Skip to main content

Table 1 Tabular description of the chosen video clips (B2-Browse2, BWW1-BrowseWhileWhalking1, FC-Fight Chase, FR1-FightRunway1, LB-LeftBag, LBx-LeftBox, MC-MeetCrowd, MWS-MeetWalkSplit, MWT1-MeetWalkTogether1, RFF-RestFallenFloor, WBS1-Walk and ByShop1) and comparison of combined RMSE between EPMCMC + ELPDA model (Proposed), EPMCMC + PDA model (Baseline) and RMSE of Torso alone in generic particle filter framework (JPDA PF).

From: Combined Data Association and Evolving Particle Filter for Tracking of Multiple Articulated Objects

Video

Frames

Targets

Occlude

Clutter

Proposed

Baseline

JPDAPF

Time

B2

173

1

No

0

1.1821

2.0413

0.9648

3187

 

198

1

Self

0

1.6669

2.3425

1.1578

3276

BWW1

361

1

Self

1

2.1638

2.6804

1.5673

3106

FC

129

1

No

0

0.5187

0.9835

0.2784

3016

 

178

2

Yes

0

2.7861

4.0076

3.1279

3127

FR1

199

2

Yes

0

2.7883

3.9801

1.4531

3229

LB

201

3

Self

0

3.4412

7.6359

5.8763

3663

 

401

3

Partial

1

3.6567

8.0015

5.1455

3841

 

208

1

No

0

1.4009

2.2156

1.0151

2923

 

146

1

Self

0

1.9768

3.8970

2.1412

3312

LBx

373

2

Partial

0

2.8990

5.7682

4.2349

3401

 

370

1

Yes

1

2.5238

3.3532

2.0451

3198

MC

282

4

Partial

0

3.8982

6.4235

6.7347

3789

MWS

301

2

Partial

1

2.0679

4.2176

3.9567

3128

MWT1

323

2

Partial

0

2.5003

3.9134

2.2734

3215

RFF

388

1

Self

0

2.3027

4.5231

1.7235

3309

WBS1

876

5

Yes

0

3.5694

9.2722

7.0163

4789