Table 3 Comparative study of FFDGCRN-ROD model with existing techniques.

From: Intelligent feature fusion with dynamic graph convolutional recurrent network for robust object detection to assist individuals with disabilities in a smart Iot edge-cloud environment

Model

\(\:\varvec{A}\varvec{c}\varvec{c}{\varvec{u}}_{\varvec{y}}\)

\(\:\varvec{P}\varvec{r}\varvec{e}{\varvec{c}}_{\varvec{n}}\)

\(\:\varvec{R}\varvec{e}\varvec{c}{\varvec{a}}_{\varvec{l}}\)

\(\:{\varvec{F}1}_{\varvec{S}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\)

NAM

89.72

88.49

88.36

91.50

PCA

91.96

92.84

90.60

87.18

TFST

91.74

89.48

86.19

86.50

Yolo-V8

89.07

87.89

87.68

91.79

Yolo-V5 large

91.26

93.15

91.91

86.48

MR-CNN

91.10

88.72

85.60

85.97

YOLO-inception

88.58

89.03

89.95

87.79

CADNet

90.08

88.65

85.89

88.36

DICSSD300

97.81

88.51

90.28

86.85

AttenRetina

93.39

92.35

86.77

92.59

FFDGCRN-ROD

99.65

93.85

92.25

92.85

Back to article page