0

我试图使用 jpegparse 而不是 h264parse 将输入源类型从视频更改为图像，但是我使用的后处理图像在人的顶部没有骨架覆盖，并且运行时的值显示检测失败。

GMainLoop *loop = NULL;
  GstCaps *caps = NULL;
  GstElement *pipeline = NULL, *source = NULL, *jpegparser = NULL,
             *decoder = NULL, *streammux = NULL, *sink = NULL, *pgie = NULL, *nvvidconv = NULL, *nvosd = NULL;


  GstBus *bus = NULL;
  guint bus_watch_id;
  GstPad *osd_sink_pad = NULL;

  if (argc != 2)
  {
    g_printerr("Usage: %s <filename> \n", argv[0]);
    return -1;
  }

  gst_init(&argc, &argv);
  loop = g_main_loop_new(NULL, FALSE);

  pipeline = gst_pipeline_new("deepstream-tensorrt-openpose-pipeline");

  source = gst_element_factory_make("filesrc", "file-source");

  jpegparser = gst_element_factory_make("jpegparse", "jpeg-parser");

  decoder = gst_element_factory_make("nvv4l2decoder", "nvv4l2-decoder");

  streammux = gst_element_factory_make("nvstreammux", "stream-muxer");

  if (!pipeline || !streammux)
  {
    g_printerr("One element could not be created. Exiting.\n");
    return -1;
  }

  pgie = gst_element_factory_make("nvinfer", "primary-nvinference-engine");

  nvsink = gst_element_factory_make("nveglglessink", "nvvideo-renderer");
  sink = gst_element_factory_make("fpsdisplaysink", "fps-display");

  g_object_set(G_OBJECT(sink), "text-overlay", FALSE, "video-sink", nvsink, "sync", FALSE, NULL);

  if (!source || !jpegparser || !decoder || !pgie || !nvvidconv || !nvosd || !sink)
  {
    g_printerr("One element could not be created. Exiting.\n");
    return -1;
  }


  g_object_set(G_OBJECT(source), "location", argv[1], NULL);

  g_object_set(G_OBJECT(streammux), "width", MUXER_OUTPUT_WIDTH, "height",
               MUXER_OUTPUT_HEIGHT, "batch-size", 1,
               "batched-push-timeout", MUXER_BATCH_TIMEOUT_USEC, NULL);


  g_object_set(G_OBJECT(pgie), "output-tensor-meta", TRUE,
               "config-file-path", "deepstream_pose_estimation_config.txt", NULL);


  bus = gst_pipeline_get_bus(GST_PIPELINE(pipeline));
  bus_watch_id = gst_bus_add_watch(bus, bus_call, loop);
  gst_object_unref(bus);


  gst_bin_add_many(GST_BIN(pipeline),
                   streammux, source, jpegparser, decoder, pgie,
                   nvvidconv, nvosd, sink, NULL);
  GstPad *sinkpad, *srcpad;
  gchar pad_name_sink[16] = "sink_0";
  gchar pad_name_src[16] = "src";

  sinkpad = gst_element_get_request_pad(streammux, pad_name_sink);
  if (!sinkpad)
  {
    g_printerr("Streammux request sink pad failed. Exiting.\n");
    return -1;
  }

  srcpad = gst_element_get_static_pad(decoder, pad_name_src);
  if (!srcpad)
  {
    g_printerr("Decoder request src pad failed. Exiting.\n");
    return -1;
  }

  if (gst_pad_link(srcpad, sinkpad) != GST_PAD_LINK_OK)
  {
    g_printerr("Failed to link decoder to stream muxer. Exiting.\n");
    return -1;
  }

  gst_object_unref(sinkpad);
  gst_object_unref(srcpad);

  if (!gst_element_link_many(source, jpegparser, decoder, NULL))
  {
    g_printerr("Elements could not be linked: 1. Exiting.\n");
    return -1;
  }

  if (!gst_element_link_many(streammux, pgie, nvvidconv, nvosd, sink, NULL))
  {
    g_printerr("Elements could not be linked: 2. Exiting.\n");
    return -1;
  }

  GstPad *pgie_src_pad = gst_element_get_static_pad(pgie, "src");
  if (!pgie_src_pad)
    g_print("Unable to get pgie src pad\n");
  else
    gst_pad_add_probe(pgie_src_pad, GST_PAD_PROBE_TYPE_BUFFER,
                      pgie_src_pad_buffer_probe, (gpointer)sink, NULL);

  osd_sink_pad = gst_element_get_static_pad(nvosd, "sink");
  if (!osd_sink_pad)
    g_print("Unable to get sink pad\n");
  else
    gst_pad_add_probe(osd_sink_pad, GST_PAD_PROBE_TYPE_BUFFER,
                      osd_sink_pad_buffer_probe, (gpointer)sink, NULL);

  g_print("Now playing: %s\n", argv[1]);
  gst_element_set_state(pipeline, GST_STATE_PLAYING);

  g_print("Running...\n");
  g_main_loop_run(loop);

  g_print("Returned, stopping playback\n");
  gst_element_set_state(pipeline, GST_STATE_NULL);
  g_print("Deleting pipeline\n");
  gst_object_unref(GST_OBJECT(pipeline));
  g_source_remove(bus_watch_id);
  g_main_loop_unref(loop);

我想将此解决方案用于姿势估计，但使用图像源，而不是视频源，但我不知道为什么此实现不起作用，所以如果有人有想法，请告诉我。任何帮助是极大的赞赏。

4

0 回答 0