Spherical Video PTZ/Performance/Jetson AGX Xavier: Difference between revisions

From RidgeRun Developer Wiki
No edit summary
 
(15 intermediate revisions by 2 users not shown)
Line 18: Line 18:


As previously mentioned, the Spherical Video PTZ features an [[Spherical Video PTZ/User Guide/Quick_Start_Guide#Spherical_Video_PTZ_Engine|engine wrapper]], designed for application development. This section aims to conduct performance measurements using the average value obtained after processing the input image through the 'Process' method of the Spherical Video PTZ engine wrapper. The values presented in the table below are the averages obtained after using the Process method '''1000 times'''. This testing was conducted using the '''8 cores''' of the '''MODE_30W_ALL''' mode on a '''Jetson AGX Xavier''' with '''JetPack 5.1.2'''.
As previously mentioned, the Spherical Video PTZ features an [[Spherical Video PTZ/User Guide/Quick_Start_Guide#Spherical_Video_PTZ_Engine|engine wrapper]], designed for application development. This section aims to conduct performance measurements using the average value obtained after processing the input image through the 'Process' method of the Spherical Video PTZ engine wrapper. The values presented in the table below are the averages obtained after using the Process method '''1000 times'''. This testing was conducted using the '''8 cores''' of the '''MODE_30W_ALL''' mode on a '''Jetson AGX Xavier''' with '''JetPack 5.1.2'''.


{| class="wikitable sortable" style="text-align:center;"
{| class="wikitable sortable" style="text-align:center;"
Line 49: Line 48:
| 12 || CudaImage || Yes || 4000x2000 || 1000x1000 || (phys) 172.00 || (Usage) 5.70 % (VRAM) 11.00 MiB || 2.09 % || 19.471
| 12 || CudaImage || Yes || 4000x2000 || 1000x1000 || (phys) 172.00 || (Usage) 5.70 % (VRAM) 11.00 MiB || 2.09 % || 19.471
|}
|}


Please consider the following points:
Please consider the following points:
Line 59: Line 57:
===Gstreamer element: rrpanoramaptz===
===Gstreamer element: rrpanoramaptz===


====Processing using system memory====
====Processing time using system memory====
 
Each of the following sections presents the pipeline used for the performance test and the resulting performance graph, depicting the processing time without PTZ transformations for different video resolutions and output sizes.
 
'''2000x1000 input to 500x500 output'''


''Processing time without ptz transformations (2000x1000 - 500x500):''
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
[[File:9-perf.svg|thumbnail|center|640px|Element performance]]
''Resulting Graph:''
[[File:9-perf.svg|thumbnail|center|640px|Element performance|alt=Graphic with performance result]]


''Processing time without ptz transformations (4000x2000 - 500x500):''
'''4000x2000 input to 500x500 output'''
 
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
[[File:10-perf.svg|thumbnail|center|640px|Element performance]]
''Resulting Graph:''
[[File:10-perf.svg|thumbnail|center|640px|Element performance|alt=Graphic with performance result]]
 
'''4000x2000 input to 1000x1000 output'''


''Processing time without ptz transformations (4000x2000 - 1000x1000):''
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
[[File:11-perf.svg|thumbnail|center|640px|Element performance]]
''Resulting Graph:''
[[File:11-perf.svg|thumbnail|center|640px|Element performance|alt=Graphic with performance result]]
 
'''Summary'''
 
This table summarizes the average processing time for different resolutions:
{| class="wikitable sortable" style="text-align:center;"
|+ Average processing time for different resolutions
|-
! Resolution (Input – Output) !! Processing Average (ms)
|-
| 2000x1000 – 500x500 || 1.08256
|-
| 4000x2000 – 500x500 || 1.45138
|-
| 4000x2000 – 1000x1000 || 1.81266
|}
 
====Processing time with ptz transformations====
 
The bash script provided applies PTZ transformations to measure how they impact the processing time of the rrpanoramaptz element. The script sequentially applies a change in the pan position every 0.02 seconds, which introduces additional computational work for the processing element. This is reflected in the measured processing times, providing a realistic understanding of the element's performance under PTZ operations.
<syntaxhighlight lang="bash" line>
#!/bin/bash
 
counter=0
 
gst-client pipeline_create p1 "videotestsrc is-live=true num-buffers=200 ! queue ! video/x-raw,width=4000,height=2000 ! rrpanoramaptz name=ptz ! video/x-raw,width=1000,height=1000 ! fakesink"
 
gst-client pipeline_play p1
 
while [ $counter -lt 180 ]; do
    gst-client --quiet element_set p1 ptz pan ${counter}
    ((counter++))
    sleep 0.02 # pan rate of change
done
 
gst-client pipeline_stop p1
gst-client pipeline_delete p1
</syntaxhighlight>
 
''Resulting Graph:''
[[File:15-perf.svg|thumbnail|center|640px|Element performance]]
 
''Average processing time: 22.2574 ms''.
 
The graph shows fluctuations in processing time, which align with the moments when pan transformations are applied by the script


====Processing time using NVMM====
====Processing time using NVMM====


''Processing time without ptz transformations (2000x1000 - 500x500):''
'''2000x1000 input to 500x500 output'''
 
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
''Resulting Graph:''
[[File:12-perf.svg|thumbnail|center|640px|Element performance]]
[[File:12-perf.svg|thumbnail|center|640px|Element performance]]


''Processing time without ptz transformations (4000x2000 - 500x500):''
'''4000x2000 input to 500x500 output'''
 
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
''Resulting Graph:''
[[File:13-perf.svg|thumbnail|center|640px|Element performance]]
[[File:13-perf.svg|thumbnail|center|640px|Element performance]]


''Processing time without ptz transformations (4000x2000 - 1000x1000):''
'''4000x2000 input to 1000x1000 output'''
 
''Pipeline Used:''
<syntaxhighlight lang=bash>
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink
GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
''Resulting Graph:''
[[File:14-perf.svg|thumbnail|center|640px|Element performance]]
[[File:14-perf.svg|thumbnail|center|640px|Element performance]]


====Framerate:====
'''Summary'''
 
This table summarizes the average processing time for different resolutions:
{| class="wikitable sortable" style="text-align:center;"
|+ Average processing time for different resolutions
|-
! Resolution (Input – Output) !! Processing Average (ms)
|-
| 2000x1000 – 500x500 || 2.05170
|-
| 4000x2000 – 500x500 || 3.21540
|-
| 4000x2000 – 1000x1000 || 3.17019
|}
 
====Processing time with ptz transformations using NVMM====


''Framerate: 30 fps (2000x1000):''
The bash script provided applies PTZ transformations to measure how they impact the processing time of the rrpanoramaptz element. The script sequentially applies a change in the pan position every 0.02 seconds, which introduces additional computational work for the processing element. This is reflected in the measured processing times, providing a realistic understanding of the element's performance under PTZ operations.
<syntaxhighlight lang=bash>
<syntaxhighlight lang="bash" line>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="framerate" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! rrpanoramaptz ! "video/x-raw,width=2000,height=1000" ! fakesink
#!/bin/bash
</syntaxhighlight>
 
[[File:2-perf.png|thumbnail|center|640px|Element performance]]
counter=0
 
gst-client pipeline_create p1 "videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! video/x-raw(memory:NVMM),width=4000,height=2000 ! rrpanoramaptz name=ptz ! video/x-raw,width=1000,height=1000 ! fakesink"
 
gst-client pipeline_play p1
 
while [ $counter -lt 180 ]; do
    gst-client --quiet element_set p1 ptz pan ${counter}
    ((counter++))
    sleep 0.02 # pan rate of change
done


''Framerate: 30 fps (1000x500 - 2000x1000):''
gst-client pipeline_stop p1
<syntaxhighlight lang=bash>
gst-client pipeline_delete p1
GST_DEBUG="GST_TRACER:7" GST_TRACERS="framerate" gst-launch-1.0 videotestsrc is-live=true num-buffers=300 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=1000,height=500,framerate=30/1" ! rrpanoramaptz ! "video/x-raw,width=2000,height=1000,framerate=30/1" ! fakesink
</syntaxhighlight>
[[File:6-perf.png|thumbnail|center|640px|Element performance]]


''Framerate: 30 fps (2000x1000 - 1000x500):''
<syntaxhighlight lang=bash>
GST_DEBUG="GST_TRACER:7" GST_TRACERS="framerate" gst-launch-1.0 videotestsrc is-live=true num-buffers=300 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=1000,height=500,framerate=30/1" ! rrpanoramaptz ! "video/x-raw,width=2000,height=1000,framerate=30/1" ! fakesink
</syntaxhighlight>
</syntaxhighlight>
[[File:7-perf.png|thumbnail|center|640px|Element performance]]


''Framerate: 60 fps (2000x1000):''
''Resulting Graph:''
<syntaxhighlight lang=bash>
[[File:16-perf.svg|thumbnail|center|640px|Element performance]]
GST_DEBUG="GST_TRACER:7" GST_TRACERS="framerate" gst-launch-1.0 videotestsrc is-live=true num-buffers=300 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! rrpanoramaptz ! "video/x-raw,width=2000,height=1000,framerate=60/1" ! fakesink
</syntaxhighlight>
[[File:5-perf.png|thumbnail|center|640px|Element performance]]


''Average processing time: 15.7266 ms''.


The graph shows fluctuations in processing time, which align with the moments when pan transformations are applied by the script.


<noinclude>
<noinclude>
{{Spherical Video PTZ/Foot||Contact_Us}}
{{Spherical Video PTZ/Foot||Contact_Us}}
</noinclude>
</noinclude>

Latest revision as of 15:14, 2 October 2024


  Index Next: Contact_Us


Spherical Video PTZ
Getting Started
User Guide
Examples
Performance
Contact Us




Benchmark environment

The measurements are taken considering the following criteria:

  • Average behaviour: measurements considering typical image processing pipelines.

Instruments:

  • GPU: Jtop
  • CPU: RidgeRun Profiler
  • RAM: RidgeRun Profiler
  • Framerate: GstShark

Engine wrapper

As previously mentioned, the Spherical Video PTZ features an engine wrapper, designed for application development. This section aims to conduct performance measurements using the average value obtained after processing the input image through the 'Process' method of the Spherical Video PTZ engine wrapper. The values presented in the table below are the averages obtained after using the Process method 1000 times. This testing was conducted using the 8 cores of the MODE_30W_ALL mode on a Jetson AGX Xavier with JetPack 5.1.2.

Spherical Video PTZ performance
n Images type PTZ used Input size (px) Output size (px) RAM (MiB) GPU Avg CPU (%) Avg processing time (ms)
1 Image No 2000x1000 500x500 (phys) 120.00 (Usage) 1.18 % (VRAM) 6.00 MiB 10.47 % 6.845
2 Image No 4000x2000 500x500 (phys) 171.00 (Usage) 4.40 % (VRAM) 6.00 MiB 11.11 % 14.472
3 Image No 4000x2000 1000x1000 (phys) 174.00 (Usage) 5.10 % (VRAM) 7.00 MiB 10.92 % 14.738
4 Image Yes 2000x1000 500x500 (phys) 124.00 (Usage) 5.14 % (VRAM) 6.00 MiB 5.64 % 12.027
5 Image Yes 4000x2000 500x500 (phys) 179.00 (Usage) 6.30 % (VRAM) 6.00 MiB 7.24 % 22.648
6 Image Yes 4000x2000 1000x1000 (phys) 183.00 (Usage) 7.47 % (VRAM) 7.00 MiB 5.68 % 30.252
7 CudaImage No 2000x1000 500x500 (phys) 121.00 (Usage) 0.02 % (VRAM) 7.00 MiB 1.73 % 0.336
8 CudaImage No 4000x2000 500x500 (phys) 170.00 (Usage) 0.05 % (VRAM) 10.00 MiB 1.54 % 0.352
9 CudaImage No 4000x2000 1000x1000 (phys) 177.00 (Usage) 0.10 % (VRAM) 11.00 MiB 1.55 % 0.380
10 CudaImage Yes 2000x1000 500x500 (phys) 119.00 (Usage) 0.40 % (VRAM) 7.00 MiB 3.64 % 5.389
11 CudaImage Yes 4000x2000 500x500 (phys) 170.00 (Usage) 0.62 % (VRAM) 10.00 MiB 3.39 % 6.812
12 CudaImage Yes 4000x2000 1000x1000 (phys) 172.00 (Usage) 5.70 % (VRAM) 11.00 MiB 2.09 % 19.471

Please consider the following points:

  • Image Type: This refers to whether the input and output images use the lp/allocators/cudaimage.hpp library (images allocated in GPU memory) or the lp/image.hpp library (images allocated in CPU memory). In the results, it is evident that processing time is higher when using an Image compared to a CudaImage. This difference arises because although the engine wrapper accepts both types of images, when using an Image, the engine internally creates a copy of the CPU memory to perform operations on the GPU. This copying process consumes considerable time compared to using an image already allocated in GPU memory.
  • PTZ Usage: This indicates a change in the pan, tilt, or zoom property before processing the input image. Consequently, the engine wrapper executes an additional step to calculate the output image, leading to an increase in processing time.

Gstreamer element: rrpanoramaptz

Processing time using system memory

Each of the following sections presents the pipeline used for the performance test and the resulting performance graph, depicting the processing time without PTZ transformations for different video resolutions and output sizes.

2000x1000 input to 500x500 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink

Resulting Graph:

Graphic with performance result
Element performance

4000x2000 input to 500x500 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink

Resulting Graph:

Graphic with performance result
Element performance

4000x2000 input to 1000x1000 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! queue max-size-buffers=0 max-size-time=0 max-size-bytes=0 ! "video/x-raw,width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink

Resulting Graph:

Graphic with performance result
Element performance

Summary

This table summarizes the average processing time for different resolutions:

Average processing time for different resolutions
Resolution (Input – Output) Processing Average (ms)
2000x1000 – 500x500 1.08256
4000x2000 – 500x500 1.45138
4000x2000 – 1000x1000 1.81266

Processing time with ptz transformations

The bash script provided applies PTZ transformations to measure how they impact the processing time of the rrpanoramaptz element. The script sequentially applies a change in the pan position every 0.02 seconds, which introduces additional computational work for the processing element. This is reflected in the measured processing times, providing a realistic understanding of the element's performance under PTZ operations. 

#!/bin/bash

counter=0

gst-client pipeline_create p1 "videotestsrc is-live=true num-buffers=200 ! queue ! video/x-raw,width=4000,height=2000 ! rrpanoramaptz name=ptz ! video/x-raw,width=1000,height=1000 ! fakesink"

gst-client pipeline_play p1

while [ $counter -lt 180 ]; do
    gst-client --quiet element_set p1 ptz pan ${counter}
    ((counter++))
    sleep 0.02 # pan rate of change
done

gst-client pipeline_stop p1
gst-client pipeline_delete p1

Resulting Graph:

Element performance

Average processing time: 22.2574 ms.

The graph shows fluctuations in processing time, which align with the moments when pan transformations are applied by the script

Processing time using NVMM

2000x1000 input to 500x500 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=2000,height=1000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink

Resulting Graph:

Element performance

4000x2000 input to 500x500 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=500,height=500" ! fakesink

Resulting Graph:

Element performance

4000x2000 input to 1000x1000 output

Pipeline Used: 

GST_DEBUG="GST_TRACER:7" GST_TRACERS="proctime" gst-launch-1.0 videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! "video/x-raw(memory:NVMM),width=4000,height=2000" ! rrpanoramaptz ! "video/x-raw,width=1000,height=1000" ! fakesink

Resulting Graph:

Element performance

Summary

This table summarizes the average processing time for different resolutions:

Average processing time for different resolutions
Resolution (Input – Output) Processing Average (ms)
2000x1000 – 500x500 2.05170
4000x2000 – 500x500 3.21540
4000x2000 – 1000x1000 3.17019

Processing time with ptz transformations using NVMM

The bash script provided applies PTZ transformations to measure how they impact the processing time of the rrpanoramaptz element. The script sequentially applies a change in the pan position every 0.02 seconds, which introduces additional computational work for the processing element. This is reflected in the measured processing times, providing a realistic understanding of the element's performance under PTZ operations. 

#!/bin/bash

counter=0

gst-client pipeline_create p1 "videotestsrc is-live=true num-buffers=200 ! nvvidconv ! queue ! video/x-raw(memory:NVMM),width=4000,height=2000 ! rrpanoramaptz name=ptz ! video/x-raw,width=1000,height=1000 ! fakesink"

gst-client pipeline_play p1

while [ $counter -lt 180 ]; do
    gst-client --quiet element_set p1 ptz pan ${counter}
    ((counter++))
    sleep 0.02 # pan rate of change
done

gst-client pipeline_stop p1
gst-client pipeline_delete p1

Resulting Graph:

Element performance

Average processing time: 15.7266 ms.

The graph shows fluctuations in processing time, which align with the moments when pan transformations are applied by the script.



  Index Next: Contact_Us



Retrieved from "https://developer.ridgerun.com/wiki/index.php?title=Spherical_Video_PTZ/Performance/Jetson_AGX_Xavier&oldid=59536"