Human’s Gesture Recognition and Imitation Based on Robot NAO

  Abstract

Based on Kinect platform, human’s gesture recognition and imitation were realized by humanoid robot NAO in this paper. The hardware system structure of Kinect platform and the principle of human skeleton extraction were mainly introduced firstly. From the image, Kinect camera gets the skeletal point information which is used to compared with preset posture of the skeletal information. Through calculate the angle between the different bones, the computer obtains the human’s posture and sends the instructions to the robot. In the physical experiments, NAO robot receives the pre-programmed corresponding action instructions and imitates the corresponding motions of humans.

 

Existing System:

 

Human’s gesture recognition is one of the important research area of Machine Vision in the modern computer vision research areas, Where more and more people pay attention to human-computer interaction. In a wide variety of human gesture recognition algorithm[1], the technical knowledge of human posture based on knowledge of skeletal information is an excellent way. Kinect [2] appeared in this context born, which makes machines to interact with the world expanded from two-dimensional to three-dimensional space, and enters into a non-contact interactions. Skeletal tracking, face recognition, microphone input, voice recognition based on Kinect & NAO robot are studied in this paper. From the image, Kinect camera gets the skeletal point information which is used to compared with preset posture of the skeletal information. Through calculate the angle between the different bones, the computer obtains the human’s posture and sends the instructions to the robot. In the physical experiments, NAO robot receives the pre-programmed corresponding action instructions and imitates the corresponding motions of humans.

 

Proposed System:

The basic idea of template-matching method can be introduced as follows. Computer system uses the obtained image to match the image in database, and the most similar matching image will be its posture. So, it is necessary to establish a database on body posture image, and enter a variety of body posture image as many as possible. When computer recognizing the human’s gesture, the accuracy depends on the quality and quantity of the database largely. Therefore, the database must have a lot of postures to ensure a high reserve of image data recognition accuracy. The infrared camera will capture scattering spot which is compared with the primary internal stored reference model. When it is different between the distance of captured spot and the primary internal stored reference model, the spot at the position of infrared image will move along the reference line. Range of all spot movement can measured through the correlation of image, and this system will form a parallax image.

 

Conclusion:

Based on Kinect platform, human’s gesture recognition and imitation were realized by humanoid robot NAO in this paper. The hardware system structure of Kinect platform and the principle of human skeleton extraction were mainly introduced firstly. From the image, Kinect camera gets the skeletal point information which is used to compared with preset posture of the skeletal information. Through calculate the angle between the different bones, the computer obtains the human’s posture and sends the instructions  the robot. In the physical experiments, NAO robot receives the pre-programmed corresponding action instructions and imitates the corresponding motions of humans.

 

References

[1] T. Stephen, (2010) January 7, “Natal Recognizes 31 Body Parts, Uses Tenth of Xbox 360 “Computing Resources””, Kotaku, Gawker Media, Retrieved, (2010) November 25.

[2] T. Stephen, (2009) June 5, “Microsoft: Project Natal Can Support Multiple Players, See Fingers”, Kotaku. Gawker Media, Retrieved, (2009) June 6.

[3] W. Mark and B. Matt, (2009) June 3, “Testing Project Natal: We Touched the Intangible”, Gizmodo, Gawker Media, Retrieved, (2009) June 6.

[4] “Nao robot replaces AIBO in RoboCup Standard Platform League”, Engadget, (2007) August 16, Retrieved (2012) October 4.

[5] L. Ismail, S. Shamsuddin, H. Yussof, H. Hashim, S. Bahari, A. Jaafar and I. Zahari, “Face Detection Technique of Humanoid Robot NAO for Application in Robotic Assistive Therapy”, Control System, Computing and Engineering (ICCSCE), 2011, International Conference on IEEE, (2011), pp. 517-521.

[6] J. Guan and Meng and M. Q.-H, “Study on distance measurement for NAO humanoid robot”, Robotics and Biomimetics (ROBIO), 2012, International Conference on IEEE, (2012), pp. 283 – 286.

[7] L. Ming, “Research on Skeleton Localization Based on Kinect Sensior[D]”, Wuhan University of Science and Technology.