BackgroundNet Coding Explanation

Major Functionalities

For our background subtraction task, we use NVIDIA’s Python program called backgroundnet.py.: The program performs three major functions:

It manages input streams whether it is an image, a video or a camera.
It manages network inference on the said input stream.
It manages output stream along with overlaying results from the model.

With our python program, the user must specify

The input stream medium. (whether to input an image, a video or a camera)
Which model network to use for the inference.
The output stream medium. (whether to output an image, a video or a camera)

In our background_camera.ipynb, we first initialize the PATH for our input and output images.

We set up Jupyter environment variables with env as well as Python variables.

%env DISPLAY=:0
%env PROGRAM_PATH=/home/zeta/jetson-inference/build/aarch64/bin
%env INPUT_PATH=/home/zeta/jetson-inference/build/aarch64/bin/images
%env OUTPUT_PATH=/home/zeta/jetson-inference/build/aarch64/bin/images/test

input_path='/home/zeta/jetson-inference/build/aarch64/bin/images'
output_path='/home/zeta/jetson-inference/build/aarch64/bin/images/test'

By setting up environment variables, we can call upon these PATH variables, when we wish to run a shell command within our jupyter notebook.

After choosing and initializing the name of our input images we can see that the IMAGE_NAME variable is also being set to be an environment variable.
When we execute our python program (backgroundnet.py), we can see the three parameters the user has set up
```
!python3 $PROGRAM_PATH/backgroundnet.py --network=u2net $INPUT_PATH/$IMAGE_NAME $OUTPUT_PATH/$OUTPUT_NAME1
```
With !python3 $PROGRAM_PATH/backgroundnet.py as our activation function, we have:
1. --network=u2net: to specify which network we wished to use.
2. $INPUT_PATH/$IMAGE_NAME: to specify our input image location.
3. $OUTPUT_PATH/$OUTPUT_NAME: to specify our output image location.
Jupyter notebook allows us view images within our browser environment. For this we have used IPython library with display module.
```
from IPython.display import Image
```
- To view the images simply specify the location of the image. For example, to view the result of our inference:
```
Image(filename=output_path+'/background_remove.jpg')
```

Minor Functionalities

There are optional flags or parameters you may set up for your backgroundnet.py program. These parameters may control the replacement of the background.

There are 2 minor functionalities you may edit:

--network: This parameter allows us to choose which network we wish to use. (for this case, the default is “u2net”)
--replace: This parameter allows us to specify an image filename to use for background replacement.

For example, to replace the background with a specific image, you can use the following command:

!python3 $PROGRAM_PATH/backgroundnet.py --network=u2net --replace=$INPUT_PATH/Ulleung_0.jpg $INPUT_PATH/$IMAGE_NAME $OUTPUT_PATH/$OUTPUT_NAME2

In this command, the --replace=$INPUT_PATH/Ulleung_0.jpg parameter specifies the image to be used as the new background.