Programming Study日本語

Disclosure: We earn a commission from Udemy when you buy a course through links on this page.

Computer Vision: OpenCV, Machine Learning and YOLO

Computer Vision: OpenCV, Machine Learning and YOLO

Udemy · English

About this course

Language
English
Category
Provider
Udemy
Data updated

AI-assisted narration and selected generated visual examples support the explanations and practical demonstrations. Build practical computer vision applications with Python while learning the machine learning concepts behind them. This course connects theory lessons with code demonstrations and downloadable practice packages, so you can move from an explanation on screen to code you can run, inspect and change on your own computer. Start with Python and Jupyter, then work with images using NumPy, OpenCV and Pillow. Explore image transformations, filtering, edge detection, segmentation and contours. These foundations help you understand the inputs and preprocessing steps used by later machine learning models. Move into image classification with scikit-learn and learn how to extract features, split data, evaluate predictions and investigate errors. Build an understanding of neural networks and convolutional neural networks, then use TensorFlow/Keras and PyTorch to connect the theory with working examples. Practice data augmentation and transfer learning with the datasets and models supplied for the exercises. Apply YOLO to object detection, object tracking, instance segmentation, image classification and human pose estimation. Explore oriented bounding boxes and open-vocabulary detection, compare YOLO with DETR and RT-DETR, and examine model export and CPU inference performance. The examples show both useful results and the practical limits of model predictions. Bring these skills together in applications such as a parking monitor, a traffic counter, a fitness repetition tracker and a document scanner. You will see how detections, tracking IDs, geometric rules and application logic combine to turn model output into a useful result. Streamlit examples introduce a simple interface for selected applications. The downloadable practice packages include notebooks or scripts, dependency instructions and the assets or mode…

Courses in the same category