Opleiding: Object Detection with YOLO: Computer Vision & AI with Python

In this hands-on course, you'll explore the core concepts of object detection, including bounding boxes, Intersection over Union (IoU), and mean Average Precision (mAP). You'll learn how YOLO works, how to use pre-trained models, and how to train your own models using annotated datasets. You'll also get hands-on experience with OpenCV for image processing and real-time detection. By the end of the day, you'll have a fully trained AI model ready to apply to your own data and projects built with Python.

What you'll learn

• Core principles of object detection and the difference from classification and segmentation.
• Working with YOLO and OpenCV.
• Annotating images and setting up datasets.
• Training custom YOLO models with Ultralytics and Roboflow.
• Evaluating model performance with IoU and mAP.

After this course you'll be able to:

• Train your own YOLO model and apply it to new images or videos.
• Create annotations and structure datasets for object detection.
• Integrate object detection into your own applications or data analysis pipelines.

Who is this for

• Data scientists and AI engineers.
• Developers looking to get hands-on with computer vision and object detection.
• Python developers interested in AI and image recognition.

Prerequisites

• Basic knowledge of Python is recommended.
• Some experience with machine learning or AI tools is a plus, but not required.

Programme

Part 1 – Introduction to Computer Vision and Object Detection

• The difference between classification, detection, and segmentation.

Part 2 – Core Concepts

• Bounding boxes, IoU, and mAP.
• Evaluating object detection models.

Part 3 – Working with YOLO and Ultralytics

• Using pre-trained models and model configurations.

Part 4 – Datasets and Annotations

• Annotating images, setting up datasets, and using Roboflow.

Part 5 – Training Your Own YOLO Model

• Training, validating, and optimising model performance.

Part 6 – OpenCV and Real-time Detection

• Image processing, video input, and live object detection.

Part 7 – Applying to Your Own Data

• Integration into projects, use cases, and Q&A.