TY - GEN
T1 - Drive-net
T2 - 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018
AU - Majdi, Mohammed S.
AU - Ram, Sundaresh
AU - Gill, Jonathan T.
AU - Rodriguez, Jeffrey J.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/21
Y1 - 2018/9/21
N2 - To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking to passengers, fixing hair and makeup, eating and drinking, and using a mobile phone. In this paper, we present an automated supervised learning method called Drive-Net for driver distraction detection. Drive-Net uses a combination of a convolutional neural network (CNN) and a random decision forest for classifying images of a driver. We compare the performance of our proposed Drive-Net to two other popular machine-learning approaches: a recurrent neural network (RNN), and a multi-layer perceptron (MLP). We test the methods on a publicly available database of images acquired under a controlled environment containing about 22425 images manually annotated by an expert. Results show that Drive-Net achieves a detection accuracy of 95%, which is 2% more than the best results obtained on the same database using other methods.
AB - To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking to passengers, fixing hair and makeup, eating and drinking, and using a mobile phone. In this paper, we present an automated supervised learning method called Drive-Net for driver distraction detection. Drive-Net uses a combination of a convolutional neural network (CNN) and a random decision forest for classifying images of a driver. We compare the performance of our proposed Drive-Net to two other popular machine-learning approaches: a recurrent neural network (RNN), and a multi-layer perceptron (MLP). We test the methods on a publicly available database of images acquired under a controlled environment containing about 22425 images manually annotated by an expert. Results show that Drive-Net achieves a detection accuracy of 95%, which is 2% more than the best results obtained on the same database using other methods.
KW - Image classification
KW - convolutional neural networks
KW - driver distraction
KW - random forest
UR - http://www.scopus.com/inward/record.url?scp=85055555073&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85055555073&partnerID=8YFLogxK
U2 - 10.1109/SSIAI.2018.8470309
DO - 10.1109/SSIAI.2018.8470309
M3 - Conference contribution
AN - SCOPUS:85055555073
T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
SP - 69
EP - 72
BT - 2018 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 8 April 2018 through 10 April 2018
ER -