Image Stitching for NVIDIA Jetson/Performance/Orin: Difference between revisions

Image Stitching for NVIDIA Jetson/Performance/Orin (view source)

Revision as of 18:15, 8 August 2024

362 bytes removed , 8 August

no edit summary

Carguedas

457

edits

@@ Line 383: / Line 383: @@
 </source>
-= Orin AGX =
+= AGX Orin =
 == Platform Setup ==
@@ Line 422: / Line 422: @@
 [[File:Latency4kstitcherorinagx.png|1000x500px|thumb|center|Latency on 3840x2160 images with and without jetson_clocks.sh]]
-== Pipeline structure ==
+= Orin NX =
-{{Review|I would move this section before the sections talking about performance}}
+== Framerate ==
-{{Review|Also, you can put the 3 pipelines used for 2, 3 and 6 inputs}}
+=== 1920x1080 ===
+The next graph shows the amount of fps for each setup of inputs with and without jetson clocks.
+=== 4K ===
+The next graph shows the amount of fps for each setup of inputs with and without jetson clocks.
+== Latency ==
+Following the same structure for latency in the AGX Orin, the pictures below show the latency of the ''cuda-stitcher'' element, for multiple input images and multiple resolutions, as well as using and not using the ''jetson_clocks'' script.
-To replicate the results using your images, videos, or cameras, you can use the following pipeline as a base for the case of 2 cameras, then you can add the other inputs for the other cases. Also, you can adjust the resolution if needed.
-<source lang=bash>
-INPUT_0=<VIDEO_INPUT_0>
-INPUT_1=<VIDEO_INPUT_1>
-gst-launch-1.0 -e cudastitcher name=stitcher \
-homography-list="`cat homographies.json | tr -d "\n" | tr -d " "`" \
-filesrc location=$INPUT_0 ! qtdemux ! h264parse ! nvv4l2decoder ! queue ! nvvidconv !  stitcher.sink_0 \
-filesrc location=$INPUT_1 ! qtdemux ! h264parse ! nvv4l2decoder ! queue ! nvvidconv ! stitcher.sink_1 \
-stitcher. ! perf print-cpu-load=true ! fakesink -v
-</source>
 = Jetson Orin Platforms CPU Usage =