https://github.com/utkarsh251106/tracking-with-yolo
This project uses YOLOv8 and DeepSORT to detect and track children and adults in video streams. It assigns unique IDs, handles re-tracking after occlusions, and outputs an annotated video with labeled bounding boxes.
https://github.com/utkarsh251106/tracking-with-yolo
computer-vision deep-learning deepsort machine-learning numpy opencv python torch ultralytics yolov8
Last synced: 5 months ago
JSON representation
This project uses YOLOv8 and DeepSORT to detect and track children and adults in video streams. It assigns unique IDs, handles re-tracking after occlusions, and outputs an annotated video with labeled bounding boxes.
- Host: GitHub
- URL: https://github.com/utkarsh251106/tracking-with-yolo
- Owner: Utkarsh251106
- Created: 2024-09-08T17:30:23.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-20T21:45:29.000Z (over 1 year ago)
- Last Synced: 2025-04-05T21:16:40.941Z (about 1 year ago)
- Topics: computer-vision, deep-learning, deepsort, machine-learning, numpy, opencv, python, torch, ultralytics, yolov8
- Language: Jupyter Notebook
- Homepage:
- Size: 50.1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Description
Tracking with YOLO is an object detection and tracking project designed to track and count the number of children and adults in a video. The dataset was annotated using Roboflow. For the actual execution of the program, the OpenCV library is used to handle camera and image-related tasks, NumPy is used for various mathematical calculations, and Ultralytics' YOLOv8 is used for object detection. Finally, the Deep SORT algorithm is used for tracking and occlusion prevention purposes.
# How to run it?
### Step 1: Clone the Repository:
```bash
git clone https://github.com/Utkarsh251106/Tracking-with-YOLO
```
### Step 2: Create a conda environment:
```bash
conda create -n venv python=3.11.9 -y
conda activate venv
```
### Step 3: Install the requirements:
```bash
pip install -r requirements.txt
```
### Step 4: To run the code:
```bash
# Start the Jupyter Notebook environment using the command
jupyter notebook
```
### Step 5: Run your Code.ipynb file