segnet-camera.py

#!/usr/bin/python
#
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
#

import jetson.inference
import jetson.utils

import argparse
import ctypes
import sys

# parse the command line
parser = argparse.ArgumentParser(description="Segment a live camera stream using an semantic segmentation DNN.", 
						   formatter_class=argparse.RawTextHelpFormatter, epilog=jetson.inference.segNet.Usage())

parser.add_argument("--network", type=str, default="fcn-resnet18-voc", help="pre-trained model to load, see below for options")
parser.add_argument("--filter-mode", type=str, default="linear", choices=["point", "linear"], help="filtering mode used during visualization, options are:\n  'point' or 'linear' (default: 'linear')")
parser.add_argument("--ignore-class", type=str, default="void", help="optional name of class to ignore in the visualization results (default: 'void')")
parser.add_argument("--alpha", type=float, default=175.0, help="alpha blending value to use during overlay, between 0.0 and 255.0 (default: 175.0)")
parser.add_argument("--camera", type=str, default="0", help="index of the MIPI CSI camera to use (e.g. CSI camera 0)\nor for VL42 cameras, the /dev/video device to use.\nby default, MIPI CSI camera 0 will be used.")
parser.add_argument("--width", type=int, default=1280, help="desired width of camera stream (default is 1280 pixels)")
parser.add_argument("--height", type=int, default=720, help="desired height of camera stream (default is 720 pixels)")

try:
	opt = parser.parse_known_args()[0]
except:
	print("")
	parser.print_help()
	sys.exit(0)

# load the segmentation network
net = jetson.inference.segNet(opt.network, sys.argv)

# set the alpha blending value
net.SetOverlayAlpha(opt.alpha)

# the mask image is half the size
half_width = int(opt.width/2)
half_height = int(opt.height/2)

# allocate the output images for the overlay & mask
img_overlay = jetson.utils.cudaAllocMapped(opt.width * opt.height * 4 * ctypes.sizeof(ctypes.c_float))
img_mask = jetson.utils.cudaAllocMapped(half_width * half_height * 4 * ctypes.sizeof(ctypes.c_float))

# create the camera and display
camera = jetson.utils.gstCamera(opt.width, opt.height, opt.camera)
display = jetson.utils.glDisplay()

# process frames until user exits
while display.IsOpen():
	# capture the image
	img, width, height = camera.CaptureRGBA()

	# process the segmentation network
	net.Process(img, width, height, opt.ignore_class)

	# generate the overlay and mask
	net.Overlay(img_overlay, width, height, opt.filter_mode)
	net.Mask(img_mask, half_width, half_height, opt.filter_mode)

	# render the images
	display.BeginRender()
	display.Render(img_overlay, width, height)
	display.Render(img_mask, half_width, half_height, width)
	display.EndRender()

	# update the title bar
	display.SetTitle("{:s} | Network {:.0f} FPS".format(opt.network, net.GetNetworkFPS()))