setup:
• Hardware Platform:Jetson Xavier NX
• DeepStream Version: 6.1
• JetPack Version: 5.0.1 DP
• TensorRT Version: 8.4.0.11
• Issue Type( questions)
Hi folks, I run some Python script on my Jetson Xavier that captures the h264 stream and implements YOLO + tracker the display the stream on the screen (this pipeline work fine).
Now I add to the pipeline more elements my goal is to encode the new video with the annotation of Yolo and stream rtp UDP multicast stream. I don’t get any error but unfortunately, I don’t see RTP packets in the Wireshark I don’t understand what is the problem, In addition, I would be happy to understand what I need to add to my pipeline after I have the stream with the inference I want to resize to 704X576 and then send the video and not stream video size 640X640. I will be happy to help.
Here is my code:
#!/usr/bin/env python3
################################################################################
# SPDX-FileCopyrightText: Copyright (c) 2019-2021 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')
from gi.repository import GLib, Gst
from common.bus_call import bus_call
import pyds
fps_streams = {}
PGIE_CLASS_ID_PERSON = 4
PGIE_CLASS_ID_GAZEBO = 3
PGIE_CLASS_ID_TRUCK = 2
PGIE_CLASS_ID_PICKUP = 1
PGIE_CLASS_ID_CAR = 0
past_tracking_meta = [0]
# UDP Properties
PORT = 46002
MULTI_GROUP = "234.0.0.0"
PORT_SINK = 46003
MULTI_GROUP_SINK = "244.0.0.0"
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,
PGIE_CLASS_ID_GAZEBO:0,
PGIE_CLASS_ID_TRUCK:0,
PGIE_CLASS_ID_PICKUP:0,
PGIE_CLASS_ID_CAR: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
try:
l_obj = l_obj.next
except StopIteration:
break
try:
l_frame = l_frame.next
except StopIteration:
break
# past traking meta data
if (past_tracking_meta[0] == 1):
l_user = batch_meta.batch_user_meta_list
while l_user is not None:
try:
# Note that l_user.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.data)
except StopIteration:
break
if (user_meta and user_meta.base_meta.meta_type == pyds.NvDsMetaType.NVDS_TRACKER_PAST_FRAME_META):
try:
# Note that user_meta.user_meta_data needs a cast to pyds.NvDsPastFrameObjBatch
# The casting is done by pyds.NvDsPastFrameObjBatch.cast()
# The casting also keeps ownership of the underlying memory
# in the C code, so the Python garbage collector will leave
# it alone
pPastFrameObjBatch = pyds.NvDsPastFrameObjBatch.cast(user_meta.user_meta_data)
except StopIteration:
break
for trackobj in pyds.NvDsPastFrameObjBatch.list(pPastFrameObjBatch):
print("streamId=", trackobj.streamID)
print("surfaceStreamID=", trackobj.surfaceStreamID)
for pastframeobj in pyds.NvDsPastFrameObjStream.list(trackobj):
print("numobj=", pastframeobj.numObj)
print("uniqueId=", pastframeobj.uniqueId)
print("classId=", pastframeobj.classId)
print("objLabel=", pastframeobj.objLabel)
for objlist in pyds.NvDsPastFrameObjList.list(pastframeobj):
print('frameNum:', objlist.frameNum)
print('tBbox.left:', objlist.tBbox.left)
print('tBbox.width:', objlist.tBbox.width)
print('tBbox.top:', objlist.tBbox.top)
print('tBbox.right:', objlist.tBbox.height)
print('confidence:', objlist.confidence)
print('age:', objlist.age)
try:
l_user = l_user.next
except StopIteration:
break
return Gst.PadProbeReturn.OK
def main(args=1):
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("filesrc", "file-source")
source = Gst.ElementFactory.make("udpsrc", "UDP-source")
source.set_property("port", PORT)
source.set_property("multicast-group", MULTI_GROUP)
if not source:
sys.stderr.write(" Unable to create Source \n")
# Since the data format in the input file is elementary h264 stream,
# we need a h264parser
print("Creating H264Parser \n")
h264parser = Gst.ElementFactory.make("h264parse", "h264-parser")
# h264parser = Gst.ElementFactory.make("mpeg4videoparse", "mpeg4-parser")
if not h264parser:
sys.stderr.write(" Unable to create h264 parser \n")
# Use nvdec_h264 for hardware accelerated decode on GPU
print("Creating Decoder \n")
decoder = Gst.ElementFactory.make("nvv4l2decoder", "nvv4l2-decoder")
decoder.set_property('enable-max-performance', 1)
if not decoder:
sys.stderr.write(" Unable to create Nvv4l2 Decoder \n")
# Create nvstreammux instance to form batches from one or more sources.
streammux = Gst.ElementFactory.make("nvstreammux", "Stream-muxer")
if not streammux:
sys.stderr.write(" Unable to create NvStreamMux \n")
streammux.set_property('width', 640)
streammux.set_property('height', 640)
streammux.set_property('batch-size', 1)
streammux.set_property('batched-push-timeout', 40000)
streammux.set_property('live-source', 1)
streammux.set_property('compute-hw', 1)
# Use nvinfer to run inferencing on decoder'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")
# Set properties of pgie
pgie.set_property('config-file-path', "config_infer_primary_yoloV5.txt")
tracker = Gst.ElementFactory.make("nvtracker", "tracker")
if not tracker:
sys.stderr.write(" Unable to create tracker \n")
# 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)
if key == 'enable-batch-process':
tracker_enable_batch_process = config.getint('tracker', key)
tracker.set_property('enable_batch_process', tracker_enable_batch_process)
if key == 'enable-past-frame':
tracker_enable_past_frame = config.getint('tracker', key)
tracker.set_property('enable_past_frame', tracker_enable_past_frame)
if key == 'compute-hw':
tracker_enable_compute_hw = config.getint('tracker', key)
tracker.set_property('compute-hw', tracker_enable_compute_hw)
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")
# Add encoding and transmit udp stream
nvvidconv_postosd = Gst.ElementFactory.make("nvvideoconvert", "convertor_postosd")
# Convert to OCU format 704X576
# nvvidconv_postosd.set_property("width", 704)
# nvvidconv_postosd.set_property("height", 576)
# for rtp stream
caps = Gst.ElementFactory.make("capsfilter", "filter")
caps.set_property("caps", Gst.Caps.from_string(
"application/x-rtp, media=video, clock-rate=90000, encoding-name=(string)H264, payload=96"))
encoder = Gst.ElementFactory.make("nvv4l2h264enc", "encoder")
encoder.set_property('maxperf-enable', 1)
encoder.set_property('preset-level', 1)
encoder.set_property('insert-sps-pps', 1)
encoder.set_property('insert-vui', 1)
rtppay = Gst.ElementFactory.make("rtph264pay", "rtppay")
sink = Gst.ElementFactory.make("udpsink", "sink")
sink.set_property('port', PORT_SINK)
sink.set_property('auto-multicast', True)
sink.set_property('host', MULTI_GROUP_SINK)
# sink.set_property('sync', 1)
# sink.set_property('async', False)
print("Adding elements to Pipeline \n")
pipeline.add(source)
pipeline.add(h264parser)
pipeline.add(decoder)
pipeline.add(streammux)
pipeline.add(pgie)
pipeline.add(tracker)
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
# file-source -> h264-parser -> nvh264-decoder ->
# nvinfer -> nvvidconv -> nvosd -> video-renderer
print("Linking elements in the Pipeline \n")
source.link(h264parser)
h264parser.link(decoder)
sinkpad = streammux.get_request_pad("sink_0")
if not sinkpad:
sys.stderr.write(" Unable to get the sink pad of streammux \n")
srcpad = decoder.get_static_pad("src")
if not srcpad:
sys.stderr.write(" Unable to get source pad of decoder \n")
srcpad.link(sinkpad)
streammux.link(pgie)
pgie.link(tracker)
tracker.link(nvvidconv)
nvvidconv.link(nvosd)
nvosd.link(nvvidconv_postosd)
nvvidconv_postosd.link(caps)
caps.link(encoder)
encoder.link(rtppay)
rtppay.link(sink)
# create and 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)
# 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)
print("Starting pipeline \n")
# start play back and listed to event
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))
In addition I try replace caps with the property:
caps.set_property(
"caps", Gst.Caps.from_string("video/x-raw(memory:NVMM), format=I420"))
