Week 2 - Visual Recognition: Computer Vision & AI
Week 2 - Visual Recognition: Computer Vision & AI
Modern Approaches to Visual Recognition
Course description
This course provides an introduction to Computer Vision, covering traditional methods based on geometry and the most recent ones based on artificial intelligence. The course explains how visual information can be represented in an image, processed and interpreted by computers, and how learning-based approaches have progressively transformed computer vision. Particular attention is devoted to deep learning methods, which today play a central role in many visual recognition tasks.
Total workload of the course: 5 hours
This MOOC is provided by Politecnico di Milano.
This MOOC was produced as part of the Edvance project – Digital Education Hub per la Cultura Digitale Avanzata. The project is funded by the European Union – Next Generation EU, Component 1, Investment 3.4 “Didattica e competenze universitarie avanzate".
Intended Learning Outcomes
If you actively participate in this course, you will achieve several expected learning outcomes:
- Explain how digital images are represented, acquired and processed by cameras and sensors
- Describe the basic principles used to recover 3D information from images, including stereo vision, point correspondences, triangulation and how 3D sensors operate
- Explain the main approaches to image classification and limitations of hand-crafted features
- Describe how deep learning and Convolutional Neural Networks learn visual features directly from annotated data
- Explain the role of training data, data augmentation, the basic principles behind transfer learning and the computing architectures that enabled the advent of deep learning
- Distinguish between different visual recognition tasks, including image classification, semantic segmentation, object detection and instance segmentation
- Describe the basic mechanism for generating images, namely generative neural networks and diffusion models
ESCO: computer vision ESCO: machine learning ESCO: deep learning ESCO: artificial neural networks ESCO: principles of artificial intelligence
Prerequisites
Basic mathematical knowledge and general familiarity with computing concepts.
Activities
Over and above consulting the content, in the form of videos and other web-based resources, you will have the opportunity to discuss course topics and to share ideas with your peers in the Forum of this MOOC. The forum of this MOOC is freely accessible, and participation is not guided; you can use it to compare yourself with other participants, or to discuss course contents with them.
Section outline
Assessment
Your final grade for the course will be based on the results of your answers to the assessed quizzes. You have an unlimited number of attempts at each quiz, but you must wait 15 minutes before you can try again. You will have successfully completed the course if you score 60% (or higher) in each one of the assessed quizzes. The maximum score possible for each quiz is given at the beginning of the quiz. You can view your score in the quiz on your last attempt or on the 'Grades' page.
Certificate
You can achieve a certificate in the form of an Open Badge for this course, if you reach at least 60% of the total score in each one of the assessed quizzes and fill in the final survey.
Once you have completed the required tasks, you will be able to access ‘Get the Open Badge’ and start issuing the badge. Instructions on how to access the badge will be sent to your e-mail address.
The Badge does not confer any academic credit, grade or degree.
Information about fees and access to materials
The course is delivered in online mode and is available free of charge.
Course faculty
Giacomo Boracchi
Teacher
Giacomo Boracchi is an Associate Professor of Computer Engineering at Dipartimento di Elettronica, Informazione e Bioingegneria of the Politecnico di Milano (DEIB). He received a Ph.D. in information technology (DEIB, 2008) and an MSc in Mathematics (Universitá Statale di Milano, 2004). His primary research interests concern machine/deep learning and image processing. In particular, his research contributions span change/anomaly detection, domain adaptation, learning in nonstationary environments, image restoration, and image analysis.
He has been the advisor of 14 PhD students and 100+ MSc students, as well as co-advisor of 10 PhD students and 4 visiting PhD students. He has been teaching computer vision and deep learning courses in both Politecnico di Milano, Università Bocconi, and Università della Svizzera Italiana (CH). He is the local coordinator of an EMJM double degree program on imaging. He leads multiple research projects on imaging or change/anomaly detection to design new industrial solutions. He has published more than 130 papers in international journals and conference proceedings.
Contact details
If you have any enquiries about the course or if you need technical assistance please contact pok@polimi.it. For further information, see FAQ page.