*****************************************************************************
* Copyright (c) 2019 NVIDIA Corporation.  All rights reserved.
*
* NVIDIA Corporation and its licensors retain all intellectual property
* and proprietary rights in and to this software, related documentation
* and any modifications thereto.  Any use, reproduction, disclosure or
* distribution of this software and related documentation without an express
* license agreement from NVIDIA Corporation is strictly prohibited.
*****************************************************************************

Prequisites:

Please follow instructions in the apps/sample_apps/deepstream-app/README on how
to install the prequisites for Deepstream SDK, the DeepStream SDK itself and the
apps.

Pipeline:
filesrc -> jpegparse -> nvv4l2decoder -> nvstreammux -> nvinfer (segmentation)
nvsegvidsual -> nvmultistreamtiler -> (nvegltransform) -> nveglglessink

Compilation Steps:
  $ cd apps/deepstream-segmentation-test/
  $ make
  $ ./deepstream-segmentation-app <config_file> <file1> [file2] ... [fileN]

E.g. for semantic segmentation, it needs semantic model which can get 4 classes map,
including backgroud, car, person, bicycle.
"nvsegvidsual" plugin chooses 4 different colors for them and to display.
  $ ./deepstream-segmentation-app dstest_segmentation_config_semantic.txt sample_720p.mjpeg sample_720p.mjpeg

E.g. for industrial segmentation, it needs industrial model which can only get defective
area map.
  $ ./deepstream-segmentation-app dstest_segmentation_config_industrial.txt sample_industrial.jpg

Don't forget to change batch-size to match the number of input files.
