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! 

Gstreamer pre-record element

Tired of trying to capture the right moment while recording? RidgeRun knows how important is the video content and we know some events happen only once in life. That is why we have introduced GStreamer Pre-record element. The pre-record element has been designed to pre-record both audio and video continuously on a FIFO. The FIFO time is configured and defines the amount of data you want to buffer, this way it will always keep the previous nth seconds before a recording event happens. Using pre-record with motion detection or other event activity sensor is a great way to see what happened right before an event occurs. For example, using pre-record in a car's video capture system along with an accelerometer allows the history right before an accident to be captured. Using pre-record with motion detection allows the changing scene to be included in the video allowing the sensitivity of the motion detection to be turned down and thus avoiding false MD triggers. Adding this feature to your produce with our pre-record element is as easy as just add a new element on your pipeline and that's it! For more information about the GStreamer Pre-record element visit: http://developer.ridgerun.com/wiki/index.php? title=GStreamer_pre-record_element

Tegra X1 - OV5647/IMX219 driver and six camera capture

Looking for a SoC able to handle 6 camera simultaneously?

Please check RidgeRun support on Tegra X1 and Gstreamer and let's your design and imagination fly: https://developer.ridgerun.com/wiki/index.php? title=Sony_IMX219_Linux_driver_for_Tegra_X1

https://developer.ridgerun.com/wiki/index.php? title=OmniVision_OV5647_Linux_driver_for_Tegra_X1

Tegra X1 camera drivers for Raspberry PI camera v2 (IMX219) and v1 (ov5647), TC358840 for 4K

Moving your raspberry pi project to a more powerful platform like Tegra X1? RidgeRun reduces your time to market offering add-on drivers ready to use on Tegra X1 for cameras like raspberry pi v2 (IMX219) and raspberry pi v1 (ov5647). These V4L2 drivers have been developed for latest Jetpack R24.2 and tested with gstreamer 1.9 allowing you to capture up to 8 Megapixels. For those products needing a HDMI input with 4K support we are also happy to announce our support to the J130 board created by Auvidea with 4K video support through the TC358840 chip from Toshiba. RidgeRun can also develop your custom driver for any camera chip, please contact us for more information. All this tested under a gstreamer environment ready to shine in your demo!

IMX219 Release notes and video

http://developer.ridgerun.com/wiki/index.php?title=Sony_IMX219_Linux_driver_for_Tegra_X1#Overview_Video

OV5647 Release notes
http://developer.ridgerun.com/wiki/index.php?title=OmniVision_OV5647_Linux_driver_for_Tegra_X1