M4. 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 2016-2017        
week date time lecture lecturer university building room
1 Tue. Dec. 13th 16:00 - 18:00 Introduction to video analysis and tracking. Motion segmentation  Montse Pardàs UPC  D5 Merit 010
1 Thu. Dec. 15th 16:00 - 18:00 Motion segmentation. Background subtraction Montse Pardàs UPC  D5 Merit 010
1 Thu. Dec. 15th 18:00 - 19:00 Project Introduction Javier Ruiz / Xavier Giró      
               
2 Tue. Dec. 20th 16:00 -18:00 Motion estimation. Optical flow Ramon Morros UPC  D5 Merit 010
2 Thu. Dec. 22nd 16:00 -18:00 Bayesian tracking (I) Ramon Morros UPC  D5 Merit 010
2 Thu. Dec. 22nd  18:00 - 19:00 Project follow-up  Javier Ruiz / Xavier Giró UPC  D5  Merit 010
               
      Christmas Holidays (from 23rd December to 8th January)        
               
3 Tue. Jan. 10th 16:00 - 18:00 Bayesian tracking (II) Ramon Morros UPC  D5 Merit 010
3 Thu. Jan. 12th 16:00 - 18:00 Model-based tracking  Josep Ramon Casas UPC   D5  Merit 010
3 Thu. Jan. 12th 18:00 - 19:00 Project follow-up Javier Ruiz / Xavier Giró UPC D5 Merit 010
               
4 Tue. Jan. 17th 16:00 -18:00 Gesture and action recognition Javier Ruiz UPC  D5 Merit 010
4 Thu. Jan. 19th 16:00 -18:00 Behaviour understanding in videos Jordi Gonzàlez UPC  D5 Merit 010
4 Thu. Jan. 19th 18:00 - 19:00 Project follow-up Javier Ruiz / Xavier Giró UPC  D5 Merit 010
               
5 Tue. Jan. 24th 16:00 -18:00 HOMEWORK        
5 Thu. Jan. 26th 16:00 -18:00 HOMEWORK        
               
6 Tue. Jan. 31st 16:00 -18:00  Video analysis with CNNs Xavier Giró UPC  D5 Merit 010
6 Thu. Feb. 2nd 16:00 -18:00 Video analysis with RNNs Xavier Giró  UPC  D5 Merit 010
6 Thu. Feb. 2nd   Project follow-up  Javier Ruiz / Xavier Giró UPC  D5 Merit 010
               
7 Tue. Feb. 7th   HOMEWORK        
7 Thu. Feb. 9th 16:00 -19:00 Project presentations Javier Ruiz / Xavier Giró UPC  D5 Merit 010
               
8 Tue. Feb. 14th   HOMEWORK        
8 Thu. Feb. 16th   HOMEWORK        
               
9 Thu. Feb. 23rd 16:00 -18:00 EXAM Montse Pardàs / Verónica Vilaplana UPC  D5 Merit 010
               

M4 Student Guide [here]