# Image Classification & Object Detection
###### tags: `黃仲璿` `2021/07/15`

## Image Classification
Image classification is a process of classifying what the image is __as a whole__. This will only output __one__ recognition result per image.

### Classifying a Single Image
`$ ./imagenet.py --network=<netname> <input filename> <output filename>`
ex.
`$ ./imagenet.py --network=resnet-18 images/jellyfish.jpg images/test/output_jellyfish.jpg`

Optional arguments:

--network <network name>
    # chose which network model to use
    # default is SSD-Mobilenet-v2
--threshold #value <a float between 0~1>
    # minimum threshold for detection confidence. Default is 0.5

### Live video Recognizing
`$ ./imagenet.py /dev/video0`
*Note: This doesn't work on remote desktop mode, has to be operated locally.*

## Object Detection with DetectNet
Object detection will dectect __multiple objects__ the network model can identify in one image, thus showing __multiple__ recognition results per image.

### Detect Objects from Images
`$ ./detectnet.py <input filename> <output filename>`
ex.
`$ ./detectnet.py --network=ssd-mobilenet-v2 images/peds_0.jpg images/test/output.jpg`

Optional arguments:

--network <network name>
    # chose which network model to use
    # default network is SSD-Mobilenet-v2
--overlay <flags seperated by ','>
    # select the way to present recognized objects.
    # default is --overlay=box, label, conf
    # box = box coloring; label = object name; conf = confidence
--threshold #value <a float between 0~1>
    # minimum threshold for detection confidence. Default is 0.5

#### Detectnet.py Source Code Notes
`argument`: The variables inserted after "./detectnet.py"
*Note: Arguments with `--` in front is optional*

`opt = parser.parse_known_args()[0]` : Getting all arguments
`output.Render(img)`: Put all overlay ontop of `img` then assign it to `output`

import jetson.inference
import jetson.utils

import argparse
import sys

# parse the command line
parser = argparse.ArgumentParser(description="Locate objects in a live camera stream using an object detection DNN.")

# argument = variables to insert after "./detectnet.py"
parser.add_argument("input_URI", type=str, default="", nargs='?', help="URI of the input stream")
parser.add_argument("output_URI", type=str, default="", nargs='?', help="URI of the output stream")
parser.add_argument("--network", type=str, default="ssd-mobilenet-v2", help="pre-trained model to load (see below for options)")
parser.add_argument("--overlay", type=str, default="box,labels,conf", help="detection overlay flags (e.g. --overlay=box,labels,conf)\nvalid combinations are:  'box', 'labels', 'conf', 'none'")
parser.add_argument("--threshold", type=float, default=0.5, help="minimum detection threshold to use") 

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

# load the object detection network
net = jetson.inference.detectNet(opt.network, sys.argv, opt.threshold)

# create video sources & outputs
input = jetson.utils.videoSource(opt.input_URI, argv=sys.argv)
output = jetson.utils.videoOutput(opt.output_URI, argv=sys.argv)

# process frames until the user exits
while True:
	# capture the next image
	img = input.Capture()

	# detect objects in the image (with overlay)
	detections = net.Detect(img, overlay=opt.overlay)

	# print the detections
	print("detected {:d} objects in image".format(len(detections)))

	for detection in detections:
		print(detection)

	# render the image
    # render = put all overlay ontop of original image then assign it to output
	output.Render(img)

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

	# print out performance info
	net.PrintProfilerTimes()

	# exit on input/output EOS
	if not input.IsStreaming() or not output.IsStreaming():
		break