micas06gua / car_detection_forza_horizon

Object detection of Forza Horizon 4 gameplay video

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

This application was developed to detect cars in Forza Horizon 4 gameplay video

Results of the the application using Yolo V4

Original video: https://www.youtube.com/watch?v=qPFYkgxRFBo

Darknet

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.

Yolo V4

license Tensorflow Versions Python Versions

You only look once (YOLO) is a family of one-stage object detectors that are fast and accurate.

Scaled-YOLOv4:

YOLOv4:

For more information see the Darknet project website.


A similar structure like the image below should be created, the darknet repository can be cloned using the link indicated above.

The Yolo V4 weights are available in the link below:

https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights



The files coco.names, yolov4.cfg and yolov4.weights need to be saved inside the darknet folder or in any other location and indicated in the python notebook car_detection.ipynb


Requirements:

  • Matplotlib pip install matplotlib
  • Numpy pip install numpy
  • OpenCV pip install opencv-python
  • Contrib pip install opencv-contrib-python
  • Darknet


In case of any questions, please contact me: edson.costa@hotmail.com

About

Object detection of Forza Horizon 4 gameplay video

License:MIT License


Languages

Language:Jupyter Notebook 100.0%