Ocular-Parking-System-v2

Deep Learning Focused Parking Assistant System

Requirements and dependencies

Python3.7 and pip

# Python3
apt-get install python3.7-dev

# python3.7-pip
sudo apt-get install python3-pip
python3.7 -m pip install pip

Dependencies installation under pip package manager

# Pytorch
sudo -H python3 -m pip install torch==1.3.0+cpu torchvision==0.4.1+cpu -f https://download.pytorch.org/whl/torch_stable.html
# For GPU or other version: https://pytorch.org/get-started/locally/

# OpenCV-4.1.1.26
python3 -m pip install --user opencv-python

# folium-0.10.1
python3 -m pip install --user folium

# Detectron2-0.1.1
python3 -m pip install cython
python3 -m pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
python3 -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
# Or build from source: https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md

Inference

# Example:
python3 main.py --video videoplayback2.mp4

# CLI Arguments:
* '--video' : Filename of input video located at img_input directory
* '--model_detection' : Filename of weights associated with detection
* '--cfg_path' : Path to model cfg file relative to 'detectron2/model_zoo'

Results

• Parkable Region Calibration

• Inference

• Overall