Processing and analysis of visual and audio data

Lecturer(s): Mohsen ARDABILIAN, Emmanuel DELLANDREA
Course ⋅ 16 hStudy ⋅ 12 h

Objectives

The processing and analysis of visual and audio data are basic approaches in computer vision and audition. Based on Artificial Intelligence techniques, they are developed and applied with the aim of endowing machines with the ability to see, hear and acquire a high level understanding of the content of digital images, sound, and videos. From an engineering perspective, the goal is to automate the tasks that the human visual and auditory system can perform with applications in many fields: Art, Audiovisual, Machine Vision, Autonomous Vehicles, Medicine, Surveillance, Military , etc.

Palabras clave

Image analysis, video analysis, audio analysis, AI, feature, descriptor, shape, color, texture, classification, recognition, fusion, image processing, super resolution, Big Data

Programme

Content-based image and/or sound retrieval Assessment of image and sound analysis, and processing approaches Image processing algorithms, super resolution Audio processing algorithms End-to-end image and sound analysis algorithms

Learning Outcomes

  • To be able to apply the appropriate processing algorithms to a given context
  • To be able to apply the appropriate analysis algorithms to a given context
  • Evaluate algorithms or processing and analysis systems
  • Know the state-of-the-art processing and analysis algorithms, as well as their principles

Assesment

Final mark = 60% Knowledge + 40% Know-how Knowledge N1 = final exam Know-how N2 = continuous assessment