NVIDIA Jetson Orin - GstInference Integrating deep learning inference into GStreamer

NVIDIA®Jetson AGX Orin™
Introduction
SoM Overview Carrier Boards NVIDIA developer kit Auvidea X230D Connect Tech Forge Software Development Support
JetPack 5.0.2
Getting Started Installing JetPack Flashing the board with GUI installer JetPack Components Compiling Source Code Flashing the Board from Cmdline Performance Tuning Evaluating Performance Set Values Manually Tuning Power Maximizing Performance Software Encoders For Jetson Orin Nano
Development in the Board
Getting into the Board Using Serial Console Using SSH Using Ubuntu Login Installing Packages
Emulation
Flashing commands for emulation
Supported Cameras
IMX477+J20 Driver
GStreamer Pipelines
Capture and Display H264 H265
RidgeRun Products
GstPTZR GstCUDA GstColorTransfer GstWebRTC GstRtspSink GstInterpipe GstInference GstVPI GStreamer Daemon GstShark
RidgeRun Reference Designs
Panoramic Stitching and WebRTC Streaming
Reference Documentation
Contact Us

Overview

GstInference is an open-source project from RidgeRun Engineering that provides a framework for integrating deep learning inference into GStreamer. Either use one of the included elements to do out-of-the box inference using the most popular deep learning architectures or leverage the base classes and utilities to support your own custom architecture.

GstInference objective is to put inference in the hands of the developer without having to worry about frameworks, platforms, or media handling. It also has a strong focus on performance, which most Python frameworks don't really consider.

Supported frameworks:

• TensorFlow
• NCSDK

Provided plugins:

• TinyYOLO version 2 detection
• Inception version 2 classification
• Inception version 4 classification
• FaceNet face recognition
• Detection overlay for detection metadata visualization
• Classification overlay for classification metadata visualization
• Embedding overlay for embedding metadata visualization

Running inference on GStreamer pipelines

It is easy to add inference elements to an existing GStreamer pipeline. By combining inference and overlay elements you can perform deep learning tasks and then easily visualize the results.

Image classification

Error creating thumbnail: Unable to save thumbnail to destination

Classification overalay example

Object detection

Detection overalay example

Face recognition

Embedding overalay example

Getting Started

To know more about the extension please refer to the GstInference Introduction wiki page.

Contact Us

For technical questions or if you would like to know more information please send an email to support@ridgerun.com.