first commit

README

@@ -0,0 +1,51 @@
+################################################################################
+# Copyright (c) 2017-2021, 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.
+#
+################################################################################
+
+Refer to the DeepStream SDK documentation for a description of the plugin.
+--------------------------------------------------------------------------------
+Pre-requisites:
+- GStreamer-1.0 Development package
+- GStreamer-1.0 Base Plugins Development package
+- OpenCV Development package
+
+Install using:
+   sudo apt-get install libgstreamer-plugins-base1.0-dev libgstreamer1.0-dev \
+       libopencv-dev
+
+--------------------------------------------------------------------------------
+Compiling and installing the plugin:
+Export or set in Makefile the appropriate cuda version using CUDA_VER
+Run make and sudo make install
+
+NOTE: 
+1. To compile the sources, run make with "sudo" or root permission.
+2. This plugin contains additional optimized sample which supports batch processing
+of buffers. Refer to the Makefile for using optimized sample.
+3. OpenCV has been deprecated by default, so blur-objects will not work.
+   To enable OpenCV in dsexample, set `WITH_OPENCV=1` in the plugin Makefile
+   (/opt/nvidia/deepstream/deepstream/sources/gst-plugins/gst-dsexample/Makefile)
+   and follow compilation and installation instructions present in this README.
+
+--------------------------------------------------------------------------------
+Corresponding config file changes (Add the following section). GPU ID might need
+modification based on the GPU configuration:
+[ds-example]
+enable=1
+processing-width=640
+processing-height=480
+full-frame=0
+#batch-size for batch supported optimized plugin
+batch-size=1
+unique-id=15
+gpu-id=0
+blur-objects=0
+# Supported memory types for blur-objects are 1 and 3
+nvbuf-memory-type=3