A Child Caring Robot for the Dangerous Behavior Detection Based on the Object Recognition and Human Action Recognition
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractIn this paper, a child caring robot is developed for detecting some dangerous behavior performed by child in the domestic environment based on the human action recognition and object recognition technologies. A human behavior is an interactive process between human and objects. Therefore, three factors need to be considered: the engaged objects, human actions and the relationship between human and the engaged objects. In our application scenario, a correlative filter is proposed to improve the stability of the object recognition with human interference. For the human action recognition, a new motion encoding method by using the Euclidean distant matrix (EDM) between joints is introduced and a convolutional neural network is utilized. Evaluation on the Northwester-UCLA dataset verified the effectiveness of this method when action categories are small. The proposed action recognition method is simple and efficient, which is crucial for online behavior detection. Extensive experiments in the real physical world for detecting the behavior of eating allergic fruit and touching/playing with electrical socket have achieved good performance.
All Author(s) ListQiang Nie, Xin Wang, Jiangliu Wang, Manlin Wang, Yunhui Liu
Name of Conference2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)
Start Date of Conference12/12/2018
End Date of Conference15/12/2018
Place of ConferenceKuala Lumpur
Country/Region of ConferenceMalaysia
Proceedings Title2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)
Detailed descriptionIn this paper, a child caring robot is developed for detecting some dangerous behavior performed by child in the domestic environment based on the human action recognition and object recognition technologies. A human behavior is an interactive process between human and objects. Therefore, three factors need to be considered: the engaged objects, human actions and the relationship between human and the engaged objects. In our application scenario, a correlative filter is proposed to improve the stability of the object recognition with human interference. For the human action recognition, a new motion encoding method by using the Euclidean distant matrix (EDM) between joints is introduced and a convolutional neural network is utilized. Evaluation on the Northwester-UCLA dataset verified the effectiveness of this method when action categories are small. The proposed action recognition method is simple and efficient, which is crucial for online behavior detection. Extensive experiments in the real physical world for detecting the behavior of eating allergic fruit and touching/playing with electrical socket have achieved good performance.
Year2019
Month3
PublisherIEEE
Pages1921 - 1926
ISBN978-1-7281-0377-8
LanguagesEnglish-United Kingdom
Keywordsimage coding, image filtering, image motion analysis, image recognition, matrix algebra, object recognition, robot vision, service robots, dangerous behavior detection, human action recognition, human behavior, human interference, online behavior detection, object recognition technologies, human object recognition, human action recognition method, child caring robot, domestic environment, correlative filter, motion encoding method, Euclidean distant matrix, convolutional neural network, Northwester-UCLA dataset, action categories, interactive process, Sockets, Robot sensing systems, Image recognition, Three-dimensional displays, Target tracking, Skeleton

Last updated on 2021-22-01 at 23:55