Exploring task-agnostic, ShapeNet-based object recognition for mobile robots

Agnese Chiatti, Gianluca Bardaro, Emanuele Bastianelli, Ilaria Tiddi, Prasenjit Mitra, Enrico Motta

Research output: Contribution to journalConference article

Abstract

This position paper presents an attempt to improve the scalability of existing object recognition methods, which largely rely on supervision and imply a huge availability of manually-labelled data points. Moreover, in the context of mobile robotics, data sets and experimental settings are often handcrafted based on the specific task the object recognition is aimed at, e.g. object grasping. In this work, we argue instead that publicly available open data such as ShapeNet [8] can be used for object classification first, and then to link objects to their related concepts, leading to task-agnostic knowledge acquisition practices. To this aim, we evaluated five pipelines for object recognition, where target classes were all entities collected from ShapeNet and matching was based on: (i) shape-only features, (ii) RGB histogram comparison, (iii) a combination of shape and colour matching, (iv) image feature descriptors, and (v) inexact, normalised cross-correlation, resembling the Deep, Siamese-like NN architecture of [31]. We discussed the relative impact of shape-derived and colour-derived features, as well as suitability of all tested solutions for future application to real-life use cases.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2322
StatePublished - Jan 1 2019
Event2019 Workshops of the EDBT/ICDT Joint Conference, EDBT/ICDT-WS 2019 - Lisbon, Portugal
Duration: Mar 26 2019 → …

Fingerprint

Object recognition
Mobile robots
Color matching
Knowledge acquisition
Scalability
Robotics
Pipelines
Availability
Color

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Chiatti, A., Bardaro, G., Bastianelli, E., Tiddi, I., Mitra, P., & Motta, E. (2019). Exploring task-agnostic, ShapeNet-based object recognition for mobile robots. CEUR Workshop Proceedings, 2322.
Chiatti, Agnese ; Bardaro, Gianluca ; Bastianelli, Emanuele ; Tiddi, Ilaria ; Mitra, Prasenjit ; Motta, Enrico. / Exploring task-agnostic, ShapeNet-based object recognition for mobile robots. In: CEUR Workshop Proceedings. 2019 ; Vol. 2322.
@article{6d53638caf2c47b59190c871b1accc9e,
title = "Exploring task-agnostic, ShapeNet-based object recognition for mobile robots",
abstract = "This position paper presents an attempt to improve the scalability of existing object recognition methods, which largely rely on supervision and imply a huge availability of manually-labelled data points. Moreover, in the context of mobile robotics, data sets and experimental settings are often handcrafted based on the specific task the object recognition is aimed at, e.g. object grasping. In this work, we argue instead that publicly available open data such as ShapeNet [8] can be used for object classification first, and then to link objects to their related concepts, leading to task-agnostic knowledge acquisition practices. To this aim, we evaluated five pipelines for object recognition, where target classes were all entities collected from ShapeNet and matching was based on: (i) shape-only features, (ii) RGB histogram comparison, (iii) a combination of shape and colour matching, (iv) image feature descriptors, and (v) inexact, normalised cross-correlation, resembling the Deep, Siamese-like NN architecture of [31]. We discussed the relative impact of shape-derived and colour-derived features, as well as suitability of all tested solutions for future application to real-life use cases.",
author = "Agnese Chiatti and Gianluca Bardaro and Emanuele Bastianelli and Ilaria Tiddi and Prasenjit Mitra and Enrico Motta",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
volume = "2322",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

Chiatti, A, Bardaro, G, Bastianelli, E, Tiddi, I, Mitra, P & Motta, E 2019, 'Exploring task-agnostic, ShapeNet-based object recognition for mobile robots', CEUR Workshop Proceedings, vol. 2322.

Exploring task-agnostic, ShapeNet-based object recognition for mobile robots. / Chiatti, Agnese; Bardaro, Gianluca; Bastianelli, Emanuele; Tiddi, Ilaria; Mitra, Prasenjit; Motta, Enrico.

In: CEUR Workshop Proceedings, Vol. 2322, 01.01.2019.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Exploring task-agnostic, ShapeNet-based object recognition for mobile robots

AU - Chiatti, Agnese

AU - Bardaro, Gianluca

AU - Bastianelli, Emanuele

AU - Tiddi, Ilaria

AU - Mitra, Prasenjit

AU - Motta, Enrico

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This position paper presents an attempt to improve the scalability of existing object recognition methods, which largely rely on supervision and imply a huge availability of manually-labelled data points. Moreover, in the context of mobile robotics, data sets and experimental settings are often handcrafted based on the specific task the object recognition is aimed at, e.g. object grasping. In this work, we argue instead that publicly available open data such as ShapeNet [8] can be used for object classification first, and then to link objects to their related concepts, leading to task-agnostic knowledge acquisition practices. To this aim, we evaluated five pipelines for object recognition, where target classes were all entities collected from ShapeNet and matching was based on: (i) shape-only features, (ii) RGB histogram comparison, (iii) a combination of shape and colour matching, (iv) image feature descriptors, and (v) inexact, normalised cross-correlation, resembling the Deep, Siamese-like NN architecture of [31]. We discussed the relative impact of shape-derived and colour-derived features, as well as suitability of all tested solutions for future application to real-life use cases.

AB - This position paper presents an attempt to improve the scalability of existing object recognition methods, which largely rely on supervision and imply a huge availability of manually-labelled data points. Moreover, in the context of mobile robotics, data sets and experimental settings are often handcrafted based on the specific task the object recognition is aimed at, e.g. object grasping. In this work, we argue instead that publicly available open data such as ShapeNet [8] can be used for object classification first, and then to link objects to their related concepts, leading to task-agnostic knowledge acquisition practices. To this aim, we evaluated five pipelines for object recognition, where target classes were all entities collected from ShapeNet and matching was based on: (i) shape-only features, (ii) RGB histogram comparison, (iii) a combination of shape and colour matching, (iv) image feature descriptors, and (v) inexact, normalised cross-correlation, resembling the Deep, Siamese-like NN architecture of [31]. We discussed the relative impact of shape-derived and colour-derived features, as well as suitability of all tested solutions for future application to real-life use cases.

UR - http://www.scopus.com/inward/record.url?scp=85062646474&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062646474&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85062646474

VL - 2322

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -

Chiatti A, Bardaro G, Bastianelli E, Tiddi I, Mitra P, Motta E. Exploring task-agnostic, ShapeNet-based object recognition for mobile robots. CEUR Workshop Proceedings. 2019 Jan 1;2322.