1 / 37

Agenda

Agenda. Presentation of ImageLab. Digital Library content-based retrieval. Computer Vision for robotic automation. Multimedia: video annotation. Medical Imaging. Video analysis for indoor/outdoor surveillance. Off-line Video analysis for telemetry a nd forensics.

lynley
Download Presentation

Agenda

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Agenda

  2. Presentation of ImageLab DigitalLibrary content-basedretrieval Computer Vision forroboticautomation Multimedia: video annotation MedicalImaging Video analysis for indoor/outdoor surveillance Off-line Video analysis fortelemetry and forensics People and vehicle surveillance Imagelab-Softech Lab of Computer Vision, Pattern Recognition and Multimedia Dipartimento di Ingegneria dell’Informazione Università di Modena e Reggio Emilia Italy http://imagelab.ing.unimore.it

  3. Imagelab: recentprojects in surveillance Projects: European International Italian & Regional With Companies • THIS Transport hubs intelligent surveillance EU JLS/CHIPS Project 2009-2010 • VIDI-Video: STREP VI FP EU  (VISOR VideosSurveillance Online Repository) 2007-2009 • BE SAFE NATO Science for Peace project 2007-2009 • Detection of infiltrated objects for security 2006-2008 Australian Council • Behave_Lib : Regione Emilia Romagna Tecnopolo Softech 2010-2013 • LAICARegione Emilia Romagna; 2005-2007 • FREE_SURF MIUR PRIN Project 2006-2008 • Building site surveillance: with Bridge-129 Italia 2009-2010 • Stopped Vehicles with Digitek Srl 2007-2008 • SmokeWave: with Bridge-129 Italia 2007-2010 • Sakbot for Traffic Analysis with Traficon 2004-2006 • Mobile surveillance with Sistemi Integrati 2007 • Domotica per disabili: posture detection FCRM 2004-2005

  4. AD-HOC: Appearance Driven Human tracking with Occlusion Handling

  5. Key aspects • Based on the SAKBOT system • Background estimation and updating • Shadow removal • Appearance based tracking • we aim at recovering a pixel based foreground mask, even during an occlusion • Recovering of missing parts from the background subtraction • Managing split and merge situations • Occlusion detection and classification • Classify the differences as real shape changes or occlusions

  6. Example1 (fromViSOR)

  7. Example 2 from PETS 2002

  8. Example 3

  9. Other experimental results Imagelab videos (available on ViSOR) PETS series

  10. Results on the PETS2006 dataset Working in real time at 10 fps!

  11. Posture classification

  12. Distributed surveillancewith non overlapping field of view

  13. Exploit the knowledgeabout the scene • To avoid all-to-all matches, the tracking system can exploit the knowledge about the scene • Preferential paths -> Pathnodes • Border line / exit zones • Physical constraints & Forbidden zones NVR • Temporal constraints

  14. Trackingwithpathnode A possiblepathbetweenCamera1 and Camera 4

  15. Pathnodesleadparticlediffusion

  16. Resultswith PF and pathnodes Single camera tracking: Multicamera tracking Recall=90.27% Recall=84.16% Precision=88.64% Precision=80.00%

  17. “VIP: Vision tool for comparing Images of People” Lantagne & al., Vision Interface 2003 Each extracted silhouette is segmented into significant region using the JSEG algorithm ( Y. Deng ,B.S. Manjunath: “Unsupervised segmentation of color-texture regions in images and video” ) Colour and texture descriptors are calculated for each region • The colour descriptor is a modified version of the descriptor • presented in Y. Deng et al.: “Efficient color representation for • Image retrieval”. • Basically an HSV histogram of the dominant colors. • The texture descriptor is based on D.K.Park et al.: “Efficient • Use of Local Edge Histogram Descriptor”. • Essentially this descriptor characterizes the edge density • inside a region according to different orientations ( 0°, 45°, • 90° and 135° ) • The similarity between two regions is the weighted sum of • the two descriptor similarities:

  18. To compare the regions inside two silhouette, a region matching scheme is used, involving a modified version of the IRM algorithm presented in J.Z. Wang et al, ”Simplicity: Semantics-sensitive integrated matching for picture libraries” . The IRM algorithm is simple and works as follows: 1) The first step is to calculate all of the similarities between all regions. 2) Similarities are sorted in decreasing order, the first one is selected, and areas of the respective pair of regions are compared. A weight, equal to the smallest percentage area between the two regions, is assigned to the similarity measure. 3) Then, the percentage area of the largest region is updated by removing the percentage area of the smallest region so that it can be matched again. The smallest region will not be matched anymore with any other region. 4) The process continues in decreasing order for all of the similarities. In the end the overall similarity between the two region sets is calculated as:

  19. ViSOR: Video Surveillance Online Repository

  20. The ViSOR video repository

  21. Aims of ViSOR • Gather and make freely available a repository of surveillance videos • Store metadata annotations, both manually provided as ground-truth and automatically generated by video surveillance tools and systems • Execute Online performance evaluation and comparison • Create an open forum to exchange, compare and discuss problems and results on video surveillance

  22. Different types of annotation • Structural Annotation: video size, authors, keywords,… • Base Annotation: ground-truth, with concepts referred to the whole video. Annotation tool: online! • GT Annotation: ground-truth, with a frame level annotation; concepts can be referred to the whole video, to a frame interval or to a single frame. Annotation tool: Viper-GT (offline) • Automatic Annotation: output of automatic systems shared by ViSOR users.

  23. Video corpus set: the 14 categories

  24. Outdoor multicamera Synchronizedviews

  25. Surveillanceofentrancedoorof a building • About 10h!

  26. Videosforsmoke detection with GT

  27. Videosforshadow detection • Already used from many researcher working on shadow detection • Some videos with GT A. Prati, I. Mikic, M.M. Trivedi, R. Cucchiara, "Detecting Moving Shadows: Algorithms and Evaluation" in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, n. 7, pp. 918-923, July, 2003

  28. Some statistics We need videos and annotations!

  29. Action recognition SIMULTANEOUS HMM action SEGMENTATION AND Recognition

  30. Probabilistic Action Classification • Classical approach: • Given a set of training videos containing an atomic action each (manually labelled) • Given a new video with a single action • … find the most likely action Dataset: "ActionsasSpace-TimeShapes (ICCV '05)." M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri

  31. Classical HMM Framework • Definition of a feature set • For each frame t, computation of the feature set Ot (observations) • Given a set of training observations O={O1…OT} for each action, training of an HMM (k) for each action k • Given a new set of observations O={O1…OT} • Find the model (k) which maximise P(k|O)

  32. A sample 17-dim feature set • Computed on the extracted blob after the foreground segmentation and people tracking:

  33. From the Rabiner tutorial

  34. Online action Recognition • Given a video with a sequence of actions • Which is the current action? Frame by frame action classification(online – Action recognition) • When does an action finish and the next one start? (offline – Action segmentation) R. Vezzani, M. Piccardi, R. Cucchiara, "An efficientBayesianframeworkfor on-line actionrecognition" in press on Proceedingsof the IEEE International Conference on Image Processing, Cairo, Egypt, November 7-11, 2009

  35. Main problem of this approach • I do not know when the action starts and when it finishes. • Using all the observations, the first action only is recognized • A possible solution: “brute force”. For each action, for each starting frame, for each ending frame, compute the model likelihood and select the maximum. UNFEASIBLE

  36. Our approach • Subsample of the starting frames (1 each 10) • Adoption of recursive formulas • Computation of the emission probability once for each model (Action) • Current frame as Ending frame • Maximum length of each action • The computational complexity is compliant with real time requirements

  37. Different length sequences • Sequences with different starting frame have different length • Unfair comparisons using the traditional HMM schema • The output of each HMM is normalized using the sequence length and a term related to the mean duration of the considered action • This allows to classify the current action and, at the same time, to perform an online action segmentation

More Related