Cooking gesture recognition using local feature and depth image

Yanli Ji, Yoshiyasu Ko, Atsushi Shimada, Hajime Nagahara, Rin-Ichiro Taniguchi

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

10 Citations (Scopus)

Abstract

In this paper, we propose a method combining visual local features and depth image information to recognize cooking gestures. We employ the feature calculation method [2] which used extended FAST detector and a compact descriptor CHOG3D to calculate visual local features. We pack the local features by BoW in frame sequences to represent the cooking gestures. In addition, the depth images of hands gestures are extracted and integrated spatio-temporally to represent the position and trajectory information of cooking gestures. The two kinds of features are used to describe cooking gestures, and recognition is realized by employing the SVM. In our method, we determine the gesture class for each frame in cooking sequences. By analyzing the results of frames, we recognize cooking gestures in a continue frame sequences of cooking menus, and find the temporal positions of the recognized gestures.

Original languageEnglish
Title of host publicationCEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012
Pages37-42
Number of pages6
DOIs
Publication statusPublished - 2012
EventACM Multimedia 2012 4th Workshop on Multimedia for Cooking and Eating Activities, CEA 2012 - Nara, Japan
Duration: Nov 2 2012Nov 2 2012

Other

OtherACM Multimedia 2012 4th Workshop on Multimedia for Cooking and Eating Activities, CEA 2012
CountryJapan
CityNara
Period11/2/1211/2/12

Fingerprint

Gesture recognition
Cooking
Trajectories
Detectors

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Ji, Y., Ko, Y., Shimada, A., Nagahara, H., & Taniguchi, R-I. (2012). Cooking gesture recognition using local feature and depth image. In CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012 (pp. 37-42) https://doi.org/10.1145/2390776.2390785

Cooking gesture recognition using local feature and depth image. / Ji, Yanli; Ko, Yoshiyasu; Shimada, Atsushi; Nagahara, Hajime; Taniguchi, Rin-Ichiro.

CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012. 2012. p. 37-42.

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

Ji, Y, Ko, Y, Shimada, A, Nagahara, H & Taniguchi, R-I 2012, Cooking gesture recognition using local feature and depth image. in CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012. pp. 37-42, ACM Multimedia 2012 4th Workshop on Multimedia for Cooking and Eating Activities, CEA 2012, Nara, Japan, 11/2/12. https://doi.org/10.1145/2390776.2390785
Ji Y, Ko Y, Shimada A, Nagahara H, Taniguchi R-I. Cooking gesture recognition using local feature and depth image. In CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012. 2012. p. 37-42 https://doi.org/10.1145/2390776.2390785
Ji, Yanli ; Ko, Yoshiyasu ; Shimada, Atsushi ; Nagahara, Hajime ; Taniguchi, Rin-Ichiro. / Cooking gesture recognition using local feature and depth image. CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012. 2012. pp. 37-42
@inproceedings{df61cae80c214462a4faee52bea55b80,
title = "Cooking gesture recognition using local feature and depth image",
abstract = "In this paper, we propose a method combining visual local features and depth image information to recognize cooking gestures. We employ the feature calculation method [2] which used extended FAST detector and a compact descriptor CHOG3D to calculate visual local features. We pack the local features by BoW in frame sequences to represent the cooking gestures. In addition, the depth images of hands gestures are extracted and integrated spatio-temporally to represent the position and trajectory information of cooking gestures. The two kinds of features are used to describe cooking gestures, and recognition is realized by employing the SVM. In our method, we determine the gesture class for each frame in cooking sequences. By analyzing the results of frames, we recognize cooking gestures in a continue frame sequences of cooking menus, and find the temporal positions of the recognized gestures.",
author = "Yanli Ji and Yoshiyasu Ko and Atsushi Shimada and Hajime Nagahara and Rin-Ichiro Taniguchi",
year = "2012",
doi = "10.1145/2390776.2390785",
language = "English",
isbn = "9781450315920",
pages = "37--42",
booktitle = "CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012",

}

TY - GEN

T1 - Cooking gesture recognition using local feature and depth image

AU - Ji, Yanli

AU - Ko, Yoshiyasu

AU - Shimada, Atsushi

AU - Nagahara, Hajime

AU - Taniguchi, Rin-Ichiro

PY - 2012

Y1 - 2012

N2 - In this paper, we propose a method combining visual local features and depth image information to recognize cooking gestures. We employ the feature calculation method [2] which used extended FAST detector and a compact descriptor CHOG3D to calculate visual local features. We pack the local features by BoW in frame sequences to represent the cooking gestures. In addition, the depth images of hands gestures are extracted and integrated spatio-temporally to represent the position and trajectory information of cooking gestures. The two kinds of features are used to describe cooking gestures, and recognition is realized by employing the SVM. In our method, we determine the gesture class for each frame in cooking sequences. By analyzing the results of frames, we recognize cooking gestures in a continue frame sequences of cooking menus, and find the temporal positions of the recognized gestures.

AB - In this paper, we propose a method combining visual local features and depth image information to recognize cooking gestures. We employ the feature calculation method [2] which used extended FAST detector and a compact descriptor CHOG3D to calculate visual local features. We pack the local features by BoW in frame sequences to represent the cooking gestures. In addition, the depth images of hands gestures are extracted and integrated spatio-temporally to represent the position and trajectory information of cooking gestures. The two kinds of features are used to describe cooking gestures, and recognition is realized by employing the SVM. In our method, we determine the gesture class for each frame in cooking sequences. By analyzing the results of frames, we recognize cooking gestures in a continue frame sequences of cooking menus, and find the temporal positions of the recognized gestures.

UR - http://www.scopus.com/inward/record.url?scp=84870484052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870484052&partnerID=8YFLogxK

U2 - 10.1145/2390776.2390785

DO - 10.1145/2390776.2390785

M3 - Conference contribution

AN - SCOPUS:84870484052

SN - 9781450315920

SP - 37

EP - 42

BT - CEA 2012 - Proceedings of the 2012 ACM Workshop on Multimedia for Cooking and Eating Activities, Co-located with ACM Multimedia 2012

ER -