Object Detection using YOLO Model

Overview

This project showcases object detection using the YOLO (You Only Look Once) model in Python, utilizing the transformers library for integration and OpenCV for image processing. The YOLO model is a state-of-the-art algorithm for real-time object detection tasks.

Objective

The objective of this project is to demonstrate the implementation of object detection using the YOLO model, transformers library, and OpenCV. The provided Python script utilizes a pre-trained YOLO model (hustvl/yolos-tiny) for detecting objects in images.

Features

• Developed a Python script for object detection using the YOLO model.
• Utilized the transformers library for YOLO model integration.
• Incorporated image processing techniques with the PIL and OpenCV libraries.
• Integrated pre-trained YOLO model (hustvl/yolos-tiny) for object detection tasks.
• Processed input images and generated bounding boxes using the YolosImageProcessor.
• Demonstrated the detection results with bounding boxes overlaid on the original image using matplotlib.
• Successfully detected objects with high confidence levels (>90%) and displayed the results visually.

Installation

1. Clone this repository to your local machine.
2. Install the required dependencies/library.

Results

References

• Ultralytics GitHub Repository

Contributors

• Abhishek Yadav