CUDA Accelerated GStreamer Camera Undistort/Performance/Xavier: Difference between revisions
(Add latency measurements) |
m (Fix typo) |
||
Line 24: | Line 24: | ||
[[File:Undistort Xavier Performance FPS Multiple Resolutions.svg|none|frame|left|Undistort FPS on multiple resolution images using Fisheye model with and without jetson_clocks.sh ]] | [[File:Undistort Xavier Performance FPS Multiple Resolutions.svg|none|frame|left|Undistort FPS on multiple resolution images using Fisheye model with and without jetson_clocks.sh ]] | ||
[[File:Undistort Xavier Performance FPS Multiple Resolutions Brown Conrady.svg|none|frame|left|Undistort FPS on multiple resolution images using | [[File:Undistort Xavier Performance FPS Multiple Resolutions Brown Conrady.svg|none|frame|left|Undistort FPS on multiple resolution images using Brown-Conrady model with and without jetson_clocks.sh ]] | ||
===Pipeline structure=== | ===Pipeline structure=== |
Revision as of 17:56, 25 March 2021
CUDA Accelerated GStreamer Camera Undistort |
---|
Undistort Basics |
Getting Started |
User Guide |
Examples |
Performance |
Contact Us |
The performance of the cuda unidstort element depends mainly on the input image resolution.
The following sections show the measurements of the cuda-undistort (FPS and Latency) for multiple image resolutions; as well as the impact of changing the distortion model.
Platform Setup
The performance measurements were done with the AGX Xavier in 30W All mode, which can be activated with
sudo nvpmodel -m 3
The following sections show a comparison between using the platform at maximum frequency (With jetson_clocks) and in base mode. This mode can be set as follows:
sudo /usr/bin/jetson_clocks
Framerate
The average Frames per Second measurements are shown in the following charts, for multiple image resolutions. Also, the impact of executing or not the jetson_clocks script is shown in the results.
Pipeline structure
The general structure of the pipeline used for the framerate measurements is shown below, for the Fisheye model.
CAMERA_MATRIX="{\"fx\":9.5211633874478218e+02, \"fy\":9.4946222068253201e+02, \"cx\":6.8041416457132573e+02, \"cy\":3.1446117133659988e+02}" DISTORTION_PARAMETERS="{\"k1\":3.8939572818197948e-01, \"k2\":-5.5685725182648649e-01, \"k3\":2.3785352925072494e+00, \"k4\":-1.2037220289124213e+00}" INPUT=image_1.jpg gst-launch-1.0 \filesrc location=$INPUT \ ! nvjpegdec ! imagefreeze ! nvvidconv\ ! cudaundistort distortion-model=fisheye \ camera-matrix="$CAMERA_MATRIX" distortion-parameters="$DISTORTION_PARAMETERS" \ ! perf print-cpu-load=true ! fakesink
Latency
For the purpose of this performance evaluation, Latency is measured as the time difference between the src of the element before the undistort and the undistort src, effectively measuring the time between input and output pads.
The pictures below show the latency of the cuda-undistort element, for both models and multiple resolutions, as well as using and not using the jetson_clocks script.
Pipeline structure
The general structure of the pipeline used for the latency measurements is shown below, for the Fisheye model.
CAMERA_MATRIX="{\"fx\":9.5211633874478218e+02, \"fy\":9.4946222068253201e+02, \"cx\":6.8041416457132573e+02, \"cy\":3.1446117133659988e+02}" DISTORTION_PARAMETERS="{\"k1\":3.8939572818197948e-01, \"k2\":-5.5685725182648649e-01, \"k3\":2.3785352925072494e+00, \"k4\":-1.2037220289124213e+00}" INPUT=image_1.jpg GST_DEBUG="3,GST_TRACER:7" GST_TRACERS="interlatency" GST_SHARK_CTF_DISABLE=1 \ gst-launch-1.0 filesrc location=$INPUT \ ! nvjpegdec ! imagefreeze ! nvvidconv \ ! cudaundistort distortion-model=fisheye \ camera-matrix="$CAMERA_MATRIX" distortion-parameters="$DISTORTION_PARAMETERS" \ ! perf print-cpu-load=true ! fakesink