IMX6 RTSP stream latency: Difference between revisions
mNo edit summary |
mNo edit summary |
||
(4 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
<seo title="IMX6 RTSP Stream Latency | Nitrogen6X Board | RidgeRun Developer" titlemode="replace" keywords="GStreamer, Linux SDK, Linux BSP, Embedded Linux, Device Drivers, | <seo title="IMX6 RTSP Stream Latency | Nitrogen6X Board | RidgeRun Developer" titlemode="replace" keywords="GStreamer, Linux SDK, Linux BSP, Embedded Linux, Device Drivers, NVIDIA, Xilinx, TI, NXP, IMX6, IMX8, i.MX6, iMX6, iMX6 Nitrogen6X board, iMX6 Nitrogen6X, RTSP, Streaming over RTSP, RTSP Sink" description="Get to know the importance of latency measurement for iMX6 Nitrogen6X board while streaming over RTSP. Read about IMX6 RTSP stream latency at RidgeRun."></seo> | ||
= Introduction = | <table> | ||
<tr> | |||
<td><div class="clear; float:right">__TOC__</div></td> | |||
<td valign=center halign=center> | |||
{| | |||
| [[File:NXP Partner Program Registered Vertical.jpg|220px]] || [[File:NXP Partner Program Horizontal.jpg|500px]] | |||
|} | |||
</td> | |||
</table> | |||
== Introduction == | |||
This page summarizes the results after measuring the latency for an iMX6 Nitrogen6X board while streaming over RTSP. | This page summarizes the results after measuring the latency for an iMX6 Nitrogen6X board while streaming over RTSP. | ||
= Test setup = | == Test setup == | ||
* iMX6Q Nitrogen6Q2G board | * iMX6Q Nitrogen6Q2G board | ||
Line 13: | Line 23: | ||
* [https://boundarydevices.com/product/bd_hdmi_mipi/ Toshiba TC358743 HDMI-to-MIPICSI2 bridge] | * [https://boundarydevices.com/product/bd_hdmi_mipi/ Toshiba TC358743 HDMI-to-MIPICSI2 bridge] | ||
The test was performed using the [http://www.ridgerun.com/#!download-center/ggplf Nitrogen6X Eval SDK] built with | The test was performed using the [http://www.ridgerun.com/#!download-center/ggplf Nitrogen6X Eval SDK] built with Linaro HFP toolchain and using the [https://developer.ridgerun.com/wiki/index.php/RTSP_Sink RidgeRun RTSP Sink element]. A 1080p30 test video showing a timer was split into 2 outputs, one of the outputs was sent to an HDMI monitor (reference video) and the other one to the iMX6 HDMI capture module. | ||
The stream was played using a | The stream was played using a GStreamer pipeline on a regular PC, then a picture of the reference video and the captured stream was taken and the latency is calculated as the difference of the values in the 2 versions of the video. | ||
= 1080p30 (VPU 352MHZ) test results = | == 1080p30 (VPU 352MHZ) test results == | ||
These are the results of the test with the video running at 1080p30 and the VPU at 352MHz. In order to reproduce them run the following pipelines: | |||
== Target board pipeline == | === Target board pipeline === | ||
<pre> | <pre> | ||
Line 30: | Line 40: | ||
== PC (receiver) pipeline == | === PC (receiver) pipeline === | ||
<pre> | <pre> | ||
Line 39: | Line 49: | ||
</pre> | </pre> | ||
== Latency results == | === Latency results === | ||
* '''Max:''' 128ms | * '''Max:''' 128ms | ||
Line 45: | Line 55: | ||
* '''Average:''' 92ms | * '''Average:''' 92ms | ||
[[Category: RidgeRun RTSP Technology]][[Category: | {{ContactUs}} | ||
[[Category: RidgeRun RTSP Technology]][[Category: IMX6]][[Category: IMX8]] |
Latest revision as of 10:34, 25 November 2021
|
Introduction
This page summarizes the results after measuring the latency for an iMX6 Nitrogen6X board while streaming over RTSP.
Test setup
- iMX6Q Nitrogen6Q2G board
- iMX6 Eval SDK with RidgeRun RTSPSINK element
- Linaro HFP toolchain
- DVI Splitter
- Toshiba TC358743 HDMI-to-MIPICSI2 bridge
The test was performed using the Nitrogen6X Eval SDK built with Linaro HFP toolchain and using the RidgeRun RTSP Sink element. A 1080p30 test video showing a timer was split into 2 outputs, one of the outputs was sent to an HDMI monitor (reference video) and the other one to the iMX6 HDMI capture module. The stream was played using a GStreamer pipeline on a regular PC, then a picture of the reference video and the captured stream was taken and the latency is calculated as the difference of the values in the 2 versions of the video.
1080p30 (VPU 352MHZ) test results
These are the results of the test with the video running at 1080p30 and the VPU at 352MHz. In order to reproduce them run the following pipelines:
Target board pipeline
gst-launch-0.10 mfw_v4lsrc device=/dev/video0 capture-mode=5 fps-n=30 queue-size=7 ! gstperf ! queue ! \ vpuenc codec=6 gopsize=30 bitrate=10000000 seqheader-method=3 ! \ queue ! mpegtsmux ! capsfilter caps="video/mpegts,mapping=/stream1" ! \ queue ! rtspsink service="5000" name=sink -v
PC (receiver) pipeline
$TARGET_IP_ADDRESS=<your board ip address> gst-launch-1.0 -e -v rtspsrc location="rtsp://$TARGET_IP_ADDRESS:5000/stream1" ! \ rtpmp2tdepay ! queue ! tsdemux ! 'video/x-h264' ! h264parse ! queue ! \ decodebin ! xvimagesink sync=false
Latency results
- Max: 128ms
- Min: 63ms
- Average: 92ms
RidgeRun Resources | |||||
Contact Us
|