Idioma:

Fast and Accurate Driver Action Recognition with Multi-Task Learning of Driver Pose and Action

Nishiyuki, Kenta ; Hyuga, Tadashi ; Tasaki, Hiroshi ; Kinoshita, Koichi ; Hasegawa, Yuki ; Yamashita, Takayoshi ; Fujiyoshi, Hironobu

Transactions of the Japanese Society for Artificial Intelligence, 2021/03/01, Vol.36(2), pp.A-K93_1-10

Tokyo: The Japanese Society for Artificial Intelligence

Texto completo disponível

Citações Citado por

Enviar para

Título:
Fast and Accurate Driver Action Recognition with Multi-Task Learning of Driver Pose and Action
Autor: Nishiyuki, Kenta ; Hyuga, Tadashi ; Tasaki, Hiroshi ; Kinoshita, Koichi ; Hasegawa, Yuki ; Yamashita, Takayoshi ; Fujiyoshi, Hironobu
Assuntos: Ablation ; action recognition ; Body parts ; Classification ; Commercial vehicles ; Driver behavior ; driver monitoring ; Embedded systems ; Human activity recognition ; Human motion ; Learning ; multi-task learning ; pose estimation ; Safety management
É parte de: Transactions of the Japanese Society for Artificial Intelligence, 2021/03/01, Vol.36(2), pp.A-K93_1-10
Descrição: Driver Action Recognition is a key component in driver monitoring systems, which is helpful for the safety management of commercial vehicles. Compared with traditional human action recognition tasks, driver action recognition is required to be fast and accurate on embedded systems. We propose a fast and accurate driver action recognition method that is composed of CNN based driver pose estimation and RNN based driver action recognition. We train our network model with multi-task learning includes localizing and detecting each body part of the driver, classifying state of each body part, and recognizing driver action at once. Our multi-task learning for the proposed model achieves a significant improvement compared to state-of-the-art human action recognition methods with limited computational resources. We also perform ablation study of our methods which composed of the driver pose localization, detection, and classification.
Editor: Tokyo: The Japanese Society for Artificial Intelligence
Idioma: Japonês

Voltar para lista de resultados

Anterior Resultado 10 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

Fast and Accurate Driver Action Recognition with Multi-Task Learning of Driver Pose and Action

Nishiyuki, Kenta ; Hyuga, Tadashi ; Tasaki, Hiroshi ; Kinoshita, Koichi ; Hasegawa, Yuki ; Yamashita, Takayoshi ; Fujiyoshi, Hironobu

Tokyo: The Japanese Society for Artificial Intelligence

Buscando em bases de dados remotas. Favor aguardar.