Managing Fatigue by Drowsiness Detection

Author(s):  
David F. Dinges ◽  
Melissa M. Mallis
Keyword(s):  
Author(s):  
Prasanna Lakshmi Kompalli ◽  
Padma Vallakati ◽  
Ganapathi Raju Nadimpalli ◽  
Vinod Mahesh Jain ◽  
Samuel Annepogu

Background: Road accidents are major cause of deaths worldwide. This is enormously due to fatigue, drowsiness and microsleep of the drivers. This don’t just risk the life of driver and copassengers but also a great threat to the vehicles and humans moving around that vehicle. Methods: Research, online content and previously published paper related to drowsiness are reviewed. Using the facial landmarks DAT file, the prototype will locate and get the eye coordinates and it will calculate Eye Aspect Ratio (EAR). The EAR indicates whether the driver is drowsy or not based on the result various sensors gets activated such as Alarm generator, LED Indicators, LCD message scroll, message sent to owner and engine gets locked. Results: The prototype is able to locate eyes in the frame and detect whether the person is sleepy or not. Whenever the person is feeling drowsy alarm gets generated in the cabinet on further if the person is feeling drowsy, LED indicators will start glowing, messaging will be scrolling at the rear part of vehicle so that other vehicles and humans gets cautioned and vehicle slows down and engine gets locked. Conclusion: This prototype will help in reduction of road accidents due to human intervention. It is not only helpful to the person who install it in their vehicles but also for the other vehicles and humans moving around it.


Information ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 3
Author(s):  
Shuang Chen ◽  
Zengcai Wang ◽  
Wenxin Chen

The effective detection of driver drowsiness is an important measure to prevent traffic accidents. Most existing drowsiness detection methods only use a single facial feature to identify fatigue status, ignoring the complex correlation between fatigue features and the time information of fatigue features, and this reduces the recognition accuracy. To solve these problems, we propose a driver sleepiness estimation model based on factorized bilinear feature fusion and a long- short-term recurrent convolutional network to detect driver drowsiness efficiently and accurately. The proposed framework includes three models: fatigue feature extraction, fatigue feature fusion, and driver drowsiness detection. First, we used a convolutional neural network (CNN) to effectively extract the deep representation of eye and mouth-related fatigue features from the face area detected in each video frame. Then, based on the factorized bilinear feature fusion model, we performed a nonlinear fusion of the deep feature representations of the eyes and mouth. Finally, we input a series of fused frame-level features into a long-short-term memory (LSTM) unit to obtain the time information of the features and used the softmax classifier to detect sleepiness. The proposed framework was evaluated with the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results showed that this method had better stability and robustness compared with other methods.


2017 ◽  
Vol 11 (5) ◽  
pp. 255-263 ◽  
Author(s):  
Fnu Rohit ◽  
Vinod Kulathumani ◽  
Rahul Kavi ◽  
Ibrahim Elwarfalli ◽  
Vlad Kecojevic ◽  
...  

2011 ◽  
Vol 5 (17) ◽  
pp. 2461-2469 ◽  
Author(s):  
B.-G. Lee ◽  
S.-J. Jung ◽  
W.-Y. Chung

Sign in / Sign up

Export Citation Format

Share Document