Object detection, tracking and event recognition: the ETISEO experience

25
Object detection, tracking and event recognition: the ETISEO experience Andrea Cavallaro Multimedia and Vision Lab Queen Mary, University of London [email protected]

description

Object detection, tracking and event recognition: the ETISEO experience. Andrea Cavallaro Multimedia and Vision Lab Queen Mary, University of London. [email protected]. Outline. QMUL’s object tracking and event recognition Change detection and object tracking - PowerPoint PPT Presentation

Transcript of Object detection, tracking and event recognition: the ETISEO experience

Page 1: Object detection, tracking and event recognition: the ETISEO experience

Object detection, tracking and event recognition: the ETISEO experience

Andrea Cavallaro

Multimedia and Vision Lab

Queen Mary, University of London

[email protected]

Page 2: Object detection, tracking and event recognition: the ETISEO experience

Outline

• QMUL’s object tracking and event recognition• Change detection and object tracking• Event recognition

• ETISEO• Evaluation: protocol, data, ground truth• Impact• Improvements of future evaluation campaigns

• Conclusions

• … and an advert

Page 3: Object detection, tracking and event recognition: the ETISEO experience

Outline

• QMUL’s object tracking and event recognition• Change detection and object tracking• Event recognition

• ETISEO• Evaluation: protocol, data, ground truth• Impact• Improvements of future evaluation campaigns

• Conclusions

• … and an advert

Page 4: Object detection, tracking and event recognition: the ETISEO experience

Prior system for event detection

http://www.elec.qmul.ac.uk/staffinfo/andrea/CREDS-help.html

RATP/CREDS

Page 5: Object detection, tracking and event recognition: the ETISEO experience

Introduction

• QMUL Detection, Tracking, Event Recognition (Q-DTE)• initially designed for Event Detection and Tracking in metro

stations• modified to respond to ETISEO • components:

• Moving object detection

• Background subtraction with noise modeling

• Object tracking

• Graph matching

• Composite target distance based on multiple object features

• Event recognition

M. Taj, E. Maggio, A. Cavallaro“Multi-feature graph-based object tracking”Proc. of CLEAR Workshop - LNCS 4122, 2006

Page 6: Object detection, tracking and event recognition: the ETISEO experience

Object detection and tracking

• Change detection• Statistical change detection

• Gaussians on colour components

• Noise filtering• Contrast enhancement

• Problem: data association after object detection• Appearance/disappearance of objects• False detections due to clutter and noisy observations

Page 7: Object detection, tracking and event recognition: the ETISEO experience

Moving object segmentation

• Motion detection through frame difference

• Problem• D = {d k}, dk 0 even if there is no structural change in k

current frame reference frame difference frame D

Page 8: Object detection, tracking and event recognition: the ETISEO experience

02 / HtP k

0Hdp k

2

2

2 2exp

2

1

kd

Adaptive threshold for change detection

• Noise modelling

• Test statistics

• Significance test

Hyp. H0: “no changes in k”, camera noise N(0, )

kw

kk d 22

02 Hp k ondistributi2

Page 9: Object detection, tracking and event recognition: the ETISEO experience

Tracking

• Graph matching using weighted features• Data association verified throughout several frames

to validate the correctness of the tracks • Support track recovery in occlusion scenarios • Features

• centre of mass

• velocity

• bounding box

• colour

).1(),(.),(.),(.),(.),(

H]h,w, , y,[x, = X

4321

..

ijXXgXXgXXgXXgXXg

yx

bj

ai

bj

ai

bj

ai

bj

ai

bj

ai

velocity

appearance

size

position

Page 10: Object detection, tracking and event recognition: the ETISEO experience

Graph matching: full graph

v(x11)

v(x21)

v(x31)

v(x41)

v(x13)

v(x23)

v(x33)

v(x43)

v(x12)

v(x22)

v(x32)

V1 V3

v(x11)

v(x21)

v(x31)

v(x41)

v(x13)

v(x23)

v(x33)

v(x43)

V2

v(x12)

v(x22)

v(x32)

Page 11: Object detection, tracking and event recognition: the ETISEO experience

v(x11)

v(x21)

v(x31)

v(x41)

v(x13)

v(x23)

v(x33)

v(x43)

v(x12)

v(x22)

v(x32)

Graph matching: max path cover

V1 V3V2

Page 12: Object detection, tracking and event recognition: the ETISEO experience

Experimental framework

• Key parameters• noise variance: 1.8• kernel size: 3x3 • feature weights

• position α = 0.40

• velocity β = 0.30

• appearance γ = 0.15

• size δ = 0.15

• Determined using CLEAR dataset/metrics• Moving object detection accuracy / precision (MODA / MODP)• Moving object tracking accuracy / precision (MOTA / MOTP)

Page 13: Object detection, tracking and event recognition: the ETISEO experience

Event recognition

Page 14: Object detection, tracking and event recognition: the ETISEO experience

Event recognition

Page 15: Object detection, tracking and event recognition: the ETISEO experience

Event recognition

Page 16: Object detection, tracking and event recognition: the ETISEO experience

Event recognition

Page 17: Object detection, tracking and event recognition: the ETISEO experience
Page 18: Object detection, tracking and event recognition: the ETISEO experience

Outline

• QMUL’s object tracking and event recognition• Change detection and object tracking• Event recognition

• ETISEO• Evaluation: protocol, data, ground truth• Impact• Improvements of future evaluation campaigns

• Conclusions

• … and an advert

Page 19: Object detection, tracking and event recognition: the ETISEO experience

ETISEO

• Impact• Promote evaluation

• Formal and objective evaluation is (urgently) needed

• Data collection and distribution• time consuming!

• common ground for research

• Priority sequences • Use of an existing XML schema • Discussion forum

• Choice of performance measures and experimental data is not obvious

Page 20: Object detection, tracking and event recognition: the ETISEO experience

Improvements

• Involve stakeholders at earlier stages• More input from end users

• what do they want / need?

• costs / weights of errors

• Involve (more) researchers from the beginning • Facilitate understanding of the protocol

• Fix errors / ambiguities early

• Use training/testing dataset• see i-Lids and CLEAR

• Maybe private dataset too

• Give meaning to measures • what is the “value” of these numbers?

• e.g., compare with a naïve result

• what is the “value” of a difference of (e.g.) 0.1?

Page 21: Object detection, tracking and event recognition: the ETISEO experience

• Improvements of future evaluation campaigns• Are we evaluating too many things simultaneously?

• Too many variables

• Do we need so many measures?• remove redundant measures

• Is the ground truth really “truth”?• statistical analysis / more annotators / confidence level

• Should we distribute the evaluation tool / ground-truth earlier? • Are we happy with the current demarcation of regions / definition of

events?• Do we want to evaluate all the event types together?

• should we focus on subsets of events and move on progressively

• Is the dataset too heterogeneous? • Can we generalize the results obtained so far?

Questions

Page 22: Object detection, tracking and event recognition: the ETISEO experience

Conclusions

• Conclusions• QMUL submission

• Statistical colour change detection

• Multi-feature weighted graph matching

• Event recognition module: evolution from CREDS 2005.

• Next: extend to 3D

• Feedback on ETISEO• Evaluation + discussion

• Extend the community / do not duplicate efforts

• Metrics

More information

http://www.elec.qmul.ac.uk/staffinfo/andrea

… and an advert

Page 23: Object detection, tracking and event recognition: the ETISEO experience

IEEE International Conference on

Advanced Video and Signal based Surveillance

IEEE AVSS 2007London (UK)

5-7 September 2007

Paper submission: 28 February 2007

Page 24: Object detection, tracking and event recognition: the ETISEO experience

• Acknowledgments• Murtaza Taj• Emilio Maggio

Page 25: Object detection, tracking and event recognition: the ETISEO experience

Evaluation metric

http://www.elec.qmul.ac.uk/staffinfo/andrea/CREDS-help.html

S

DAt

B

Maximum Delay

Maximum Score

Accepted anticipation

Unaccepted anticipation