Body area segmentation from visual scene based on predictability of neuro-dynamical system

Harumitsu Nobuta, Kenta Kawamoto, Kuniaki Noda, Kohtaro Sabe, Shun Nishide, Hiroshi G. Okuno, Tetsuya Ogata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose neural models for segmenting the area of a body from visual scene based on predictability. Neuroscience has shown that a prediction model in brain, which predicts sensory-feedback from motor command, can divide the sensory-feedback into the self-motion derived feedback and other derived feedback. The prediction model is important for prediction control of the body. Previous studies in robotics of the prediction model assumed that a robot can recognize the position of its body (e.g. its hand) and that the view contains only that body part. In our models, motor commands and visual feedback (pixel image that includes not only a hand but also object and background) are input into a neural network model and then the body area is segmented and prediction model of body is acquired. Our model contains two parts: 1) An object detection model obtains a conversion system between object positions and the pixel image. 2) A movement prediction model predicts hand-object positions from motor commands and identifies the body. We confirmed that our models can segment the body/object area based on their pixel textures and discriminate between them by using prediction error.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD
Duration: 2012 Jun 102012 Jun 15

Other

Other2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
CityBrisbane, QLD
Period12/6/1012/6/15

Fingerprint

Dynamical systems
Sensory feedback
Pixels
Feedback
Brain
Robotics
Textures
Robots
Neural networks

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Nobuta, H., Kawamoto, K., Noda, K., Sabe, K., Nishide, S., Okuno, H. G., & Ogata, T. (2012). Body area segmentation from visual scene based on predictability of neuro-dynamical system. In Proceedings of the International Joint Conference on Neural Networks [6252530] https://doi.org/10.1109/IJCNN.2012.6252530

Body area segmentation from visual scene based on predictability of neuro-dynamical system. / Nobuta, Harumitsu; Kawamoto, Kenta; Noda, Kuniaki; Sabe, Kohtaro; Nishide, Shun; Okuno, Hiroshi G.; Ogata, Tetsuya.

Proceedings of the International Joint Conference on Neural Networks. 2012. 6252530.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nobuta, H, Kawamoto, K, Noda, K, Sabe, K, Nishide, S, Okuno, HG & Ogata, T 2012, Body area segmentation from visual scene based on predictability of neuro-dynamical system. in Proceedings of the International Joint Conference on Neural Networks., 6252530, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, 12/6/10. https://doi.org/10.1109/IJCNN.2012.6252530
Nobuta H, Kawamoto K, Noda K, Sabe K, Nishide S, Okuno HG et al. Body area segmentation from visual scene based on predictability of neuro-dynamical system. In Proceedings of the International Joint Conference on Neural Networks. 2012. 6252530 https://doi.org/10.1109/IJCNN.2012.6252530
Nobuta, Harumitsu ; Kawamoto, Kenta ; Noda, Kuniaki ; Sabe, Kohtaro ; Nishide, Shun ; Okuno, Hiroshi G. ; Ogata, Tetsuya. / Body area segmentation from visual scene based on predictability of neuro-dynamical system. Proceedings of the International Joint Conference on Neural Networks. 2012.
@inproceedings{44e06fe1177e424fa0ef2d4c945a52df,
title = "Body area segmentation from visual scene based on predictability of neuro-dynamical system",
abstract = "We propose neural models for segmenting the area of a body from visual scene based on predictability. Neuroscience has shown that a prediction model in brain, which predicts sensory-feedback from motor command, can divide the sensory-feedback into the self-motion derived feedback and other derived feedback. The prediction model is important for prediction control of the body. Previous studies in robotics of the prediction model assumed that a robot can recognize the position of its body (e.g. its hand) and that the view contains only that body part. In our models, motor commands and visual feedback (pixel image that includes not only a hand but also object and background) are input into a neural network model and then the body area is segmented and prediction model of body is acquired. Our model contains two parts: 1) An object detection model obtains a conversion system between object positions and the pixel image. 2) A movement prediction model predicts hand-object positions from motor commands and identifies the body. We confirmed that our models can segment the body/object area based on their pixel textures and discriminate between them by using prediction error.",
author = "Harumitsu Nobuta and Kenta Kawamoto and Kuniaki Noda and Kohtaro Sabe and Shun Nishide and Okuno, {Hiroshi G.} and Tetsuya Ogata",
year = "2012",
doi = "10.1109/IJCNN.2012.6252530",
language = "English",
isbn = "9781467314909",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Body area segmentation from visual scene based on predictability of neuro-dynamical system

AU - Nobuta, Harumitsu

AU - Kawamoto, Kenta

AU - Noda, Kuniaki

AU - Sabe, Kohtaro

AU - Nishide, Shun

AU - Okuno, Hiroshi G.

AU - Ogata, Tetsuya

PY - 2012

Y1 - 2012

N2 - We propose neural models for segmenting the area of a body from visual scene based on predictability. Neuroscience has shown that a prediction model in brain, which predicts sensory-feedback from motor command, can divide the sensory-feedback into the self-motion derived feedback and other derived feedback. The prediction model is important for prediction control of the body. Previous studies in robotics of the prediction model assumed that a robot can recognize the position of its body (e.g. its hand) and that the view contains only that body part. In our models, motor commands and visual feedback (pixel image that includes not only a hand but also object and background) are input into a neural network model and then the body area is segmented and prediction model of body is acquired. Our model contains two parts: 1) An object detection model obtains a conversion system between object positions and the pixel image. 2) A movement prediction model predicts hand-object positions from motor commands and identifies the body. We confirmed that our models can segment the body/object area based on their pixel textures and discriminate between them by using prediction error.

AB - We propose neural models for segmenting the area of a body from visual scene based on predictability. Neuroscience has shown that a prediction model in brain, which predicts sensory-feedback from motor command, can divide the sensory-feedback into the self-motion derived feedback and other derived feedback. The prediction model is important for prediction control of the body. Previous studies in robotics of the prediction model assumed that a robot can recognize the position of its body (e.g. its hand) and that the view contains only that body part. In our models, motor commands and visual feedback (pixel image that includes not only a hand but also object and background) are input into a neural network model and then the body area is segmented and prediction model of body is acquired. Our model contains two parts: 1) An object detection model obtains a conversion system between object positions and the pixel image. 2) A movement prediction model predicts hand-object positions from motor commands and identifies the body. We confirmed that our models can segment the body/object area based on their pixel textures and discriminate between them by using prediction error.

UR - http://www.scopus.com/inward/record.url?scp=84865106492&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865106492&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252530

DO - 10.1109/IJCNN.2012.6252530

M3 - Conference contribution

AN - SCOPUS:84865106492

SN - 9781467314909

BT - Proceedings of the International Joint Conference on Neural Networks

ER -