M6. Video Analysis

The objective of this module is to present the main concepts and technologies that are necessary for image sequence 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: mono-camera video sequences, multi-camera and depth camera sequences. Both theoretical bases and algorithms will be studied. Main subjects will be motion segmentation, background subtraction, motion estimation both in 2D and 3D, tracking algorithms and model-based analysis. Higher level techniques such as gesture or action recognition and video retrieval will also be studied. Students will work on a project on traffic monitoring where they will apply the concepts learned in the course.
Project title: 
Road traffic monitoring

The goal of this project is to learn the basic concepts and techniques related to video sequences processing, mainly for surveillance applications. We will focus on video sequences from outdoor scenarios, with the application of traffic monitoring in mind. The main techniques of video processing will be applied in the context of video surveillance: moving object segmentation, motion estimation and compensation and video object tracking are basic components of many video processing systems. In a first stage, moving object segmentation will be tackled considering scenarios with static camera. Afterwards, camera motion will be considered. Tracking of the moving objects can be performed in both scenarios. The tracking result provides high level information that can be analysed for traffic monitoring. The learning objectives for the students are the use of pixel based statistical models (such as mixture of gaussians) for modeling a scene background and for moving object segmentation, the development of optical flow estimation methods for camera motion compensation, and techniques for object tracking (ranging from simple blob analysis to more complex techniques based on filtering and probabilistic data association). The performance of the developed techniques will be measured using standard metrics for video analysis.

Module lectures: 

 

Academic Year 2018-2019         
Week Date Time Lecture Lecturer University Building Room
1 Tue. Feb.26th  16:00 - 18:00 Introduction to video analysis: classical techniques and deep learning  Montse Pardàs / Xavier Giró UPC    
1 Thu. Feb.28th 16:00 - 18:00 Video segmentation (I) Montse Pardàs UPC    
1 Thu. Feb.28th 18:00 - 19:00 Project Introduction

Javier Ruiz / Xavier Giró

UPC    
               
2 Tue. Mar.5th 16:00 -18:00 Video segmentation (II) Montse Pardàs UPC    
2 Thu. Mar.7th 16:00 -18:00 Motion estimation (I) Ramon Morros UPC    
2 Thu. Mar.7th 18:00 -19:00 Project follow-up

Javier Ruiz / Xavier Giró

UPC    
               
3 Tue. Mar.12th 16:00 -18:00 Motion estimation (II) Bayesian tracking (I) Ramon Morros UPC    
3 Thu. Mar.14th 16:00 -18:00 Bayessian tracking (II) Ramon Morros UPC    
3 Thu. Mar.14th 18:00 -19:00 Project follow-up

Javier Ruiz / Xavier Giró

UPC    
               
4 Tue. Mar.19th 16:00 -18:00 Tracking contours. Model based tracking. Montse Pardàs / Josep R. Casas UPC    
4 Thu. Mar.21st 16:00 -18:00 Object tracking and segmentation with Deep Learning. Deep Video Generation. Xavier Giró UPC    
4 Thu. Mar.21st 18:00 -19:00 Project follow-up

Javier Ruiz / Xavier Giró

UPC    
               
5 Tue. Mar.20th   HOMEWORK        
5 Thu. Mar.22nd   HOMEWORK        
               
               
               
6 Tue. Apr.2nd 16:00 -18:00  Recognition: Activity, pose and gestures. Classical techniques and deep learning. Javier Ruiz  UPC     
6 Thu. Apr.4th 16:00 -18:00 Learning from videos. Cross-modal deep learning.  Xavier Giró  UPC     
6 Thu. Apr.4th 18:00 -19:00 Project follow-up Javier Ruiz / Xavier Giró UPC    
               
7 Thu. Apr.11th 16:00 -19:00 Project presentations

Javier Ruiz / Xavier Giró

UPC    
               
      Easter Holidays (from Mar. 26th to Apr. 2nd)        
               
8 Tue. Apr.23rd   HOMEWORK        
8 Thu. Apr.25th   HOMEWORK        
               
9 Thu. May.2nd 16:00 -19:00 EXAM Montse Pardàs UPC    
               

M6 Student Guide [here]