This repository contains code for the blog post Deep Learning based Object Detection using YOLOv3 with OpenCV ( Python / C++ ).

Run the getModels.sh file from command line to download the needed model files

  sudo chmod a+x getModels.sh
  ./getModels.sh

Command line usage for object detection using YOLOv3

• Python

  • Using CPU

    • A single image:

    python3 object_detection_yolo.py --image=bird.jpg --device 'cpu'

    • A video file:

    python3 object_detection_yolo.py --video=run.mp4 --device 'cpu'

  • Using GPU

    • A single image:

    python3 object_detection_yolo.py --image=bird.jpg --device 'gpu'

    • A video file:

    python3 object_detection_yolo.py --video=run.mp4 --device 'gpu'

• C++:

  • Using CPU

    • A single image:

    ./build/object_detection_yolo --image=bird.jpg --device=cpu

    • A video file:

     ./build/object_detection_yolo --video=run.mp4 --device=cpu

  • Using GPU

    • A single image:

    ./build/object_detection_yolo --image=bird.jpg --device=gpu

    • A video file:

     ./build/object_detection_yolo --video=run.mp4 --device=gpu

• Using g++

g++ -ggdb pkg-config --cflags --libs /usr/local/Cellar/opencv3/3.4.2/lib/pkgconfig/opencv.pc object_detection_yolo.cpp -o object_detection_yolo.out

• Using CMake

  • On Unix systems

  mkdir build && cd build
  cmake ..
  cmake --build . --config Release
  cd ..

  • On Windows systems

  mkdir build
  cd build
  cmake -G "Visual Studio 16 2019" ..
  cmake --build . --config Release
  cd ..

Note: To run on Windows system, change syntax accordingly:

.\build\Release\object_detection_yolo --video=run.mp4 --device=gpu

Want to become an expert in AI? AI Courses by OpenCV is a great place to start.