DL Streamer Samples¶
Samples are simple applications that demonstrate how to use the DL Streamer. The samples are available in the <INSTALL_DIR>/data_processing/dl_streamer/samples
directory.
Samples separated into several categories
gst_launch command-line samples (samples construct GStreamer pipeline via gst-launch-1.0 command-line utility)
Action Recognition Sample - demonstrates action recognition via gvaactionrecognitionbin element
Face Detection And Classification Sample - constructs object detection and classification pipeline example with gvadetect and gvaclassify elements to detect faces and estimate age, gender, emotions and landmark points
Audio Event Detection Sample - constructs audio event detection pipeline example with gvaaudiodetect element and uses gvametaconvert, gvametapublish elements to convert audio event metadata with inference results into JSON format and to print on standard out
Vehicle and Pedestrian Tracking Sample - demonstrates object tracking via gvatrack element
Human Pose Estimation Sample - demonstrates human pose estimation with full-frame inference via gvaclassify element
Metadata Publishing Sample - demonstrates how gvametaconvert and gvametapublish elements are used for converting metadata with inference results into JSON format and publishing to file or Kafka/MQTT message bus
gvapython Sample - demostrates pipeline customization with gvapython element and application provided Python script for inference post-processing
C++ samples
Draw Face Attributes C++ Sample - constructs pipeline and sets “C” callback to access frame metadata and visualize inference results
Python samples
Draw Face Attributes Python Sample - constructs pipeline and sets Python callback to access frame metadata and visualize inference results
Benchmark
Benchmark Sample - measures overall performance of single-channel or multi-channel video analytics pipelines
How To Build And Run¶
Samples with C/C++ code provide build_and_run.sh
shell script to build application via cmake before execution.
Other samples (without C/C++ code) provide .sh script for constucting and executing gst-launch or Python command line.
DL Models¶
DL Streamer samples use pre-trained models from OpenVINO™ Toolkit Open Model Zoo
Before running samples, run script download_models.sh
once to download all models required for samples. The script located in samples
top folder.
Note
To install all necessary requirements for download_models.sh
script run this command:
pip3 install -r $INTEL_OPENVINO_DIR/deployment_tools/open_model_zoo/tools/downloader/requirements.in
Input video¶
First command-line parameter in DL Streamer samples specifies input video and supports
local video file
web camera device (ex.
/dev/video0
)RTSP camera (URL starting with
rtsp://
) or other streaming source (ex URL starting with`http:// <http://>`__
)
If command-line parameter not specified, most samples by default stream video example from predefined HTTPS link, so require internet conection.
Note
Most samples set property sync=false
in video sink element to disable real-time synchronization and run pipeline as fast as possible. Change to sync=true
to run pipeline with real-time speed.