RidgeRun - GStreamer Deep Learning inference plugin: GstInference

GstInference is an open-source project from RidgeRun Engineering that provides a framework for integrating deep learning inference into GStreamer.

Check out the presentation from RidgeRun Engineering team about our latest development on GstInference at Edinburg GStreamer Conference 2018.

GstInference: A GStreamer Deep Learning Framework : https://gstconf.ubicast.tv/videos/gstinference-a-gstreamer-deep-learning-framework/

RidgeRun developer wiki: http://developer.ridgerun.com/wiki/index.php?title=GstInference

For more information please contact us at support@ridgerun.com

Deploying Deep Learning on the Jetson Xavier using the Deep Learning Accelerator

jetson-inference is a training guide for inference and deep learning on Jetson platforms. It uses NVIDIA TensorRT for efficiently deploying neural networks.The "dev" branch on the repository is specifically oriented for Jetson Xavier since it uses the Deep Learning Accelerator (DLA) integration with TensorRT 5.

With jetson-inference you can deploy deep learning examples on the Xavier in a matter of minutes. Some of the example applications are showed below.

ImageNet is a classification network trained with a database of 1000 objects. The input is an image and it outputs the most likely class and the probability that the image belongs to that class.

Image recognition networks output a class probabilities corresponding to the entire input image. Detection networks, on the other hand, find where in the image those objects are located. DetectNet accepts an input image, and outputs the class and coordinates of the detected bounding boxes.

For more examples and a tutorial on how to get jetson-inference running in your Xavier please visit our jetson-inference wiki page.

If you are new to the Xavier or are planning on getting one please visit our Jetson Xavier wiki page.

RidgeRun support for The 2019 FIRST® Robotics Competition

RidgeRun support for The 2019 FIRST® Robotics Competition season.

RidgeRun believes supporting education is the right thing to do and because of this RidgeRun is proud to help the teams on the FIRST Robotics Competition [1] with software for embedded systems to improve the acquisition, processing and analysis of Audio and Video signals!

[1] https://www.firstinspires.org/robotics/frc

For more information please contact us at support@ridgerun.com

Object tracking in Jetson TX1/TX2 using GStPTZR

RidgeRun's new GStPTZR element allows to crop, zoom and rotate a video stream, simulating the behavior of a pan/tilt/zoom/rotate PTZR video camera.

These features, paired with information obtained from a jetson-inference pre-built model, can be used to provide a video stream focused on the detected object.

Captured video (left) is provided to a jetson-inferencce model. The model detects a person and provides the location. GstPTZR is used to crop the area of interest as a separate stream.

Using the GstPTZR element in an already-existing GStreamer pipeline is easy, and can provide a simple way to focus on the important parts of the video stream. 

Captured video (left) and the cropped version obtained with GStPTZR (right) that allow for detection of an object on a specific area of the video.

RidgeRun's GStPTZR is highly customizable and can be used for a wide variety of applications, both paired with detection models and other specific use cases.

For more information, visit www.ridgerun.com/gstptzr and contact us at support@ridgerun.com to request an evaluation version for your application.

The examples in the pictures above were created using models from the Jetson Inference guide.

GStreamer Conference Presentations

RidgeRun is back from the GStreamer Conference 2017.   See the presentations here

Building a media Server in under 30 minutes:
https://gstconf.ubicast.tv/videos/gstreamer-daemon-building-a-media-server-in-under-30-minutes/

GstShark profiling:
https://gstconf.ubicast.tv/videos/gstshark-profiling-a-real-life-example/

GstCUDA Pre-Release Announcement

RidgeRun is about to release a very exciting new GStreamer plug-in which will accelerate your CUDA development on Nvidia platforms TX1 and TX2

GstCUDA is a RidgeRun developed GStreamer plug-in enabling CUDA algorithm easy integration into GStreamer pipelines. GstCUDA offers a framework allowing users to develop custom elements executing different CUDA algorithms. The GstCUDA framework is a series of base classes abstracting the complexity of both CUDA and GStreamer. With GstCUDA, developers avoid writing elements from scratch, allowing the developer to focus on the algorithm logic, and accelerating time to market.

Lean more in our Developers Wiki

GStreamer Conference 2017

RidgeRun is happy to announce its participation in the GStreamer Conference 2017! RidgeRun will be presenting the following topics:

• GStreamer Daemon - building a media server in under 30 minutes
  
• GstShark profiling: a real-life example
• GstGPGPU - GstCUDA and GstOpenCL
• GStreamer and OpenCV using a GstOpenCV element

Please take the opportunity to chat with some of our engineers on Saturday and Sunday 21-22 October 2017 at node5 in Prague, Czech Republic!