1. Java 与 FFMPEG
FFMPEG 是一个广泛用于媒体处理的库,在Java的世界里,处理视频的能力相当弱,于是有很大需求需要Java 调用 FFMPEG。 Java 调用C 的方式有很多,可以用最原始的JNI方式,也可以JNA方式,还可以是命令行。
采用命令行的方式比较简单,不过有很大局限性,尤其是涉及到 视频的处理和分析的时候,比如要取出某个packet,然后进行处理。
这里介绍的是用JavaCPP 调用 ffmpeg 库的方式,而不是命令行模式。
JavaCPP的源码在这里:https://github.com/bytedeco/javacpp
基于JavaCPP的项目
1)JavaCV,是做图形图像的,有人脸识别、增强现实AR 等开源算法,非常不错 项目主页是:https://github.com/bytedeco/javacv
2)JavaAV 封装了FFMPEG的java 接口
项目主页:https://github.com/hoary/JavaAV
2. JavaCPP Presets
为了方便使用,JavaCPP下面有个presets项目,主页是 https://github.com/bytedeco/javacpp-presets,将一些常用的项目都编译好了以方便使用。
集成的项目包括:
• OpenCV 2.4.9 http://opencv.org/downloads.html
• FFmpeg 2.3.x http://ffmpeg.org/download.html
• FlyCapture 2.6.x http://ww2.ptgrey.com/sdk/flycap
• libdc1394 2.1.x or 2.2.x http://sourceforge.net/projects/libdc1394/files/
• libfreenect 0.5 https://github.com/OpenKinect/libfreenect
• videoInput 0.200 https://github.com/ofTheo/videoInput/tree/update2013
• ARToolKitPlus 2.3.0 https://launchpad.net/artoolkitplus
• flandmark 1.07 http://cmp.felk.cvut.cz/~uricamic/flandmark/#download
• FFTW 3.3.4 http://www.fftw.org/download.html
• GSL 1.16 http://www.gnu.org/software/gsl/#downloading
• LLVM 3.4.2 http://llvm.org/releases/download.html
• Leptonica 1.71 http://www.leptonica.org/download.html
• Tesseract 3.03-rc1 https://code.google.com/p/tesseract-ocr/
包含的平台有: android-arm, android-x86, linux-x86, linux-x86_64, macosx-x86_64, windows-x86, windows-x86_64,
但需要注意:这里的 linux-x86_64 是 基于Fedora 平台的,无法在 CentOS下使用。
3. 在CentOS下编译
1)安装JDK
2)安装 apache-maven 2/3
3) 安装 gcc,gcc+,gcc-c++,yasm
yum -y install yasm gcc+ gcc-c++
4) 获取源码
git clone http://github.com/bytedeco/javacpp-presets
5) 编译 ffmpeg
cd javacpp-presets/
./cppbuild.sh -platform linux-x86_64 install ffmpeg
6) 编译 jni 和 相关jar
mvn install --projects ffmpeg
7) 编译完成后,会在 ffmpeg 的lib上生成相关 .so ,javacpp-presets/targets 下生成相关的jar
4. 测试
1) 将相关的 .so 复制到 /lib64 目录下,或者通过 -Djava.library.path 指定到.so 所在目录
2) 拷贝一个实例用来测试,
public class Tutorial01 {
static void SaveFrame(AVFrame pFrame, int width, int height, int iFrame)
throws IOException {
// Open file
OutputStream stream = new FileOutputStream("frame" + iFrame + ".ppm");
// Write header
stream.write(("P6\n" + width + " " + height + "\n255\n").getBytes());
// Write pixel data
BytePointer data = pFrame.data(0);
byte[] bytes = new byte[width * 3];
int l = pFrame.linesize(0);
for (int y = 0; y < height; y++) {
data.position(y * l).get(bytes);
stream.write(bytes);
}
// Close file
stream.close();
}
public static void main(String[] args) throws IOException {
AVFormatContext pFormatCtx = new AVFormatContext(null);
int i, videoStream;
AVCodecContext pCodecCtx = null;
AVCodec pCodec = null;
AVFrame pFrame = null;
AVFrame pFrameRGB = null;
AVPacket packet = new AVPacket();
int[] frameFinished = new int[1];
int numBytes;
BytePointer buffer = null;
AVDictionary optionsDict = null;
SwsContext sws_ctx = null;
if (args.length < 1) {
args = new String[] { "/root/test.ts" };
// System.out.println("Please provide a movie file");
// System.exit(-1);
}
// Register all formats and codecs
av_register_all();
// Open video file
if (avformat_open_input(pFormatCtx, args[0], null, null) != 0) {
System.exit(-1); // Couldn't open file
}
// Retrieve stream information
if (avformat_find_stream_info(pFormatCtx, (PointerPointer) null) < 0) {
System.exit(-1); // Couldn't find stream information
}
// Dump information about file onto standard error
av_dump_format(pFormatCtx, 0, args[0], 0);
// Find the first video stream
videoStream = -1;
for (i = 0; i < pFormatCtx.nb_streams(); i++) {
if (pFormatCtx.streams(i).codec().codec_type() == AVMEDIA_TYPE_VIDEO) {
videoStream = i;
break;
}
}
if (videoStream == -1) {
System.exit(-1); // Didn't find a video stream
}
// Get a pointer to the codec context for the video stream
pCodecCtx = pFormatCtx.streams(videoStream).codec();
// Find the decoder for the video stream
pCodec = avcodec_find_decoder(pCodecCtx.codec_id());
if (pCodec == null) {
System.err.println("Unsupported codec!");
System.exit(-1); // Codec not found
}
// Open codec
if (avcodec_open2(pCodecCtx, pCodec, optionsDict) < 0) {
System.exit(-1); // Could not open codec
}
// Allocate video frame
pFrame = av_frame_alloc();
// Allocate an AVFrame structure
pFrameRGB = av_frame_alloc();
if (pFrameRGB == null) {
System.exit(-1);
}
// Determine required buffer size and allocate buffer
numBytes = avpicture_get_size(AV_PIX_FMT_RGB24, pCodecCtx.width(),
pCodecCtx.height());
buffer = new BytePointer(av_malloc(numBytes));
sws_ctx = sws_getContext(pCodecCtx.width(), pCodecCtx.height(),
pCodecCtx.pix_fmt(), pCodecCtx.width(), pCodecCtx.height(),
AV_PIX_FMT_RGB24, SWS_BILINEAR, null, null,
(DoublePointer) null);
// Assign appropriate parts of buffer to image planes in pFrameRGB
// Note that pFrameRGB is an AVFrame, but AVFrame is a superset
// of AVPicture
avpicture_fill(new AVPicture(pFrameRGB), buffer, AV_PIX_FMT_RGB24,
pCodecCtx.width(), pCodecCtx.height());
// Read frames and save first five frames to disk
i = 0;
while (av_read_frame(pFormatCtx, packet) >= 0) {
// Is this a packet from the video stream?
if (packet.stream_index() == videoStream) {
// Decode video frame
avcodec_decode_video2(pCodecCtx, pFrame, frameFinished, packet);
// Did we get a video frame?
if (frameFinished[0] != 0) {
// Convert the image from its native format to RGB
sws_scale(sws_ctx, pFrame.data(), pFrame.linesize(), 0,
pCodecCtx.height(), pFrameRGB.data(),
pFrameRGB.linesize());
// Save the frame to disk
if (++i <= 5) {
SaveFrame(pFrameRGB, pCodecCtx.width(),
pCodecCtx.height(), i);
}
}
}
// Free the packet that was allocated by av_read_frame
av_free_packet(packet);
}
// Free the RGB image
av_free(buffer);
av_free(pFrameRGB);
// Free the YUV frame
av_free(pFrame);
// Close the codec
avcodec_close(pCodecCtx);
// Close the video file
avformat_close_input(pFormatCtx);
System.exit(0);
}
}
4)运行实例,得到输出结果: Input #0, mpegts, from '/root/test.ts': Duration: 00:03:20.02, start: 0.056778, bitrate: 1455 kb/s Program 1 Metadata: service_name : jVideo service_provider: jTeam Stream #0:0[0x100]: Video: h264 (High) ([27][0][0][0] / 0x001B), yuv420p, 960x540 [SAR 1:1 DAR 16:9], 25 fps, 25 tbr, 90k tbn, 50 tbc Stream #0:1[0x101]: Audio: aac ([15][0][0][0] / 0x000F), 44100 Hz, stereo, fltp, 66 kb/s