Detection of Driver Drowsiness Using 3D Deep Neural Network and Semi-Supervised Gradient Boosting Machine
| Autor: | Xuan-Phung Huynh, Yong-Guk Kim, Sang-Min Park |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Artificial neural network
business.industry Computer science 020206 networking & telecommunications Pattern recognition 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Task (project management) Active appearance model Data set Face (geometry) Active shape model 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Gradient boosting business computer |
| Zdroj: | Computer Vision – ACCV 2016 Workshops ISBN: 9783319545257 ACCV Workshops (3) |
| DOI: | 10.1007/978-3-319-54526-4_10 |
| Popis: | Detecting drowsiness of the driver with a reliable and confident manner is a challenging task since it requires accurate monitoring of facial behavior such as eye-closure, nodding and yawning. It is even harder to deal with it when she wears sunglasses or scarf, appearing in the data set given for this challenge. One of the popular ways to analyze facial behavior has been using standard face models such as active shape model or active appearance model. These models work well for the frontal faces and yet often stumble for the extreme head pose cases. To handle these issues, we propose an approach based on recent machine learning techniques: first, 3D convolutional neural network to extract features in spatial-temporal domain; secondly, gradient boosting for drowsiness classification; thirdly, semi-supervised learning to enhance overall performance. The highest score from our submissions was 87.46% accuracy, suggesting that this approach has a potential for real application. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|