This page documents the following "Basic Inference Pipelines" consiting of
- CSI Source, Primary GIE, OSD, and 3D Window Sink
- File Source, Primary GIE, IOU Tracker, OSD, EGL Window Sink, and File Sink
- File Source, Primary GIE, IOU Tracker, OSD, EGL Window Sink, and RTSP Sink
- File Source, Primary GIE, IOU Tracker, OSD, EGL Window Sink, and V4L2 Sink
- File Source, Primary GIE, DCF Tracker, 2 Secondary GIEs, OSD, EGL Windon Sink
- RTSP Source, Primary GIE, IOU Tracker, OSD, EGL Window Sink
- HTTP Source, Primary GIE, IOU Tracker, OSD, EGL Window Sink
- File Source, Preprocessor, Primary GIE, IOU Tracker, OSD, EGL Window Sink
- File Source, Primary TIS, DSF Tracker, OSD, EGL Window Sink
- File Source, Primary TIS, IOU Tracker, OSD, EGL Window Sink
- File Source, Primary TIS, IOU Tracker, 2 Secondary TIS, OSD, EGL Window Sink
- Image Source, Primary GIE, OSD, and EGL Window Sink
- URI Source, Primary GIE, IOU Tracker, and App Sink
- V4L2 Source, Primary GIE, IOU Tracker, OSD, and EGL Window Sink
- App Source, Primary TIE, IOU Tracker, OSD, and EGL Window Sink
1csi_pgie_osd_3dsink.py- cpp example is still to be done
#
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - CSI Source
# - Primary GST Inference Engine (PGIE)
# - On-Screen Display
# - 3D Sink
# ...and how to add them to a new Pipeline and play.
#
# IMPORTANT! this examples uses a CSI Camera Source and 3D Sink - Jetson only!
##
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - File Source
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - On-Screen Display (OSD)
# - Window Sink
# - File Sink to encode and save the stream to file.
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# #
# This simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - A File Source
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# - RTSP Sink
# ...and how to add them to a new Pipeline and play.
#
# The example registers handler callback functions for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# #
# This simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - A File Source
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# - V4L2 Sink
# ...and how to add them to a new Pipeline and play.
#
# The V4L2 Sink is used to display video to v4l2 video devices.
#
# V4L2 Loopback can be used to create "virtual video devices". Normal (v4l2)
# applications will read these devices as if they were ordinary video devices.
# See: https://github.com/umlaeute/v4l2loopback for more information.
#
# You can install v4l2loopback with
# $ sudo apt-get install v4l2loopback-dkms
#
# Run the following to setup '/dev/video3'
# $ sudo modprobe v4l2loopback video_nr=3
#
# When the script is running, you can use the following GStreamer launch
# command to test the loopback
# $ gst-launch-1.0 v4l2src device=/dev/video3 ! videoconvert ! xvimagesink
#
# The example registers handler callback functions for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# #
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - File Source
# - Primary GST Inference Engine (PGIE)
# - DCF Tracker
# - 2 Secondary GST Inference Engines (SGIEs)
# - On-Screen Display (OSD)
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# #
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - RTSP Source
# - Primary GST Inference Engine (PGIE)
# - DCF Tracker
# - On-Screen Display (OSD)
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - error-message events
# - Pipeline change-of-state events
# - RTSP Source change-of-state events.
#
# IMPORTANT! The error-message-handler callback fucntion will stop the Pipeline
# and main-loop, and then exit. If the error condition is due to a camera
# connection failure, the application could choose to let the RTSP Source's
# connection manager periodically reattempt connection for some length of time.
#################################################################################
#
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - HTTP URI Source
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - On-Screen Display (OSD)
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - component-buffering messages
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
#
# IMPORTANT! The URI Source will send messages on the Pipeline bus when
# buffering is in progress. The buffering_message_handler callback is
# added to the Pipeline to be called with every buffer message received.
# The handler callback is required to pause the Pipeline while buffering
# is in progress.
#
# The callback is called with the percentage of buffering done, with
# 100% indicating that buffering is complete.
#
#################################################################################
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - URI Source
# - Preprocessor
# - Primary GIE
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# Specific services must be called for the PGIE to be able to receive tensor-meta
# buffers from the Preprocessor component.
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# 1file_ptis_dcf_tracker_osd_window.py- cpp example is still to be done
#
# The example demonstrates how to create a set of Pipeline components,
# specifically:
# - File Source
# - Primary Triton Inference Server (PTIS)
# - NcDCF Low Level Tracker
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# #
# The example demonstrates how to create a set of Pipeline components,
# specifically:
# - File Source
# - Primary Triton Inference Server (PTIS)
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# 1file_ptis_iou_tracker_2stis_osd_window.py- cpp example is still to be done
#
# The example demonstrates how to create a set of Pipeline components,
# specifically:
# - File Source
# - Primary Triton Inference Server (PTIS)
# - 2 Secondary Triton Inference Servers(STIS)
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# 1image_jpeg_pgie_osd_window.py- cpp example is still to be done
#
# The example demonstrates how to create a set of Pipeline components,
# specifically:
# - Image Source - single image to EOS
# - Primary GST Inference Engine (PGIE)
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
# - end-of-stream EOS events
# - Pipeline change-of-state events
# 1uri_file_pgie_iou_tracker_app_sink.py- cpp example is still to be done
#
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - URI Source
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - APP Sink
# ...and how to add them to a new Pipeline and play
#
# A "new_buffer_handler_cb" is added to the APP Sink to process the frame
# and object meta-data for each buffer received
##
# The simple example demonstrates how to create a set of Pipeline components,
# specifically:
# - V4L2 Source - Web Camera
# - Primary GST Inference Engine (PGIE)
# - IOU Tracker
# - On-Screen Display
# - Window Sink
# ...and how to add them to a new Pipeline and play
#
# The example registers handler callback functions with the Pipeline for:
# - key-release events
# - delete-window events
#
# The key-release handler function will update the V4L2 device picture settings
# based on the key value as follows during runtime.
# * brightness - or more correctly the black level.
# enter 'B' to increase, 'b' to decrease
# * contrast - color contrast setting or luma gain.
# enter 'C' to increase, 'c' to decrease
# * hue - color hue or color balence.
# enter 'H' to increase, 'h' to decrease
#
# The Picture Settings are all integer values, range - Python example is still to be done
raw_i420_app_src_ptis_tracker_osd_window.cpp
#
# This example illustrates how to push raw video buffers to a DSL Pipeline
# using an App Source component. The example application adds the following
# client handlers to control the input of raw buffers to the App Source
# * need_data_handler - called when the App Source needs data to process
# * enough_data_handler - called when the App Source has enough data to process
#
# The client handlers add/remove a callback function to read, map, and push data
# to the App Source called "read_and_push_data".
#
# The raw video file used with this example is created by executing the following
# gst-launch-1.0 command.
#
# gst-launch-1.0 uridecodebin \
# uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 \
# ! nvvideoconvert ! 'video/x-raw, format=I420, width=1280, height=720' \
# ! filesink location=./sample_720p.i420
#