Citation

Liu Y, Lasang P, Pranata S, Shen S, Zhang W. IEEE Trans. Intel. Transp. Syst. 2019; 20(10): 3818-3831.

Copyright

(Copyright © 2019, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2019.2921325

PMID

unavailable

Abstract

Driver poses recognition contains three tasks such as body joint, head angle, and face landmark estimation, which is of paramount interest for the advanced driver assistance systems (ADAS). Recently proposed methods intend to use deeper and more complicated networks to achieve better performance, which leads to heavy models that are not feasible for the resource limited applications such as ADAS. To resolve this issue, we have worked on the following aspects: 1) a lightweight network model, which is referred to as recurrent multi-task thin net (RM-ThinNet), has been proposed which was especially designed for the computationally and memory limited devices; 2) a recurrent structure has been introduced to handle the scale difference and dependency between different tasks, and this recurrence ensures the different tasks are accomplished at different stages and their outputs can augment each other; and 3) a virtual data synthesization pipeline and a couple transfer learning method have been presented, by which network can be learnt effectively by relatively a small number of real data. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method and competitive performance can be achieved with smaller model size and faster speed.


Keywords: Social Transition

Language: en

Keywords

ADAS; advanced driver assistance systems; augmented reality; body joint; Computational modeling; Data models; deeper networks; driver information systems; Driver joints detection; driver pose estimation; Face; face landmark estimation; face landmark localization; face recognition; head angle; head angle estimation; learning (artificial intelligence); lightweight network model; memory limited devices; pose estimation; Pose estimation; recurrent lightweight network; recurrent multitask thin net; recurrent structure; resource limited applications; RM-ThinNet; Task analysis; Training; transfer learning; transfer learning method; virtual data augmented transfer learning; virtual data synthesization pipeline