Koichi Emura

Anticipating Driver Actions via Deep Neural Networks and New Driver Personalization Technique through Transfer Learning.

Anticipating driving behaviours is a promising technology for novel advanced driver assistance systems. In recent years, predicting a driver’s future action became an important element to preventive safety technologies and has been advancing greatly contributing to a reduction in road accidents. In this paper, we propose a deep learning network that anticipates driving actions based on information of subject vehicle as well as surrounding vehicles and environment. By re-using a network trained on a great number of various drivers’ data with different driving behaviours and linking it to a particular driver with particular taste we propose a method that enables the anticipation of driving behaviours that can be tailored to each driver individually, leading to improved user experiences. We experimentally test our method for acceleration, deceleration and brake profile anticipation task using actual driving data. Our results demonstrate the effectiveness of our approach, achieving a great improvement when anticipating for individuals.

Creating mobile animation messages without authoring

Mobile phone e-mail messaging is increasingly being chosen by consumers as their primary communication tool. Messages exchanged among mobile phone users frequently contain “emojis (pictograms)”. Some consumers have started to use services which add a relevant animated image to a message. Consumers will start to exchange animated messages if they are able. This paper proposes a method of generating animations from text messages without an authoring process. This method utilizes information available in the consumer’s ubiquitous computing environment to supply the information needed to make animations which are not included in the original e-mail message.