In this paper, we present a literature survey about drowsy driving detection using PERCLOS metric that determines the percentage of eye closure. This metric determines that an eye is closed if the percentage of eye closure is 80% or above. When this percentage is observed for multiple frames of a video camera feed, the driver is determined to be in an unsafe fatigue status. In our research, we found that the PERCLOS metric had a 0.79 to 0.87 correlation coefficient value which exceeds the 0.7 R value needed to be considered a strong correlation coefficient. A higher value than 0.7 indicates a more linear relationship which means that the metric is dependable 1.
%0 Journal Article
%1 kim2020detecting
%A Kim, Samuel
%A Wisanggeni, Irfan
%A Ros, Ryan
%A Hussein, Rania
%D 2020
%J International Journal of Image Processing (IJIP)
%K Autonomous Driving. PERCLOS, Real-time Systems,
%N 1
%P 1-7
%T Detecting Fatigue Driving Through PERCLOS: A Review
%U http://www.cscjournals.org/library/manuscriptinfo.php?mc=IJIP-1194
%V 14
%X In this paper, we present a literature survey about drowsy driving detection using PERCLOS metric that determines the percentage of eye closure. This metric determines that an eye is closed if the percentage of eye closure is 80% or above. When this percentage is observed for multiple frames of a video camera feed, the driver is determined to be in an unsafe fatigue status. In our research, we found that the PERCLOS metric had a 0.79 to 0.87 correlation coefficient value which exceeds the 0.7 R value needed to be considered a strong correlation coefficient. A higher value than 0.7 indicates a more linear relationship which means that the metric is dependable 1.
@article{kim2020detecting,
abstract = {In this paper, we present a literature survey about drowsy driving detection using PERCLOS metric that determines the percentage of eye closure. This metric determines that an eye is closed if the percentage of eye closure is 80% or above. When this percentage is observed for multiple frames of a video camera feed, the driver is determined to be in an unsafe fatigue status. In our research, we found that the PERCLOS metric had a 0.79 to 0.87 correlation coefficient value which exceeds the 0.7 R value needed to be considered a strong correlation coefficient. A higher value than 0.7 indicates a more linear relationship which means that the metric is dependable [1].},
added-at = {2020-11-29T02:54:53.000+0100},
author = {Kim, Samuel and Wisanggeni, Irfan and Ros, Ryan and Hussein, Rania},
biburl = {https://www.bibsonomy.org/bibtex/2f16848f0491155b19d09979de2c506ff/cscjournals},
interhash = {df24b555b1eb66266355821706c51c19},
intrahash = {f16848f0491155b19d09979de2c506ff},
issn = {1985-2304},
journal = {International Journal of Image Processing (IJIP)},
keywords = {Autonomous Driving. PERCLOS, Real-time Systems,},
language = {English},
month = {February},
number = 1,
pages = {1-7},
timestamp = {2020-11-29T02:54:53.000+0100},
title = {Detecting Fatigue Driving Through PERCLOS: A Review},
url = {http://www.cscjournals.org/library/manuscriptinfo.php?mc=IJIP-1194},
volume = 14,
year = 2020
}