YOLOv8m-NLF Head Detection Open-Source Object Detection Model - Accurately Identify the Positions of Helmets and Heads in NFL Games

Home

Yolov8m Nlf Head Detection

Developed by keremberke

An object detection model based on YOLOv8m, specifically designed to detect helmets and head positions in NFL games.

Object Detection

TensorBoard

#American Football Helmet Detection #Multi-class Helmet Recognition #YOLOv8 Model

Downloads 305

Release Time : 1/29/2023

Model Overview

This model focuses on detecting helmets and head positions in American football games, supporting the recognition of various helmet states, including intact helmets, blurred helmets, partial helmets, etc.

Model Features

Multi-class Helmet Detection

Capable of recognizing various helmet states, including intact helmets, blurred helmets, difficult helmets, etc.

Based on YOLOv8 Architecture

Utilizes the advanced YOLOv8m architecture, providing efficient and accurate object detection capabilities.

Sports Scene Optimization

Specifically optimized for NFL game scenarios, adapting to complex sports environments.

Model Capabilities

Image Object Detection

Sports Scene Analysis

Helmet Position Recognition

Use Cases

Sports Analysis

Player Head Tracking

Used to track the head positions of players during games, assisting in analyzing player movements and collision situations.

Safety Monitoring

Detects players' helmet-wearing status, aiding in identifying potential safety risks.

🚀 keremberke/yolov8m-nlf-head-detection

This model is based on the YOLOv8 architecture, specifically designed for object detection tasks, especially for detecting heads in the NFL - related scenarios. It provides a practical solution for accurately identifying and classifying objects within images.

✨ Features

Object Detection: Capable of detecting various types of helmets in NFL scenarios, including blurred, difficult, partial, and sideline helmets.
Model Compatibility: Built on the Ultralytics library, ensuring compatibility with the latest YOLOv8 framework.

📦 Installation

To use this model, you need to install the ultralyticsplus library. You can install it using the following command:

pip install ultralyticsplus==0.0.24 ultralytics==8.0.23

💻 Usage Examples

Basic Usage

from ultralyticsplus import YOLO, render_result

# load model
model = YOLO('keremberke/yolov8m-nlf-head-detection')

# set model parameters
model.overrides['conf'] = 0.25  # NMS confidence threshold
model.overrides['iou'] = 0.45  # NMS IoU threshold
model.overrides['agnostic_nms'] = False  # NMS class-agnostic
model.overrides['max_det'] = 1000  # maximum number of detections per image

# set image
image = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model.predict(image)

# observe results
print(results[0].boxes)
render = render_result(model=model, image=image, result=results[0])
render.show()

📚 Documentation

Supported Labels

The model supports the following labels:

['Helmet', 'Helmet-Blurred', 'Helmet-Difficult', 'Helmet-Partial', 'Helmet-Sideline']

Model Index

Model Name: keremberke/yolov8m-nlf-head-detection
Task Type: Object Detection
Dataset: keremberke/nfl-object-detection (validation split)
Metrics:
- mAP@0.5(box): 0.28743

More Models

More models are available at: awesome-yolov8-models

Property	Details
Library Name	ultralytics
Library Version	8.0.23
Inference	false
Datasets	keremberke/nfl-object-detection
Model Name	keremberke/yolov8m-nlf-head-detection
Task Type	object-detection
Dataset Type	keremberke/nfl-object-detection
Dataset Name	nfl-object-detection
Dataset Split	validation
Metrics Type	precision
Metrics Value	0.28743
Metrics Name	mAP@0.5(box)

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご