Task-oriented function detection based on operational tasks

Yuchi Ishikawa; Haruya Ishikawa; Shuichi Akizuki; Masaki Yamazaki; Yasuhiro Taniguchi; Yoshimitsu Aoki

doi:10.1109/ICAR46387.2019.8981633

Task-oriented function detection based on operational tasks

Yuchi Ishikawa, Haruya Ishikawa, Shuichi Akizuki, Masaki Yamazaki, Yasuhiro Taniguchi, Yoshimitsu Aoki

Department of Electronics and Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose novel representations for functions of an object, namely Task-oriented Function, which is improved upon the idea of Afforadance in the field of Robotics Vision. We also propose a convolutional neural network to detect task-oriented functions. This network takes as input an operational task as well as an RGB image and assign each pixel an appropriate label for every task. Task-oriented funciton makes it possible to descibe various ways to use an object because the outputs from the network differ depending on operational tasks. We introduce a new dataset for task-oriented function detection, which contains about 1200 RGB images and 6000 pixel-level annotations assuming five tasks. Our proposed method reached 0.80 mean IOU in our dataset.

Original language	English
Title of host publication	2019 19th International Conference on Advanced Robotics, ICAR 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	635-640
Number of pages	6
ISBN (Electronic)	9781728124674
DOIs	https://doi.org/10.1109/ICAR46387.2019.8981633
Publication status	Published - 2019 Dec
Event	19th International Conference on Advanced Robotics, ICAR 2019 - Belo Horizonte, Brazil Duration: 2019 Dec 2 → 2019 Dec 6

Publication series

Name	2019 19th International Conference on Advanced Robotics, ICAR 2019

Conference

Conference	19th International Conference on Advanced Robotics, ICAR 2019
Country	Brazil
City	Belo Horizonte
Period	19/12/2 → 19/12/6

ASJC Scopus subject areas

Artificial Intelligence
Mechanical Engineering
Control and Optimization
Modelling and Simulation

Access to Document

10.1109/ICAR46387.2019.8981633

Fingerprint Dive into the research topics of 'Task-oriented function detection based on operational tasks'. Together they form a unique fingerprint.

Cite this

Ishikawa, Y., Ishikawa, H., Akizuki, S., Yamazaki, M., Taniguchi, Y., & Aoki, Y. (2019). Task-oriented function detection based on operational tasks. In 2019 19th International Conference on Advanced Robotics, ICAR 2019 (pp. 635-640). [8981633] (2019 19th International Conference on Advanced Robotics, ICAR 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAR46387.2019.8981633

Task-oriented function detection based on operational tasks. / Ishikawa, Yuchi; Ishikawa, Haruya; Akizuki, Shuichi; Yamazaki, Masaki; Taniguchi, Yasuhiro; Aoki, Yoshimitsu.

2019 19th International Conference on Advanced Robotics, ICAR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 635-640 8981633 (2019 19th International Conference on Advanced Robotics, ICAR 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ishikawa, Y, Ishikawa, H, Akizuki, S, Yamazaki, M, Taniguchi, Y & Aoki, Y 2019, Task-oriented function detection based on operational tasks. in 2019 19th International Conference on Advanced Robotics, ICAR 2019., 8981633, 2019 19th International Conference on Advanced Robotics, ICAR 2019, Institute of Electrical and Electronics Engineers Inc., pp. 635-640, 19th International Conference on Advanced Robotics, ICAR 2019, Belo Horizonte, Brazil, 19/12/2. https://doi.org/10.1109/ICAR46387.2019.8981633

Ishikawa Y, Ishikawa H, Akizuki S, Yamazaki M, Taniguchi Y, Aoki Y. Task-oriented function detection based on operational tasks. In 2019 19th International Conference on Advanced Robotics, ICAR 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 635-640. 8981633. (2019 19th International Conference on Advanced Robotics, ICAR 2019). https://doi.org/10.1109/ICAR46387.2019.8981633

Ishikawa, Yuchi ; Ishikawa, Haruya ; Akizuki, Shuichi ; Yamazaki, Masaki ; Taniguchi, Yasuhiro ; Aoki, Yoshimitsu. / Task-oriented function detection based on operational tasks. 2019 19th International Conference on Advanced Robotics, ICAR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 635-640 (2019 19th International Conference on Advanced Robotics, ICAR 2019).

@inproceedings{5e77a2965e5548bc9820938b7ae47c83,

title = "Task-oriented function detection based on operational tasks",

abstract = "We propose novel representations for functions of an object, namely Task-oriented Function, which is improved upon the idea of Afforadance in the field of Robotics Vision. We also propose a convolutional neural network to detect task-oriented functions. This network takes as input an operational task as well as an RGB image and assign each pixel an appropriate label for every task. Task-oriented funciton makes it possible to descibe various ways to use an object because the outputs from the network differ depending on operational tasks. We introduce a new dataset for task-oriented function detection, which contains about 1200 RGB images and 6000 pixel-level annotations assuming five tasks. Our proposed method reached 0.80 mean IOU in our dataset.",

author = "Yuchi Ishikawa and Haruya Ishikawa and Shuichi Akizuki and Masaki Yamazaki and Yasuhiro Taniguchi and Yoshimitsu Aoki",

year = "2019",

month = dec,

doi = "10.1109/ICAR46387.2019.8981633",

language = "English",

series = "2019 19th International Conference on Advanced Robotics, ICAR 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "635--640",

booktitle = "2019 19th International Conference on Advanced Robotics, ICAR 2019",

note = "19th International Conference on Advanced Robotics, ICAR 2019 ; Conference date: 02-12-2019 Through 06-12-2019",

}

TY - GEN

T1 - Task-oriented function detection based on operational tasks

AU - Ishikawa, Yuchi

AU - Ishikawa, Haruya

AU - Akizuki, Shuichi

AU - Yamazaki, Masaki

AU - Taniguchi, Yasuhiro

AU - Aoki, Yoshimitsu

PY - 2019/12

Y1 - 2019/12

N2 - We propose novel representations for functions of an object, namely Task-oriented Function, which is improved upon the idea of Afforadance in the field of Robotics Vision. We also propose a convolutional neural network to detect task-oriented functions. This network takes as input an operational task as well as an RGB image and assign each pixel an appropriate label for every task. Task-oriented funciton makes it possible to descibe various ways to use an object because the outputs from the network differ depending on operational tasks. We introduce a new dataset for task-oriented function detection, which contains about 1200 RGB images and 6000 pixel-level annotations assuming five tasks. Our proposed method reached 0.80 mean IOU in our dataset.

AB - We propose novel representations for functions of an object, namely Task-oriented Function, which is improved upon the idea of Afforadance in the field of Robotics Vision. We also propose a convolutional neural network to detect task-oriented functions. This network takes as input an operational task as well as an RGB image and assign each pixel an appropriate label for every task. Task-oriented funciton makes it possible to descibe various ways to use an object because the outputs from the network differ depending on operational tasks. We introduce a new dataset for task-oriented function detection, which contains about 1200 RGB images and 6000 pixel-level annotations assuming five tasks. Our proposed method reached 0.80 mean IOU in our dataset.

UR - http://www.scopus.com/inward/record.url?scp=85084280598&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084280598&partnerID=8YFLogxK

U2 - 10.1109/ICAR46387.2019.8981633

DO - 10.1109/ICAR46387.2019.8981633

M3 - Conference contribution

AN - SCOPUS:85084280598

T3 - 2019 19th International Conference on Advanced Robotics, ICAR 2019

SP - 635

EP - 640

BT - 2019 19th International Conference on Advanced Robotics, ICAR 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Advanced Robotics, ICAR 2019

Y2 - 2 December 2019 through 6 December 2019

ER -