Skip to content

Vehicle Detection application based on OpenCV, YOLOv3 and PyQt5 GUI - implementation in terms of Software Engineering course on AGH University of Science and Technology

License

Notifications You must be signed in to change notification settings

Smendowski/vehicle-detection

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

73 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Vehicle Detection

  1. Description.
  2. Features
  3. Technologies used
  4. Installation
  5. Screen shots
  6. License

1. Description

A cross-platform application made as part of the project from software engineering on AGH University of Science and Technology.

2. Features and functionality

  • Detection
  • Categorization
  • Possibility to run on different models
  • Frame skipping & interpolation

3. Technologies used

3. Installation

PowerShell is highly recommended. No other legacy environments are supported Linux is also not supported.
Project developed under Python 3.8.6

For dummies

Just run build.ps1
If you are not allowed to run scripts type the following command Set-ExecutionPolicy RemoteSigned -Scope CurrentUser
Activate virtual enviroment .\<envName>\Scripts\activate.
Run app by typing python .\src\main.py (path must be relative).

For geeks

Virtualenv

  1. Get virtualenv using pip3 install virtualenv
  2. cd <project-directory>
  3. virtualenv <envName>
  4. .\<envName>\Scripts\activate
  5. Install all required modules using pip3 install -r requirements.txt
  6. Run app by typing python .\src\main.py

Here you go -> make sure to always run venv when doing the project
Hint: Set the Python interpreter in VSCode or PyCharm


Pipenv - Python packaging tool - an alternative to virtualenv

  1. Activate Pipenv environment: pipenv shell
  2. Install packages: pipenv install
  3. Run app by typing python ./src/main.py

Weights - download and place in the "model" directory


Configure libVLC and FFmpeg

libVLC is required for internal video player. FFmpeg is required for interpolating video.

  1. Download latest VLC 3.0.11.
  2. Extract libvlc.dll and copy it into the dlls folder. dlls folder must be in main directory.
  3. Install FFmpeg choco install ffmpeg
    3.1 Alternatively download latest build from here and add ffmpeg.exe and ffprobe.exe to the $Path
    $env:Path += ";<path_to_ffmpeg>".

4. Screen shots

Start Screen Start Screen - ComboBox Start Screen after processing Video tab Logs tab Stats tab

5. Creators

Smendowski Mateusz, Śladowski Piotr, Twardosz Adam

6. License

License: MIT

About

Vehicle Detection application based on OpenCV, YOLOv3 and PyQt5 GUI - implementation in terms of Software Engineering course on AGH University of Science and Technology

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 97.0%
  • PowerShell 3.0%