Driver behavior recognition based on deep convolutional neural networks
Authors:
- 24 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 636-641
Abstract
Traffic safety is a severe problem around the world. Many road accidents are normally related with the driver's unsafe driving behavior, e.g. eating while driving. In this work, we propose a vision-based solution to recognize the driver's behavior based on convolutional neural networks. Specifically, given an image, skin-like regions are extracted by Gaussian Mixture Model, which are passed to a deep convolutional neural networks model, namely R*CNN, to generate action labels. The skin-like regions are able to provide abundant semantic information with sufficient discriminative capability. Also, R*CNN is able to select the most informative regions from candidates to facilitate the final action recognition. We tested the proposed methods on Southeast University Driving-posture Dataset and achieve mean Average Precision(mAP) of 97.76% on the dataset which prove the proposed method is effective in drivers's action recognition.Keywords
This publication has 27 references indexed in Scilit:
- Contextual Action Recognition with R* CNN2015
- Actions and Attributes from Wholes and Parts2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Making full use of spatial-temporal interest points: An AdaBoost approach for action recognition2010
- SIFT Flow: Dense Correspondence across Scenes and Its ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Representing shape with a spatial pyramid kernel2007
- Learning methods for generic object recognition with invariance to pose and lighting2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Recognizing human actions: a local SVM approach2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998