In the field of intelligent transportation system (ITS), automatic interpretation of a driver�s behavior is an urgent and challenging\ntopic. This paper studies vision-based driving posture recognition in the human action recognition framework. A driving action\ndataset was prepared by a side-mounted camera looking at a driver�s left profile.The driving actions, including operating the shift\nlever, talking on a cell phone, eating, and smoking, are first decomposed into a number of predefined action primitives, that is,\ninteraction with shift lever, operating the shift lever, interaction with head, and interaction with dashboard. A global grid-based\nrepresentation for the action primitives was emphasized, which first generate the silhouette shape from motion history image,\nfollowed by application of the pyramid histogram of oriented gradients (PHOG) for more discriminating characterization. The\nrandomforest (RF) classifier was then exploited to classify the action primitives together with comparisons to some other commonly\napplied classifiers such as ??NN, multiple layer perceptron, and support vector machine. Classification accuracy is over 94% for the\nRF classifier in holdout and cross-validation experiments on the four manually decomposed driving actions.
Loading....