1 / 19

Tracking Groups of People for Video Surveillance

Tracking Groups of People for Video Surveillance. Xinzhen(Elaine) Wang Advisor: Dr.Longin Latecki. Agenda. Introduction Tracking Module Experimental results Conclusion. Introduction to tracking groups . Goal: Given a video sequence , track real groups of people present in the scene.

jania
Download Presentation

Tracking Groups of People for Video Surveillance

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. Tracking Groups of People for Video Surveillance Xinzhen(Elaine) Wang Advisor: Dr.Longin Latecki

  2. Agenda • Introduction • Tracking Module • Experimental results • Conclusion

  3. Introduction to tracking groups • Goal: Given a video sequence , track real groups of people present in the scene. • Steps: I Motion detection II Tracking module III Interpretation module • ADVISOR: project overview

  4. Goal : Detect mobile objects in the scene and classify them into moving regions. Detection of moving regions Extraction of features Parameters: centre of gravity, position, height and width (calculate both in 2D and in 3D) Classification (labeling) of moving regions 8 classes of mobile objects (person, occluded person, group, crowd, metro train, scene object, noise, unknown) Motion detector

  5. Group Tracking • A real group: • A set of persons who are close to each other. • A set of moving regions. • Four particularities: • Size coherence: each moving region of a group has the dimensions of a person or bigger if several persons partially overlap each other. • Spatial coherence: all moving regions inside a group are close to each other.

  6. Characteristics (conti): • Temporal coherence: the speed of the moving regions inside a group cannot exceed the speed of a person. • Structure coherence: The number and the size of moving regions inside a group should be stable.

  7. Steps in tracking algorithm • Tracking moving regions from frame to frame. • Computing inside the sub-graph all possible paths • Compute the group structure that gathers all these paths

  8. Frame to Frame Tracker • Goal: • Link from frame to frame all moving regions computed by the motion detector. • A link: • The link between Mnew and Mold is computed depending on their 2D and 3D distance and the similitude between their bounding box sizes. • Split: one Mold linked to several Mnew • Merge: several Mold linked to one Mnew.

  9. O contains old moving regions, all those detected at tc – 1 and also those did not get linked at the previous q frames Frame to Frame Tracker • N contains new moving regions detected at time tc • F computes the links between O and N • G computes the links between N and O

  10. Goal : Select trajectories of moving regions that can correspond to real persons inside a group during a temporal window. Size coefficient: Computing Paths • If the size coefficient is bigger than the size of a person, then the path is likely to corresponding to a real person inside a group. • To rank the paths

  11. Creation of Paths

  12. Update of Paths: If Mlast is the last moving region added in and is linked to the moving region Mnew detected in the new frame, is duplicated in and extended with Mnew. If Mlast is not liked to any new moving region, the path is only duplicated. As a result, the rank of such a path decreases. Removing Paths Pi is totally overlapping Pj and the size of Pj is bigger. Pi does not belong to a group anymore Update and Removing

  13. Goal : Select the paths of a connected sub-graph of that best match with the trajectories of real persons. A group Gm is represented by its N paths Pm,k, Groups computing • Description: • Groups are computed with a delay T, which constitutes a temporal window [tc – T, tc] of size T. • In this window, first compute all possible future trajectories of moving regions detected at time tc – T • Select at time tc – T the moving regions best match a real group that would be observed from time tc – T to tc.

  14. Density of the group over time • Group quality coefficient (q.c.): • Instantaneous quality coefficient: • Proximity between Pm,best and Pm,k • Distance between Pm,best and Pm,k

  15. Group Operations: • Creation of Group • Selecting Nmaxpaths with biggest size coef, compute q.c. • Check if the q.c. is higher thank a threshold. • Update of Gm at tc - T • Adding, extending or removing the paths composing the group. • Remove all paths Pm,i too far from Pm,best • Select the remaining paths with best size coefficients • Recompute Pm,best and q.c. • Removing Groups • A group is removed if its quality coefficient is lower than a threshold.

  16. Experimental Results • Tested on several metro sequences • Longest sequence has more than 6500 frames • Red box: moving regions classified as PERSON • Green box: moving regions classified as GROUP • Blue box: moving regions tracked as a real group. • Main limitation: • An imperfect estimation of real group size due to errors in motion detection. • Over-estimation • Under-estimation

  17. Conclusions • Track correctly groups of people from beginning to end. • Future development: • Computation of group trajectory, speed and events inside the group in order to recognize abnormal behaviors.

  18. Thank You !

More Related