Skip to content

lewisExternal/BillboardAdvertDetection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Billboard advert detection

As the adoption of augmented reality (AR) headsets proliferates, the ways in which consumers will experience content will change considerably, which means a radical shift away from the current state of billboard advertising.

This is to show how to create a computer vision model for applications such as ad-blocking in everyday life.

test_1 test_2 test_3

Read the Medium article here

Run Locally

Data collection and annotation

Change directory to the data sub directory and run the following.

docker compose up --build 

For the streamlit application to collect images, please navigate to:

http://localhost:8501/

To see label studio for the annotation of images, please navigate to:

http://localhost:8888/

Once finished be sure to run the following.

docker compose down

Train model

Change directory to the training sub directory and run the following.

docker compose up --build 

To see the training notebook, please navigate to:

http://localhost:8888/lab

Once finished be sure to run the following.

docker compose down

Requirements

Requires docker desktop

References

About

Create a computer vision model for applications such as ad-blocking in everyday life

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors