GitXplorerGitXplorer
r

nfl_helmet_assignment

public
0 stars
0 forks
0 issues

Commits

List of commits on branch main.
Unverified
ac395a3d3011ad5020fb5e0d37835ffc58b44a4f

[Dev] Add YOLOv5 training to main.py

committed 3 years ago
Unverified
4615bf00d28f68b6c9c51cac48d5d72a108cc226

[Dev] Build dataset to YOLOv5 format

committed 3 years ago
Unverified
ce99cb1816c5d08fad9e890881c28e016103f5b6

[Fix] Update Makefile

committed 3 years ago
Unverified
7274901cba3765fde12d2ac919eac349126b369c

[Dev] Add command to setup the project easily

committed 3 years ago
Unverified
5b408250c790c2beb1f3e937cf8daf9145b818f3

[Fix] Update submodule configuration

committed 3 years ago
Unverified
e48b8466d307e2d6682ffdb25cb1f23dddd1a241

[Dev] Add yolov5 as a submodule

committed 3 years ago

README

The README file for this repository.

NFL Health & Safety - Helmet Assignment: Segment and label helmets in video footage

Project setup

One can setup the project with the following command (preferably in a virtual environment):

make setup_project

Helmet detection notebook

The notebook yolov5_helmet_detection.ipynb displays an application of YOLOv5 to helmet detection. Running the whole notebook will generate a video clip with inference results obtained on one of the test videos. This video clip can be viewed in the last cell of the notebook.

Be careful to specify well where you store Kaggle's data for this challenge (in the second code cell of the notebook).

Pipeline

The goal of this competition is to assign specific players to each helmet.

In order to do so, the targeted pipeline of this project is the following:

  1. Helmet detection with an object detection algorithm such as YOLOv5. There may be issues with sideline players' helmets.
  2. Helmet tracking so that several different instances do not switch with each other (SORT algorithm?). As there may be many players in a very small area, this can be challenging.
  3. Use the provided tracking data to identify players.