The objective of this module is to present the main concepts and technologies that are necessary for video analysis. In the first place, we will present the applications of image sequence analysis and the different kind of data where these techniques will be applied, together with a general overview of the signal processing techniques and the general deep learning architectures in which video analysis is based. Examples will be given for mono-camera video sequences, multi-camera and depth camera sequences. Both theoretical bases and algorithms will be studied. For each subject, classical state of the art techniques will be presented, together with the deep learning techniques which lead to different approaches. Main subjects will be video segmentation, background subtraction, motion estimation, tracking algorithms and model-based analysis.
Higher level techniques such as gesture or action recognition, deep video generation and cross-modal deep learning will also be studied. Students will work on a project on road traffic monitoring applied to ADAS (Advanced Driver Assistance Systems) where they will apply the concepts learned in the course. The project will focus on video object detection and segmentation, optical flow estimation and multi-target / multi-camera tracking of vehicles.
Module Project: Road Traffic Monitoring
The aim of this project is to learn the basic concepts and techniques related to video sequences processing. A motion estimation, compensation and segmentation will be performed in video sequences in order to allow the tracking of different objects present in the scene. The project will be mainly focused on surveillance sequences with the application of traffic monitoring in mind.
M6 Schedule – Academic Year 2021-2022 – Student Guide <here>
M6 schedule will be released soon, the global academic year schedule is <here>