Object-Based Goal Recognition Using Real-World Data

Roger Granada; Juarez Monteiro; Nathan Gavenski; Felipe Meneguzzi

doi:10.1007/978-3-030-60884-2_24

Object-Based Goal Recognition Using Real-World Data

Roger Granada^* (Corresponding Author), Juarez Monteiro^* (Corresponding Author), Nathan Gavenski^* (Corresponding Author), Felipe Meneguzzi^* (Corresponding Author)

^*Corresponding author for this work

Pontifícia Universidade Católica do Rio Grande do Sul

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

4 Citations (Scopus)

Abstract

Goal and plan recognition of daily living activities has attracted much interest due to its applicability to ambient assisted living. Such applications require the automatic recognition of high-level activities based on multiple steps performed by human beings in an environment. In this work, we address the problem of plan and goal recognition of human activities in an indoor environment. Unlike existing approaches that use only actions to identify the goal, we use objects and their relations to identify the plan and goal towards which the subject in the video is pursuing. Our approach combines state-of-the-art object and relationship detection to analyze raw video data with a goal recognition algorithm to identify the subject’s ultimate goal in the video. Experiments show that our approach identifies cooking activities in a kitchen scenario.

Original language	English
Title of host publication	Advances in Soft Computing
Subtitle of host publication	19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1
Editors	Lourdes Martínez-Villaseñor, Oscar Herrera-Alcántara, Hiram Ponce, Félix A. Castro-Espinoza
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	325-337
Number of pages	13
ISBN (Electronic)	978-3-030-60884-2
ISBN (Print)	978-3-030-60883-5
DOIs	https://doi.org/10.1007/978-3-030-60884-2_24
Publication status	Published - 7 Oct 2020
Event	19th Mexican International Conference on Artificial Intelligence - Mexico City, Mexico Duration: 12 Oct 2020 → 17 Oct 2020 http://micai.org/2020/

Publication series

Name	Lecture Notes in Artificial Intelligence
Publisher	Springer
Volume	12468
ISSN (Print)	2945-9133
ISSN (Electronic)	2945-9141

Conference

Conference	19th Mexican International Conference on Artificial Intelligence
Abbreviated title	MICAI 2020
Country/Territory	Mexico
City	Mexico City
Period	12/10/20 → 17/10/20
Internet address	http://micai.org/2020/

Keywords

goal recognition
relationship detection
object detection

Access to Document

10.1007/978-3-030-60884-2_24Licence: Unspecified

Cite this

Granada, R., Monteiro, J., Gavenski, N., & Meneguzzi, F. (2020). Object-Based Goal Recognition Using Real-World Data. In L. Martínez-Villaseñor, O. Herrera-Alcántara, H. Ponce, & F. A. Castro-Espinoza (Eds.), Advances in Soft Computing: 19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1 (pp. 325-337). (Lecture Notes in Artificial Intelligence; Vol. 12468). Springer . https://doi.org/10.1007/978-3-030-60884-2_24

Object-Based Goal Recognition Using Real-World Data. / Granada, Roger (Corresponding Author); Monteiro, Juarez (Corresponding Author); Gavenski, Nathan (Corresponding Author) et al.
Advances in Soft Computing: 19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1. ed. / Lourdes Martínez-Villaseñor; Oscar Herrera-Alcántara; Hiram Ponce; Félix A. Castro-Espinoza. Cham, Switzerland: Springer , 2020. p. 325-337 (Lecture Notes in Artificial Intelligence; Vol. 12468).

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

Granada, R, Monteiro, J, Gavenski, N & Meneguzzi, F 2020, Object-Based Goal Recognition Using Real-World Data. in L Martínez-Villaseñor, O Herrera-Alcántara, H Ponce & FA Castro-Espinoza (eds), Advances in Soft Computing: 19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1. Lecture Notes in Artificial Intelligence, vol. 12468, Springer , Cham, Switzerland, pp. 325-337, 19th Mexican International Conference on Artificial Intelligence, Mexico City, Mexico, 12/10/20. https://doi.org/10.1007/978-3-030-60884-2_24

Granada R, Monteiro J, Gavenski N, Meneguzzi F. Object-Based Goal Recognition Using Real-World Data. In Martínez-Villaseñor L, Herrera-Alcántara O, Ponce H, Castro-Espinoza FA, editors, Advances in Soft Computing: 19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1. Cham, Switzerland: Springer . 2020. p. 325-337. (Lecture Notes in Artificial Intelligence). doi: 10.1007/978-3-030-60884-2_24

Granada, Roger ; Monteiro, Juarez ; Gavenski, Nathan et al. / Object-Based Goal Recognition Using Real-World Data. Advances in Soft Computing: 19th Mexican International Conference on Artificial Intelligence, MICAI 2020 Mexico Cit, Mexico, October 12-17, 2020 Proceedings, Part 1. editor / Lourdes Martínez-Villaseñor ; Oscar Herrera-Alcántara ; Hiram Ponce ; Félix A. Castro-Espinoza. Cham, Switzerland : Springer , 2020. pp. 325-337 (Lecture Notes in Artificial Intelligence).

@inproceedings{3b394f29eba24a9a9f7d23f2e348cf9a,

title = "Object-Based Goal Recognition Using Real-World Data",

abstract = "Goal and plan recognition of daily living activities has attracted much interest due to its applicability to ambient assisted living. Such applications require the automatic recognition of high-level activities based on multiple steps performed by human beings in an environment. In this work, we address the problem of plan and goal recognition of human activities in an indoor environment. Unlike existing approaches that use only actions to identify the goal, we use objects and their relations to identify the plan and goal towards which the subject in the video is pursuing. Our approach combines state-of-the-art object and relationship detection to analyze raw video data with a goal recognition algorithm to identify the subject{\textquoteright}s ultimate goal in the video. Experiments show that our approach identifies cooking activities in a kitchen scenario.",

keywords = "goal recognition, relationship detection, object detection",

author = "Roger Granada and Juarez Monteiro and Nathan Gavenski and Felipe Meneguzzi",

year = "2020",

month = oct,

day = "7",

doi = "10.1007/978-3-030-60884-2_24",

language = "English",

isbn = "978-3-030-60883-5",

series = "Lecture Notes in Artificial Intelligence",

publisher = "Springer ",

pages = "325--337",

editor = "Mart{\'i}nez-Villase{\~n}or, {Lourdes } and Herrera-Alc{\'a}ntara, { Oscar } and Hiram Ponce and Castro-Espinoza, {F{\'e}lix A. }",

booktitle = "Advances in Soft Computing",

note = "19th Mexican International Conference on Artificial Intelligence, MICAI 2020 ; Conference date: 12-10-2020 Through 17-10-2020",

url = "http://micai.org/2020/",

}

TY - GEN

T1 - Object-Based Goal Recognition Using Real-World Data

AU - Granada, Roger

AU - Monteiro, Juarez

AU - Gavenski, Nathan

AU - Meneguzzi, Felipe

PY - 2020/10/7

Y1 - 2020/10/7

N2 - Goal and plan recognition of daily living activities has attracted much interest due to its applicability to ambient assisted living. Such applications require the automatic recognition of high-level activities based on multiple steps performed by human beings in an environment. In this work, we address the problem of plan and goal recognition of human activities in an indoor environment. Unlike existing approaches that use only actions to identify the goal, we use objects and their relations to identify the plan and goal towards which the subject in the video is pursuing. Our approach combines state-of-the-art object and relationship detection to analyze raw video data with a goal recognition algorithm to identify the subject’s ultimate goal in the video. Experiments show that our approach identifies cooking activities in a kitchen scenario.

AB - Goal and plan recognition of daily living activities has attracted much interest due to its applicability to ambient assisted living. Such applications require the automatic recognition of high-level activities based on multiple steps performed by human beings in an environment. In this work, we address the problem of plan and goal recognition of human activities in an indoor environment. Unlike existing approaches that use only actions to identify the goal, we use objects and their relations to identify the plan and goal towards which the subject in the video is pursuing. Our approach combines state-of-the-art object and relationship detection to analyze raw video data with a goal recognition algorithm to identify the subject’s ultimate goal in the video. Experiments show that our approach identifies cooking activities in a kitchen scenario.

KW - goal recognition

KW - relationship detection

KW - object detection

UR - http://www.meneguzzi.eu/felipe/pubs/micai-object-gr-2020.pdf

U2 - 10.1007/978-3-030-60884-2_24

DO - 10.1007/978-3-030-60884-2_24

M3 - Published conference contribution

SN - 978-3-030-60883-5

T3 - Lecture Notes in Artificial Intelligence

SP - 325

EP - 337

BT - Advances in Soft Computing

A2 - Martínez-Villaseñor, Lourdes

A2 - Herrera-Alcántara, Oscar

A2 - Ponce, Hiram

A2 - Castro-Espinoza, Félix A.

PB - Springer

CY - Cham, Switzerland

T2 - 19th Mexican International Conference on Artificial Intelligence

Y2 - 12 October 2020 through 17 October 2020

ER -

Object-Based Goal Recognition Using Real-World Data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this