Research Article

Human Activity Recognition Using Gaussian Mixture Hidden Conditional Random Fields

Table 7

Classification results of the proposed system on UCF sports dataset (A) using ANN, (B) using SVM, (C) using HMM, and (D) using existing HCRF [30], while removing the proposed HCRF model (unit: %).

ActivitiesDivingGSKickingLiftingHBRRunSkatingBSWalk

(A)
Diving6842566432
GS2712454633
Kicking3470354236
Lifting5436556462
HBR3463664554
Running3354664645
Skating2545346935
BS4253465674
Walking5423436370
Average67.78
(B)
Diving7142356324
GS3772432522
Kicking4274453233
Lifting5636943532
HBR2332802422
Running2322575623
Skating2123447824
BS3463423705
Walking4124230381
Average75.00
(C)
Diving7932234322
GS0832432132
Kicking1285133230
Lifting3028232422
HBR0224800534
Running1213484212
Skating2034018631
BS1112030884
Walking1242524377
Average82.67
(D)
Diving9030102211
GS3842131321
Kicking3485002312
Lifting1218911122
HBR0210912301
Running2312380423
Skating2412308440
BS2112103882
Walking0211014091
Average86.89

GS: golf swinging, HBR: horseback riding, BS: baseball swinging.