Getting started with TI Jacinto 7 Edge AI/Demos/Semantic Segmentation

Run the Semantic Segmentation app

Select the right camera device:

To select the camera device corresponding to the USC camera or CSI camera being used, run the following command:

ls -l /dev/v4l/by-path/

The above command will output something like the following:

lrwxrwxrwx 1 root root 12 Jun  1 19:28 platform-xhci-hcd.2.auto-usb-0:1.2:1.0-video-index0 -> ../../video0
lrwxrwxrwx 1 root root 12 Jun  1 19:28 platform-xhci-hcd.2.auto-usb-0:1.2:1.0-video-index1 -> ../../video1

In this case, a symbolic link to /dev/video1 is created for the USB camera driver (try both symbolic links if one does not work).

Run the demo:

/opt/edge_ai_apps/apps_cpp/bin/Release/app_sem
antic_segmentation \
--device /dev/video1 \
-m /opt/edge_ai_apps/models/segmentation/TVM-SS-569-fpnlite-aspp-regnetx400mf-ade20k32-384x384 \
-o output/segmentation_%d.jpg

The help will show you the flags options

[docker] root@j7-evm:/opt/edge_ai_apps/apps_cpp/build# /opt/edge_ai_apps/apps_cpp/bin/Release/app_semantic_segmentation --help 
 
# 
# /opt/edge_ai_apps/apps_cpp/bin/Release/app_semantic_segmentation PARAMETERS [OPTIONAL PARAMETERS]
# OPTIONS:
#  --model       |-m Path to the model directory.
#  [--input      |-i Source to gst pipeline camera or file.]
#  [--output     |-o Set gst pipeline output display or file.]
#  [--device     |-d Device name for camera input.]
#  [--index      |-u Start index for multiple file input output.]
#  [--frame      |-f Framerate of gstreamer pipeline for image input.]
#  [--no-curses  |-n Disable curses report.]
#  [--connector  |-c Connector id to select output display.]
#  [--log-level  |-l Logging level to enable. [0: DEBUG 1:INFO 2:WARN 3:ERROR]. Default is 2.
#  [--help       |-h]
# 
# 
# (c) Texas Instruments 2021
#

❯