app-source-bin-rstp-out.py

#!/usr/bin/env python3

################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2020-2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
################################################################################

import sys
sys.path.append('../')
import configparser
import gi
gi.require_version('Gst', '1.0')
gi.require_version('GstRtspServer', '1.0')
from gi.repository import GLib, Gst, GstRtspServer
from common.is_aarch_64 import is_aarch64
from common.bus_call import bus_call

import pyds

import ctypes
import numpy as np


PGIE_CLASS_ID_PERSON = 0

id_name_dic = {}
codec="H264"


def osd_sink_pad_buffer_probe(pad,info,u_data):
    frame_number=0
    #Intiallizing object counter with 0.
    obj_counter = {
        PGIE_CLASS_ID_PERSON:0,
    }
    num_rects=0

    gst_buffer = info.get_buffer()
    if not gst_buffer:
        print("Unable to get GstBuffer ")
        return

    # Retrieve batch metadata from the gst_buffer
    # Note that pyds.gst_buffer_get_nvds_batch_meta() expects the
    # C address of gst_buffer as input, which is obtained with hash(gst_buffer)
    batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
    l_frame = batch_meta.frame_meta_list
    while l_frame is not None:
        try:
            # Note that l_frame.data needs a cast to pyds.NvDsFrameMeta
            # The casting is done by pyds.NvDsFrameMeta.cast()
            # The casting also keeps ownership of the underlying memory
            # in the C code, so the Python garbage collector will leave
            # it alone.
           frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
        except StopIteration:
            break

        frame_number=frame_meta.frame_num
        num_rects = frame_meta.num_obj_meta
        l_obj=frame_meta.obj_meta_list
        while l_obj is not None:
            try:
                # Casting l_obj.data to pyds.NvDsObjectMeta
                obj_meta=pyds.NvDsObjectMeta.cast(l_obj.data)
            except StopIteration:
                break
            obj_counter[obj_meta.class_id] += 1
            l_user_meta = obj_meta.obj_user_meta_list

            while l_user_meta is not None:
                try:
                    # Note that l_user_meta.data needs a cast to pyds.NvDsUserMeta
                    # The casting is done by pyds.NvDsUserMeta.cast()
                    # The casting also keeps ownership of the underlying memory
                    # in the C code, so the Python garbage collector will leave
                    # it alone
                    user_meta=pyds.NvDsUserMeta.cast(l_user_meta.data)
                except StopIteration:
                    break

                tensor_meta = pyds.NvDsInferTensorMeta.cast(user_meta.user_meta_data)
                layer = pyds.get_nvds_LayerInfo(tensor_meta, 0)
                ptr = ctypes.cast(pyds.get_ptr(layer.buffer), ctypes.POINTER(ctypes.c_float))
                v = np.ctypeslib.as_array(ptr, shape=(1,128))
                v = v / np.linalg.norm(v)
                # print(v.shape)

                with np.load("embeddings-correct.npz") as embeddings:
                    best_distance = 2
                    for key, embedding in embeddings.items():
                        # print(f"key: {key}")
                        # print(f"embedding shape: {embedding.shape}")
                        distance = np.min(np.linalg.norm(embedding - v, axis=1))
                        # print(f"distance: {distance}")

                        if distance < 1 and distance < best_distance:
                            id_name_dic[str(obj_meta.object_id)] = key
                            best_distance = distance

                try:
                    l_user_meta=l_user_meta.next
                except StopIteration:
                    break

            if str(obj_meta.object_id) in id_name_dic.keys():
                obj_meta.text_params.display_text = id_name_dic[str(obj_meta.object_id)]

            try: 
                l_obj=l_obj.next
            except StopIteration:
                break

        # Acquiring a display meta object. The memory ownership remains in
        # the C code so downstream plugins can still access it. Otherwise
        # the garbage collector will claim it when this probe function exits.
        display_meta=pyds.nvds_acquire_display_meta_from_pool(batch_meta)
        display_meta.num_labels = 1
        py_nvosd_text_params = display_meta.text_params[0]
        # Setting display text to be shown on screen
        # Note that the pyds module allocates a buffer for the string, and the
        # memory will not be claimed by the garbage collector.
        # Reading the display_text field here will return the C address of the
        # allocated string. Use pyds.get_string() to get the string content.
        py_nvosd_text_params.display_text = "Frame Number={} Person_count={}".format(frame_number, obj_counter[PGIE_CLASS_ID_PERSON])

        # Now set the offsets where the string should appear
        py_nvosd_text_params.x_offset = 10
        py_nvosd_text_params.y_offset = 12

        # Font , font-color and font-size
        py_nvosd_text_params.font_params.font_name = "Serif"
        py_nvosd_text_params.font_params.font_size = 10
        # set(red, green, blue, alpha); set to White
        py_nvosd_text_params.font_params.font_color.set(1.0, 1.0, 1.0, 1.0)

        # Text background color
        py_nvosd_text_params.set_bg_clr = 1
        # set(red, green, blue, alpha); set to Black
        py_nvosd_text_params.text_bg_clr.set(0.0, 0.0, 0.0, 1.0)
        # Using pyds.get_string() to get display_text as string
        print(pyds.get_string(py_nvosd_text_params.display_text))
        pyds.nvds_add_display_meta_to_frame(frame_meta, display_meta)
        try:
            l_frame=l_frame.next
        except StopIteration:
            break
			
    return Gst.PadProbeReturn.OK


def cb_newpad(decodebin, decoder_src_pad, data):
    print("In cb_newpad\n")
    caps = decoder_src_pad.get_current_caps()
    gststruct = caps.get_structure(0)
    gstname = gststruct.get_name()
    source_bin = data
    features = caps.get_features(0)

    # Need to check if the pad created by the decodebin is for video and not
    # audio.
    print("gstname=", gstname)
    if(gstname.find("video") != -1):
        # Link the decodebin pad only if decodebin has picked nvidia
        # decoder plugin nvdec_*. We do this by checking if the pad caps contain
        # NVMM memory features.
        print("features=", features)
        if features.contains("memory:NVMM"):
            # Get the source bin ghost pad
            bin_ghost_pad=source_bin.get_static_pad("src")
            if not bin_ghost_pad.set_target(decoder_src_pad):
                sys.stderr.write("Failed to link decoder src pad to source bin ghost pad\n")
        else:
            sys.stderr.write(" Error: Decodebin did not pick nvidia decoder plugin.\n")


def decodebin_child_added(child_proxy, Object, name, user_data):
    print("Decodebin child added:", name, "\n")
    if(name.find("decodebin") != -1):
        Object.connect("child-added",decodebin_child_added,user_data)


def create_source_bin(index, uri):
    print("Creating source bin")

    # Create a source GstBin to abstract this bin's content from the rest of the
    # pipeline
    bin_name = "source-bin-%02d" %index
    print(bin_name)
    nbin = Gst.Bin.new(bin_name)
    if not nbin:
        sys.stderr.write(" Unable to create source bin \n")

    # Source element for reading from the uri.
    # We will use decodebin and let it figure out the container format of the
    # stream and the codec and plug the appropriate demux and decode plugins.
    uri_decode_bin = Gst.ElementFactory.make("uridecodebin", "uri-decode-bin")
    if not uri_decode_bin:
        sys.stderr.write(" Unable to create uri decode bin \n")
    # We set the input uri to the source element
    uri_decode_bin.set_property("uri", uri)
    # Connect to the "pad-added" signal of the decodebin which generates a
    # callback once a new pad for raw data has beed created by the decodebin
    uri_decode_bin.connect("pad-added", cb_newpad, nbin)
    uri_decode_bin.connect("child-added", decodebin_child_added, nbin)

    # We need to create a ghost pad for the source bin which will act as a proxy
    # for the video decoder src pad. The ghost pad will not have a target right
    # now. Once the decode bin creates the video decoder and generates the
    # cb_newpad callback, we will set the ghost pad target to the video decoder
    # src pad.
    Gst.Bin.add(nbin, uri_decode_bin)
    bin_pad = nbin.add_pad(Gst.GhostPad.new_no_target("src", Gst.PadDirection.SRC))
    if not bin_pad:
        sys.stderr.write(" Failed to add ghost pad in source bin \n")
        return None

    return nbin


def main(args):
    # Check input arguments
    if len(args) != 2:
        sys.stderr.write("usage: %s <v4l2-device-path>\n" % args[0])
        sys.exit(1)

    # Standard GStreamer initialization
    Gst.init(None)

    # Create gstreamer elements
    # Create Pipeline element that will form a connection of other elements
    print("Creating Pipeline \n ")
    pipeline = Gst.Pipeline()

    if not pipeline:
        sys.stderr.write(" Unable to create Pipeline \n")

    # # Source element for reading from the file
    # print("Creating Source \n ")
    # source = Gst.ElementFactory.make("v4l2src", "usb-cam-source")
    # if not source:
    #     sys.stderr.write(" Unable to create Source \n")

    # caps_v4l2src = Gst.ElementFactory.make("capsfilter", "v4l2src_caps")
    # if not caps_v4l2src:
    #     sys.stderr.write(" Unable to create v4l2src capsfilter \n")


    # print("Creating Video Converter \n")

    # # Adding videoconvert -> nvvideoconvert as not all
    # # raw formats are supported by nvvideoconvert;
    # # Say YUYV is unsupported - which is the common
    # # raw format for many logi usb cams
    # # In case we have a camera with raw format supported in
    # # nvvideoconvert, GStreamer plugins' capability negotiation
    # # shall be intelligent enough to reduce compute by
    # # videoconvert doing passthrough (TODO we need to confirm this)


    # # videoconvert to make sure a superset of raw formats are supported
    # vidconvsrc = Gst.ElementFactory.make("videoconvert", "convertor_src1")
    # if not vidconvsrc:
    #     sys.stderr.write(" Unable to create videoconvert \n")

    # # nvvideoconvert to convert incoming raw buffers to NVMM Mem (NvBufSurface API)
    # nvvidconvsrc = Gst.ElementFactory.make("nvvideoconvert", "convertor_src2")
    # if not nvvidconvsrc:
    #     sys.stderr.write(" Unable to create Nvvideoconvert \n")

    # caps_vidconvsrc = Gst.ElementFactory.make("capsfilter", "nvmm_caps")
    # if not caps_vidconvsrc:
    #     sys.stderr.write(" Unable to create capsfilter \n")

    # Create nvstreammux instance to form batches from one or more sources.

    uri_name = args[1]
    print(f"uri name: {uri_name}")

    if uri_name.find("rtsp://") == 0 :
        is_live = True
    source_bin = create_source_bin(0, uri_name)

    if not source_bin:
        sys.stderr.write("Unable to create source bin \n")

    streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
    if not streammux:
        sys.stderr.write(" Unable to create NvStreamMux \n")

    # Use nvinfer to run inferencing on camera's output,
    # behaviour of inferencing is set through config file
    pgie = Gst.ElementFactory.make("nvinfer", "primary-inference")
    if not pgie:
        sys.stderr.write(" Unable to create pgie \n")

    tracker = Gst.ElementFactory.make("nvtracker", "tracker")
    if not tracker:
        sys.stderr.write(" Unable to create tracker \n")

    sgie1 = Gst.ElementFactory.make("nvinfer", "secondary1-nvinference-engine")
    if not sgie1:
        sys.stderr.write(" Unable to make sgie1 \n")

    # Use convertor to convert from NV12 to RGBA as required by nvosd
    nvvidconv = Gst.ElementFactory.make("nvvideoconvert", "convertor")
    if not nvvidconv:
        sys.stderr.write(" Unable to create nvvidconv \n")

    # Create OSD to draw on the converted RGBA buffer
    nvosd = Gst.ElementFactory.make("nvdsosd", "onscreendisplay")

    if not nvosd:
        sys.stderr.write(" Unable to create nvosd \n")


    nvvidconv_postosd = Gst.ElementFactory.make("nvvideoconvert", "convertor_postosd")
    if not nvvidconv_postosd:
        sys.stderr.write(" Unable to create nvvidconv_postosd \n")
    
    # Create a caps filter
    caps = Gst.ElementFactory.make("capsfilter", "filter")
    caps.set_property("caps", Gst.Caps.from_string("video/x-raw, format=I420"))
    
    # Make the encoder
    if codec == "H264":
        encoder = Gst.ElementFactory.make("x264enc", "encoder")
        print("Creating H264 Encoder")
    elif codec == "H265":
        encoder = Gst.ElementFactory.make("x265enc", "encoder")
        print("Creating H265 Encoder")
    if not encoder:
        sys.stderr.write(" Unable to create encoder")

    encoder.set_property("speed-preset", "veryfast")
    encoder.set_property("tune", "zerolatency")
    encoder.set_property("byte-stream", True)
    encoder.set_property("bitrate", 4096)
    encoder.set_property("sliced-threads", True)

    # Make the payload-encode video into RTP packets
    if codec == "H264":
        rtppay = Gst.ElementFactory.make("rtph264pay", "rtppay")
        print("Creating H264 rtppay")
    elif codec == "H265":
        rtppay = Gst.ElementFactory.make("rtph265pay", "rtppay")
        print("Creating H265 rtppay")
    if not rtppay:
        sys.stderr.write(" Unable to create rtppay")
    
    # Make the UDP sink
    updsink_port_num = 5400
    sink = Gst.ElementFactory.make("udpsink", "udpsink")
    if not sink:
        sys.stderr.write(" Unable to create udpsink")
    
    sink.set_property('host', '224.224.255.255')
    sink.set_property('port', updsink_port_num)
    sink.set_property('async', False)
    sink.set_property('sync', 1)

    # # Finally render the osd output
    # if is_aarch64():
    #     print("Creating nv3dsink \n")
    #     sink = Gst.ElementFactory.make("nv3dsink", "nv3d-sink")
    #     if not sink:
    #         sys.stderr.write(" Unable to create nv3dsink \n")
    # else:
    #     print("Creating EGLSink \n")
    #     sink = Gst.ElementFactory.make("nveglglessink", "nvvideo-renderer")
    #     if not sink:
    #         sys.stderr.write(" Unable to create egl sink \n")

    # print("Playing cam %s " %args[1])
    # caps_v4l2src.set_property('caps', Gst.Caps.from_string("video/x-raw, framerate=30/1"))
    # caps_vidconvsrc.set_property('caps', Gst.Caps.from_string("video/x-raw(memory:NVMM)"))
    # source.set_property('device', args[1])
    streammux.set_property('width', 1920)
    streammux.set_property('height', 1080)
    streammux.set_property('batch-size', 1)
    streammux.set_property('batched-push-timeout', 4000000)
    pgie.set_property('config-file-path', "face_detect_pgie_config.txt")
    sgie1.set_property('config-file-path', "facenet_sgie_config.txt")

    #Set properties of tracker
    config = configparser.ConfigParser()
    config.read('tracker_config.txt')
    config.sections()

    for key in config['tracker']:
        if key == 'tracker-width' :
            tracker_width = config.getint('tracker', key)
            tracker.set_property('tracker-width', tracker_width)
        if key == 'tracker-height' :
            tracker_height = config.getint('tracker', key)
            tracker.set_property('tracker-height', tracker_height)
        if key == 'gpu-id' :
            tracker_gpu_id = config.getint('tracker', key)
            tracker.set_property('gpu_id', tracker_gpu_id)
        if key == 'll-lib-file' :
            tracker_ll_lib_file = config.get('tracker', key)
            tracker.set_property('ll-lib-file', tracker_ll_lib_file)
        if key == 'll-config-file' :
            tracker_ll_config_file = config.get('tracker', key)
            tracker.set_property('ll-config-file', tracker_ll_config_file)
    # Set sync = false to avoid late frame drops at the display-sink
    sink.set_property('sync', False)

    print("Adding elements to Pipeline \n")
    # pipeline.add(source)
    # pipeline.add(caps_v4l2src)
    # pipeline.add(vidconvsrc)
    # pipeline.add(nvvidconvsrc)
    # pipeline.add(caps_vidconvsrc)
    pipeline.add(source_bin)
    pipeline.add(streammux)
    pipeline.add(pgie)
    pipeline.add(tracker)
    pipeline.add(sgie1)
    pipeline.add(nvvidconv)
    pipeline.add(nvosd)
    pipeline.add(nvvidconv_postosd)
    pipeline.add(caps)
    pipeline.add(encoder)
    pipeline.add(rtppay)
    pipeline.add(sink)

    # we link the elements together
    # v4l2src -> nvvideoconvert -> mux -> 
    # nvinfer -> nvvideoconvert -> nvosd -> video-renderer
    print("Linking elements in the Pipeline \n")
    # source.link(caps_v4l2src)
    # caps_v4l2src.link(vidconvsrc)
    # vidconvsrc.link(nvvidconvsrc)
    # nvvidconvsrc.link(caps_vidconvsrc)

    sinkpad = streammux.get_request_pad("sink_0")
    if not sinkpad:
        sys.stderr.write(" Unable to get the sink pad of streammux \n")
    # srcpad = caps_vidconvsrc.get_static_pad("src")
    srcpad = source_bin.get_static_pad("src")
    if not srcpad:
        sys.stderr.write(" Unable to get source pad of sourcebin \n")
    srcpad.link(sinkpad)
    streammux.link(pgie)
    pgie.link(tracker)
    tracker.link(sgie1)
    sgie1.link(nvvidconv)
    nvvidconv.link(nvosd)
    nvosd.link(nvvidconv_postosd)
    nvvidconv_postosd.link(caps)
    caps.link(encoder)
    encoder.link(rtppay)
    rtppay.link(sink)

    # create an event loop and feed gstreamer bus mesages to it
    loop = GLib.MainLoop()
    bus = pipeline.get_bus()
    bus.add_signal_watch()
    bus.connect ("message", bus_call, loop)

    # Start streaming
    rtsp_port_num = 8554
    
    server = GstRtspServer.RTSPServer.new()
    server.props.service = "%d" % rtsp_port_num
    server.attach(None)
    
    factory = GstRtspServer.RTSPMediaFactory.new()
    factory.set_launch( "( udpsrc name=pay0 port=%d buffer-size=524288 caps=\"application/x-rtp, media=video, clock-rate=90000, encoding-name=(string)%s, payload=96 \" )" % (updsink_port_num, codec))
    factory.set_shared(True)
    server.get_mount_points().add_factory("/ds-test", factory)
    
    print("\n *** DeepStream: Launched RTSP Streaming at rtsp://localhost:%d/ds-test ***\n\n" % rtsp_port_num)

    # Lets add probe to get informed of the meta data generated, we add probe to
    # the sink pad of the osd element, since by that time, the buffer would have
    # had got all the metadata.
    osdsinkpad = nvosd.get_static_pad("sink")
    if not osdsinkpad:
        sys.stderr.write(" Unable to get sink pad of nvosd \n")

    osdsinkpad.add_probe(Gst.PadProbeType.BUFFER, osd_sink_pad_buffer_probe, 0)

    # start play back and listen to events
    print("Starting pipeline \n")
    pipeline.set_state(Gst.State.PLAYING)
    try:
        loop.run()
    except:
        pass
    # cleanup
    pipeline.set_state(Gst.State.NULL)

if __name__ == '__main__':
    sys.exit(main(sys.argv))