1. Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker Laura Leal-Taix´e, Gerard Pons-Moll and Bodo Rosenhahn ICCV2011

2. Outline Goal Multiple people tracking Modeling social behavior Experimental results Conclusion

3. Goal People detection is not always correct. It is important to merge the detection results into right trajectoies.

4. Multiple people tracking divided in two steps – object detection – data association  form complete trajectories Build a graph with the nodes  pedestrian detections The matching problem is equivalent to minimum-cost network flow problem

5. Multiple people tracking,trajectory of k Find the that best explains the detection. 4 P(o i |T) is the likelihood.

6. Multiple people tracking trajectory T k have following dependencies – Constant velocity assumption find o i depends on o i-1,o i-2 – Grouping behavior – Avoidance term

7. Multiple people tracking Represent by Markov chain:

8. Multiple people tracking

9. Combine (1),(2),(3)

10. Multiple people tracking Three kinds of edges: – Link edges – Detection edges – Entrance and exit edges

11. Multiple people tracking Link edges The edges (e i, b j ) connect the end nodes e i with the beginning nodes b j in following frames,with cost C i,j and flag f i,j Flag =1 if o i and o j belong to T k,and ∆f≤F max 111

12. Multiple people tracking Detection edges The edges (b i, e i ) connect the beginning node b i and end node e i, with cost C i and flag f i

13. Modeling social behavior If a pedestrian doesn’t meet any obstacles, he will naturally follow a straight line. But the pedestrian will have some social behavior. Add Social Force Model (SFM)and Group behavior(GR) into the problem.

14. Modeling social behavior Social forces have three main terms: – The desire to maintain certain speed – The desire to keep away from others – The desire to reach a destination We focus on first two!

15. Modeling social behavior Constant velocity assumpion – When a person walk at a speed V at time t – We assume he will have speed V at time t+∆t

16. Modeling social behavior Avoidance term

17. Modeling social behavior From the training sequence in [22], we learn the probabilty of P g and P i [22] S. Pellegrini, A. Ess, K. Schindler, and L. van Gool. You’ll never walk alone: modeling social behavior for multi-target tracking. ICCV, 2009. 1, 2, 5, 7

18. Experimental results Blue=>DIST Greed=>with SDM Red=>SFM+GR

19. Experimental results

20. To show the importance of social behavior and the robustness of our algorithm at low frame rates, we track at 2.5fps (taking one every tenth frame).

21. Experimental results DA (detection accuracy) TA (tracking accuracy) DP (detection precision) TP (tracking precision)

22. Experimental results [28]use network flow [22]use social behavior [27] use social and grouping

23. Experimental results

24. Conclusion It is important to have social and group relation on tracking. This paper outperform on low fps than others and have high accuracies on miss detections,false alarms and noise.