Skip to main content

Table 4 Intra-dataset, final evaluation results for rPPG signals estimated from VIPL-HR dataset by PVM, POS, PbV, G-R (GR), Chrom and Green methods

From: Performance analysis of remote photoplethysmography deep filtering using long short-term memory neural network

 

PVM-VIPL

POS-VIPL

PbV-VIPL

rPPG

BP

WV

SG

MTO

MTM

rPPG

BP

WV

SG

MTO

MTM

rPPG

BP

WV

SG

MTO

MTM

MAE

9.91

7.49

8.02

10.12

4.51

4.02

7.16

6.26

6.14

7.03

3.85

3.76

6.79

6.28

6.04

6.21

4.05

3.7

r

0.4

0.58

0.54

0.39

0.7

0.75

0.56

0.62

0.63

0.58

0.81

0.76

0.6

0.64

0.64

0.65

0.78

0.78

SNR

1.08

1.35

1.34

1.24

5.48

9.98

0.6

0.76

0.83

1.08

5.19

9.76

0.19

0.35

0.41

0.71

5.04

10.78

TMC

0.72

0.79

0.79

0.76

0.84

0.95

0.55

0.72

0.71

0.71

0.81

0.95

0.57

0.75

0.74

0.73

0.78

0.95

 

GR-VIPL

Chrom-VIPL

Green-VIPL

rPPG

BP

WV

SG

MTO

MTM

rPPG

BP

WV

SG

MTO

MTM

rPPG

BP

WV

SG

MTO

MTM

MAE

18.75

12.93

12.98

18.34

4.79

4.79

9.27

8.5

8.27

8.12

4.37

4.33

25.73

17.72

17.79

25.43

10

7.12

r

0.15

0.36

0.33

0.15

0.72

0.69

0.52

0.56

0.56

0.57

0.77

0.74

0.06

0.07

0.05

0.05

0.23

0.4

SNR

− 1.22

− 1

− 0.92

− 1

3.87

8.66

− 0.55

− 0.4

− 0.33

− 0.04

4.27

8.74

− 2.72

− 2.46

− 2.39

− 2.62

1.32

6.18

TMC

0.59

0.74

0.73

0.71

0.81

0.96

0.53

0.71

0.69

0.68

0.79

0.95

0.55

0.71

0.7

0.66

0.74

0.95