Transfer Learning of Temporal Information for Driver Action Classification

摘要

Correct classification of image data can depend on features learned in multiple sequential frames. We focus on the problem of learning action from video data with an emphasis on driver behavior monitoring. An insufficient quantity of high quality labeled data is a major problem in machine learning research. This is especially true when deep neural networks are used. Although some sufficiently large, general purpose image databases exist for action recognition, most of these are limited to single frames. This kind of data requires that the action recognition task is applied regardless of the temporal information (information from previous and next frames of a video sequence). In this paper, we show that temporal information is useful for accurate classification of video and that the temporal information in lower layers of a convolutional neural network can successfully be transferred from one network to another to greatly improve performance on the driver behavior monitoring task.