av_frame_unref(frame);
av_frame_free(&frame);
frame = nullptr;
}
if (audioFrame) {
audioFrameQueue.push(audioFrame, false);
audioFrame = nullptr;
}
LOGD(TAG, "audio decode loop finish");
}
视频解码:
void Player::decodeVideoLoop() {
if (!formatCtx) {
return;
}
if (!videoDecoder) {
LOGE(TAG, "video decoder is null");
return;
}
int ret;
optional<PacketWrapper *> packetOpt;
PacketWrapper *pw = nullptr;
AVFrame *frame = nullptr;
VideoFrame *videoFrame = nullptr;
while (!stopDecodeVideoFlag && enableVideo) {
packetOpt = videoPacketQueue.pop();
if (!packetOpt.has_value()) {
LOGE(TAG, "video packetOpt has no value");
break;
}
pw = packetOpt.value();
if ((pw->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT) {
LOGD(TAG, "decode video, meet a seek frame");
playerContext.recyclePacketWrapper(pw);
pw = nullptr;
videoFrameQueue.clear();
videoDecoder->flush();
videoFrame = playerContext.getEmptyVideoFrame();
videoFrame->flags |= STREAM_FLAG_SOUGHT;
videoFrameQueue.forcePush(videoFrame);
videoFrame = nullptr;
continue;
}
ret = videoDecoder->sendPacket(pw->avPacket);
if (ret < 0) {
LOGE(TAG, "video decoder send packet failed, err = %d", ret);
break;
}
while (true) {
frame = av_frame_alloc();
ret = videoDecoder->receiveFrame(frame);
if (ret < 0) {
av_frame_unref(frame);
av_frame_free(&frame);
frame = nullptr;
break;
}
videoFrame = playerContext.getEmptyVideoFrame();
videoFrame->setParams(frame, AVPixelFormat(frame->format),
formatCtx->streams[videoStreamIndex]->time_base);
if (!videoFrameQueue.push(videoFrame)) {
videoFrameQueue.push(videoFrame, false);
}
// DON'T delete AVFrame, it will be carried to output by VideoFrame.
videoFrame = nullptr;
frame = nullptr;
}
if (ret == AVERROR(EAGAIN)) {
// LOGD(TAG, "video stream again");
continue;
} else if (ret == AVERROR_EOF) {
// LOGD(TAG, "video stream meets eof");
break;
} else {
// LOGE(TAG, "video decoder error: %d", ret);
break;
}
}
if (pw) {
playerContext.recyclePacketWrapper(pw);
}
if (frame) {
av_frame_unref(frame);
av_frame_free(&frame);
frame = nullptr;
}
if (videoFrame) {
videoFrameQueue.push(videoFrame, false);
videoFrame = nullptr;
}
LOGD(TAG, "video decode loop finish");
}
同步代码:
void Player::syncLoop() {
chrono::system_clock::time_point lastAudioWriteTime;
chrono::system_clock::time_point lastVideoWriteTime;
int64_t lastAudioPts = -1;
int64_t lastVideoPts = -1;
if (stateListener != nullptr) {
stateListener->playStateChanged(true);
}
AudioFrame *audioFrame = unPlayedAudioFrame;
unPlayedAudioFrame = nullptr;
VideoFrame *videoFrame = unPlayedVideoFrame;
unPlayedVideoFrame = nullptr;
while (!stopSyncFlag) {
if (enableAudio && enableVideo) {
if (audioFrame == nullptr) {
optional<AudioFrame *> frameOpt = audioFrameQueue.pop();
if (frameOpt.has_value()) {
audioFrame = frameOpt.value();
} else {
break;
}
}
if (videoFrame == nullptr) {
optional<VideoFrame *> frameOpt = videoFrameQueue.pop();
if (frameOpt.has_value()) {
videoFrame = frameOpt.value();
} else {
break;
}
}
if (lastAudioPts == -1) {
lastAudioPts = audioFrame->pts;
}
if (lastVideoPts == -1) {
lastVideoPts = videoFrame->pts;
}
if ((audioFrame->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT
&& (videoFrame->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT) {
LOGD(TAG, "sync, meet both audio and video seek frame");
playerContext.recycleAudioFrame(audioFrame);
audioFrame = nullptr;
playerContext.recycleVideoFrame(videoFrame);
videoFrame = nullptr;
continue;
} else if ((audioFrame->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT) {
LOGD(TAG, "sync, meet audio seek frame");
playerContext.recycleVideoFrame(videoFrame);
videoFrame = nullptr;
continue;
} else if ((videoFrame->flags & STREAM_FLAG_SOUGHT) == STREAM_FLAG_SOUGHT) {
LOGD(TAG, "sync, meet video seek frame");
playerContext.recycleAudioFrame(audioFrame);
audioFrame = nullptr;
continue;
}
int64_t audioOutputPts = audioFrame->getOutputPts();
if (videoFrame->pts <= audioOutputPts) {
lastVideoPts = videoFrame->pts;
videoOutput->write(videoFrame);
videoFrame = nullptr;
} else {
int64_t outputFrames = (videoFrame->pts + 3 - audioOutputPts) * 1.0f / 1000 * audioFrame->sampleRate;
outputFrames = min((int64_t)(audioFrame->numFrames - audioFrame->outputStartIndex), outputFrames);
audioFrame->outputFrameCount = outputFrames;
lastAudioPts = audioOutputPts;
audioOutput->write(audioFrame);
audioFrame->outputStartIndex += audioFrame->outputFrameCount;
if (audioFrame->outputStartIndex == audioFrame->numFrames) {
playerContext.recycleAudioFrame(audioFrame);
audioFrame = nullptr;
}
}
if (stateListener != nullptr) {
stateListener->progressChanged(lastAudioPts, false);
}
} else if (enableVideo) {
if (videoFrame == nullptr) {
optional<VideoFrame *> frameOpt = videoFrameQueue.pop();
if (frameOpt.has_value()) {
videoFrame = frameOpt.value();
} else {
break;
}
}
lastVideoPts = videoFrame->pts;
videoOutput->write(videoFrame);
videoFrame = nullptr;
this_thread::sleep_for(chrono::milliseconds(17));
if (stateListener != nullptr) {
stateListener->progressChanged(lastVideoPts, false);
}
} else if (enableAudio) {
if (audioFrame == nullptr) {
optional<AudioFrame *> frameOpt = audioFrameQueue.pop();
if (frameOpt.has_value()) {
audioFrame = frameOpt.value();
} else {
break;
}
}
lastAudioPts = audioFrame->pts;
audioOutput->write(audioFrame);
playerContext.recycleAudioFrame(audioFrame);
audioFrame = nullptr;
if (stateListener != nullptr) {
stateListener->progressChanged(lastAudioPts, false);
}
} else {
LOGE(TAG, "both audio and video disabled, break");
break;
}
}
if (audioFrame) {
unPlayedAudioFrame = audioFrame;
}
if (videoFrame) {
unPlayedVideoFrame = videoFrame;
}
if (stateListener != nullptr) {
stateListener->playStateChanged(false);
}
}
不同的平台使用不同的音频框架进行音频输出。Android平台我选择使用oboe。对音频输出我定义了一下接口来统一各平台的调用。
//
// Created by 祖国瑞 on 2022/9/5.
//
#ifndef ANDROID_VIDEOPLAYER_IAUDIOOUTPUT_H
#define ANDROID_VIDEOPLAYER_IAUDIOOUTPUT_H
#include
#include "PlayerContext.h"
#include "AudioFrame.h"
extern "C" {
#include "FFmpeg/libavformat/avformat.h"
}
class IAudioOutput {
public:
IAudioOutput(PlayerContext *playerContext) {
this->playerCtx = playerContext;
}
virtual bool create(int sampleRate, int channels, AVSampleFormat sampleFormat) = 0;
virtual void release() = 0;
virtual void start() = 0;
virtual void stop() = 0;
virtual bool write(AudioFrame *audioFrame) = 0;
virtual void write(uint8_t *buffer, int framesPerChannel) = 0;
protected:
PlayerContext *playerCtx = nullptr;
};
#endif //ANDROID_VIDEOPLAYER_IAUDIOOUTPUT_H
由于oboe使用比较简单,这里就不单独列出来了。需要注意的是,由于源文件采样率及采样格式多种多样,音频框架不一定支持。所以在输出之前,使用FFmpeg的avresample来重采样。
视频输出使用OpenGL ES,这里还有很多需要优化,比如EGL的格式目前是写死的,对于超出8bit长度的像素格式,还是统一转换为了float32并建立纹理,YUV的非planner数据(例如NV21格式,U和V是混合在一个数据平面中交替出现的)需要切分成三个纹理使用。这样很多工作都是由cpu完成的,开销比较大,而且速度较慢。接下来会探索Android的ANativeBuffer支持的format,它与OpenGL ES的纹理格式是对应的,尽量减少cpu工作。
视频输出同样也对各平台规定了一个接口:
//
// Created by 祖国瑞 on 2022/9/5.
//
#ifndef ANDROID_VIDEOPLAYER_IVIDEOOUTPUT_H
#define ANDROID_VIDEOPLAYER_IVIDEOOUTPUT_H
#include
#include "VideoFrame.h"
#include "PlayerContext.h"
#include "SizeMode.h"
class IVideoOutput {
public:
IVideoOutput(PlayerContext *playerContext) {
this->playerCtx = playerContext;
};
virtual bool setFormat(AVPixelFormat pixelFormat, AVColorSpace colorSpace, bool isHDR) = 0;
virtual bool create(void *surface) = 0;
virtual void release() = 0;
virtual void setScreenSize(int32_t width, int32_t height) = 0;
virtual bool isReady() = 0;
virtual void write(VideoFrame* frame) = 0;
virtual void setSizeMode(SizeMode mode) = 0;
protected:
PlayerContext *playerCtx;
AVPixelFormat srcPixelFormat = AVPixelFormat::AV_PIX_FMT_NONE;
};
#endif //ANDROID_VIDEOPLAYER_IVIDEOOUTPUT_H
对于Android平台,我使用OpenGL ES来渲染。
首先,shader部分很简单,其主要作用就是yuv转rgb。但是由于GPU天然适合做大量简单计算,所以我们可以在shader里去最大化兼容各种像素格式,例如10bit int,16bit float等。以及各种大尾序小尾序等。
static const char *vertexShaderCode =
"#version 300 es\n"
"layout (location = 0) in vec3 aPos;\n"
"layout (location = 1) in vec2 aTexCoord;\n"
"out vec2 TexCoord;\n"
"void main() {\n"
" gl_Position = vec4(aPos, 1.0f);\n"
" TexCoord = aTexCoord;\n"
"}\n";
static const char *yuv2rgbShaderCode =
"#version 300 es\n"
"precision mediump float;\n"
"uniform sampler2D tex_y;\n"
"uniform sampler2D tex_u;\n"
"uniform sampler2D tex_v;\n"
"in vec2 TexCoord;\n"
"out vec4 FragColor;\n"
"void main() {\n"
" float y = texture(tex_y, TexCoord).r - 0.0625f;\n"
" float u = texture(tex_u, TexCoord).r - 0.5f;\n"
" float v = texture(tex_v, TexCoord).r - 0.5f;\n"
" float r = 1.164f * y + 1.793f * v;\n"
" float g = 1.164f * y - 0.213f * u - 0.533f * v;\n"
" float b = 1.164f * y + 2.112f * u;\n"
" //float a = texture(tex_y, TexCoord).r;\n"
" FragColor = vec4(r, g, b, 1.0f);\n"
"}\n";
static const char *yuv16ui2rgbShaderCode =
"#version 300 es\n"
"precision mediump float;\n"
"uniform usampler2D tex_y;\n"
"uniform usampler2D tex_u;\n"
"uniform usampler2D tex_v;\n"
"in vec2 TexCoord;\n"
"out vec4 FragColor;\n"
"void main() {\n"
" float y = float(texture(tex_y, TexCoord).r) - 0.0625f;\n"
" float u = float(texture(tex_u, TexCoord).r) - 0.5f;\n"
" float v = float(texture(tex_v, TexCoord).r) - 0.5f;\n"
" float r = 1.164f * y + 1.793f * v;\n"
" float g = 1.164f * y - 0.213f * u - 0.533f * v;\n"
" float b = 1.164f * y + 2.112f * u;\n"
" //float a = texture(tex_y, TexCoord).r;\n"
" FragColor = vec4(r, g, b, 1.0f);\n"
"}\n";
static const char *rgbShaderCode =
"#version 300 se\n"
"\n"
"uniform sampler2D tex_rgb;\n"
"\n"
"in vec2 TexCoord;\n"
"\n"
"out vec4 FragColor;\n"
"\n"
"void main() {\n"
" FragColor = texture(tex_rgb, TexCoord);\n"
"}\n";
然后就是像素处理了,我们需要把各种像素布局和像素格式的图片转换为OpenGL ES可以接受的texture,然后才能在shader里进行处理。
首先是根据像素格式来确定使用哪种shader。
bool GLESRender::setFormat(AVPixelFormat format, AVColorSpace colorSpace, bool isHDR) {
LOGD(TAG, "setFormat");
if (!eglWindow.isReady()) {
LOGE(TAG, "eglWindow is not ready");
return false;
}
pixelType = get_pixel_type(format);
pixelLayout = get_pixel_layout(format);
if (pixelType == PixelType::None || pixelLayout == PixelLayout::None) {
LOGE(TAG, "unsupported pixel format: %d", format);
return false;
}
// 根据像素格式来确定texture的格式等。注意这里GLES的format与GL的format并不完全一致,有很多是用不了的。
// 你可以参考Android的硬件buffer format与GLES的format的对应关系。
// 链接在此:https://developer.android.google.cn/ndk/reference/group/a-hardware-buffer
if (pixelType == PixelType::RGB) {
switch (format) {
case AV_PIX_FMT_RGB24:
glDataType = GL_UNSIGNED_BYTE;
glInternalFormat = GL_RGB;
glDataFormat = GL_UNSIGNED_BYTE;
glSupportFormat = true;
break;
case AV_PIX_FMT_RGB565LE:
glDataType = GL_UNSIGNED_SHORT_5_6_5;
glInternalFormat = GL_RGB;
glDataFormat = GL_UNSIGNED_SHORT_5_6_5;
glSupportFormat = true;
break;
case AV_PIX_FMT_RGB444LE:
glDataType = GL_UNSIGNED_SHORT_4_4_4_4;
glInternalFormat = GL_RGB;
glDataFormat = GL_UNSIGNED_SHORT_4_4_4_4;
glSupportFormat = true;
break;
default:
LOGE(TAG, "unsupported RGB format: %d", format);
return false;
}
if (!shader.compileShader(vertexShaderCode, rgbShaderCode)) {
LOGE(TAG, "format = RGB24, compile shader failed");
return false;
}
} else if (pixelType == PixelType::YUV) {
yuvCompDepth = get_yuv_comp_depth(format);
if (yuvCompDepth < 0) {
LOGE(TAG, "get_yuv_comp_depth failed, format = %d", format);
return false;
}
const char *fragmentCode;
if (yuvCompDepth <= 8) {
glDataType = GL_UNSIGNED_BYTE;
glInternalFormat = GL_LUMINANCE;
glDataFormat = GL_LUMINANCE;
fragmentCode = yuv2rgbShaderCode;
} else if (yuvCompDepth <= 16) {
glDataType = GL_FLOAT;
glInternalFormat = GL_R32F;
glDataFormat = GL_RED;
fragmentCode = yuv2rgbShaderCode;
} else {
LOGE(TAG, "unsupported yuvCompDepth: %d", yuvCompDepth);
return false;
}
if (!shader.compileShader(vertexShaderCode, fragmentCode)) {
LOGE(TAG, "format = %d, compile shader failed", format);
return false;
}
eglWindow.makeCurrent();
LOGD(TAG, "yuvCompDepth = %d", yuvCompDepth);
} else {
LOGE(TAG, "unsupported pixel format: %d", format);
return false;
}
this->format = format;
this->colorSpace = colorSpace;
this->isHDR = isHDR;
LOGD(TAG, "setFormat: format = %d, pixType = %d, glDataType = 0x%x", format, pixelType, glDataType);
if (!shader.isReady()) {
LOGE(TAG, "shader is not ready");
return false;
}
return true;
}
拿到视频数据后,某些yuv数据需要将其转换成三个独立的纹理,再给OpenGL ES去处理。最关键的信息就是像素类型、像素布局和像素深度。
enum class PixelType {
None = -1,
RGB,
YUV
};
// 像素布局。
enum class PixelLayout {
None = -1,
// 多数yuv数据(例如YUV420P)都是planner,YUV三种像素是独立存储的,各占一个平面。
Planner,
// 多数RGB数据(例如RGB565)都是packet,RGB三像素依次存储,混编在一个平面内。
Packet,
// 半平面,Android平台的NV21和NV12就是这种格式,Y像素单独存储到一个平面,UV数据依次存储,混编在一个平面
Semi_Planner,
};
// 获取某种yuv格式的像素深度。一般都是8bit,现在有很多HDR视频是10bit。
// 目前还没有RGB相关的该方法,因为RGB图片本来就可以直接转为纹理,不需要单独处理。如果之后出现了与ANativeBuffer的格式不兼容的RGB格式,
// 也需要类似的处理。
int get_yuv_comp_depth(AVPixelFormat format);
然后就是将yuv数据分别读取到三个像素buffer中,方便之后转换为纹理。
bool read_yuv_pixel(AVFrame *frame, AVPixelFormat format, int64_t width, int64_t height,
uint8_t *yBuffer, int *yWidth, int *yHeight,
uint8_t *uBuffer, int *uWidth, int *uHeight,
uint8_t *vBuffer, int *vWidth, int *vHeight) {
PixelLayout layout = get_pixel_layout(format);
if (layout == PixelLayout::Planner) {
return read_yuv_planner(frame, format, width, height, yBuffer, yWidth, yHeight, uBuffer, uWidth, uHeight, vBuffer, vWidth, vHeight);
} else if (layout == PixelLayout::Packet) {
return read_yuv_packet(frame, format, width, height, yBuffer, yWidth, yHeight, uBuffer, uWidth, uHeight, vBuffer, vWidth, vHeight);
} else if (layout == PixelLayout::Semi_Planner) {
return read_yuv_semi_planner(frame, format, width, height, yBuffer, yWidth, yHeight, uBuffer, uWidth, uHeight, vBuffer, vWidth, vHeight);
} else {
return false;
}
}