2019
DOI: 10.1109/tii.2019.2897594
|View full text |Cite
|
Sign up to set email alerts
|

Efficient Fire Detection for Uncertain Surveillance Environment

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
118
0
1

Year Published

2019
2019
2021
2021

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 234 publications
(119 citation statements)
references
References 39 publications
0
118
0
1
Order By: Relevance
“…We have compared the performances of our scheme in terms of three metrics including false positive, false negative, and accuracy. While the method of Khan Muhammad et al [31] performs the best in terms of false positive and false negative, ours with the delayed decision of the majority voting in 10 s outperforms in accuracy. Note that our proposed method can produce this better by introducing the delayed decision in DTA.…”
Section: Majority Voting and Interpretation Of Fire Behaviormentioning
confidence: 65%
“…We have compared the performances of our scheme in terms of three metrics including false positive, false negative, and accuracy. While the method of Khan Muhammad et al [31] performs the best in terms of false positive and false negative, ours with the delayed decision of the majority voting in 10 s outperforms in accuracy. Note that our proposed method can produce this better by introducing the delayed decision in DTA.…”
Section: Majority Voting and Interpretation Of Fire Behaviormentioning
confidence: 65%
“…The disadvantage of these methods is that the neural network models require high-configuration hardware and are unsuitable for embedded systems. SqueezeNet and MobileNetV2 were proposed to meet the constraints of embedded systems [36,37]. At the cost of lower accuracy, these lightweight neural network models are computationally efficient and can be deployed to platforms like Raspberry Pi.…”
Section: Fire Detection Via Machine Learning and Deep Learning Methodsmentioning
confidence: 99%
“…Muhammad et al [17,18] proposed a cost-effective fire detection CNN architecture for surveillance videos with less computational time and memory footprints. eir model is inspired by GoogLeNet architecture, considering its reasonable computational complexity and suitability for the intended problem compared with other computationally expensive networks such as AlexNet.…”
Section: Literature Reviewmentioning
confidence: 99%