Table 4 Comparison evaluation of the SASVCP-ODTSA model with existing techniques34,35,36.

From: A smart assistive system for visually challenged people through efficient object detection using deep learning with tunicate swarm algorithm

Technique

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

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

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

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

Time Consumed (sec)

Libra RCNN

92.79

90.68

72.30

83.56

16.14

Cascade RCNN + res2net + DCNv2

91.05

84.35

70.82

82.49

20.96

YOLOv3

96.54

79.14

76.73

80.12

14.91

YOLOXs

95.51

80.28

79.31

84.02

20.60

ResNet18 + LSA

97.68

84.45

72.59

76.93

18.36

IOD155 + tfidf

89.43

85.96

71.21

81.22

9.36

PointNet++

94.13

87.42

72.88

73.67

10.34

CBORM model

98.41

82.00

79.14

82.58

21.13

SASVCP-ODTSA

99.58

91.77

84.71

87.15

6.45