A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet
https://orcid.org/0000-0001-7850-0847
https://orcid.org/0000-0002-4656-3314
The ability of EfficientDet, a framework developed in 2019 for object detection, to automatically detect smoke plumes at a distance of several kilometers is demonstrated. Recent articles have raised concerns about the effectiveness of EfficientDet in fire detection applications, with over 40% of false positives reported. The proposed EfficientDet model achieved a true detection rate of 80.4% and a false-positive rate of 1.13% on a testing set. The data set used in this study, which includes 14,125 smoke and 21,203 non-smoke images, is one of the largest, or even the largest, of its kind reported in the literature for images containing smoke plumes. Our results surpass those of a previous study that used the same data set and are more reliable and realistic than those reported by others, which may seem better, but were calculated using smaller and less representative data sets.
Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet
https://orcid.org/0000-0001-7850-0847
https://orcid.org/0000-0002-4656-3314
The ability of EfficientDet, a framework developed in 2019 for object detection, to automatically detect smoke plumes at a distance of several kilometers is demonstrated. Recent articles have raised concerns about the effectiveness of EfficientDet in fire detection applications, with over 40% of false positives reported. The proposed EfficientDet model achieved a true detection rate of 80.4% and a false-positive rate of 1.13% on a testing set. The data set used in this study, which includes 14,125 smoke and 21,203 non-smoke images, is one of the largest, or even the largest, of its kind reported in the literature for images containing smoke plumes. Our results surpass those of a previous study that used the same data set and are more reliable and realistic than those reported by others, which may seem better, but were calculated using smaller and less representative data sets.
Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet
https://orcid.org/0000-0001-7850-0847
https://orcid.org/0000-0002-4656-3314
The ability of EfficientDet, a framework developed in 2019 for object detection, to automatically detect smoke plumes at a distance of several kilometers is demonstrated. Recent articles have raised concerns about the effectiveness of EfficientDet in fire detection applications, with over 40% of false positives reported. The proposed EfficientDet model achieved a true detection rate of 80.4% and a false-positive rate of 1.13% on a testing set. The data set used in this study, which includes 14,125 smoke and 21,203 non-smoke images, is one of the largest, or even the largest, of its kind reported in the literature for images containing smoke plumes. Our results surpass those of a previous study that used the same data set and are more reliable and realistic than those reported by others, which may seem better, but were calculated using smaller and less representative data sets.
Automatic early detection of wildfire smoke with visible-light cameras and EfficientDet
Fernandes, Armando M (author) / Utkin, Andrei B (author) / Chaves, Paulo (author)
Journal of Fire Sciences ; 41 ; 122-135
2023-07-01
14 pages
Article (Journal)
Electronic Resource
English
Computer-Vision-Based Statue Detection with Gaussian Smoothing Filter and EfficientDet
| DOAJ | 2022
An Intelligent Wildfire Detection Approach through Cameras Based on Deep Learning
| DOAJ | 2022
Wildfire smoke detection based on local extremal region segmentation and surveillance
| British Library Online Contents | 2016
Hybrid Stereocorrelation Using Infrared and Visible Light Cameras
| British Library Online Contents | 2016