Skip to content

Real-time segmentation of dash cam videos. Pretrained computer vision models such as UNET and CANET are used to segment dash cam video.

License

Notifications You must be signed in to change notification settings

cksajil/dash-cam-segmenter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

84 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time segmentation of dash cam videos

Pretrained computer vision models such as UNET and CANET are used to segment dash cam video specifically on Indian roads.

Python Version

Python 3.9.1

Setting up virtual environment

# Installing Virtual Environment
python -m pip install --user virtualenv

# Creating New Virtual Environment
python -m venv envname

# Activating Virtual Environment
source envname/bin/activate

# Upgrade PIP
python -m pip install --upgrade pip

# Installing Packages
python -m pip install -r requirements.txt

How to run

python3 main.py --youtube "YouTube video URL"

python3 main.py --file <path_to_video_in_hard_disc>

# Example
python3 main.py --youtube "https://youtu.be/INcqJsGfBZU"

python3 main.py --file ./video/demo_video.mp4

Output

An output video like the following comparing original and segmented frames side by side will get generated in the video folder.

About

Real-time segmentation of dash cam videos. Pretrained computer vision models such as UNET and CANET are used to segment dash cam video.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages