Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality

Ryo Hachiuma; Hideo Saito

doi:10.1109/WEVR.2016.7859541

Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality

Ryo Hachiuma, Hideo Saito

Department of Information and Computer Science

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

4 Citations (Scopus)

Abstract

In this paper, we propose a method for recognition and pose estimation of primitive shapes from depth images for spatial augmented reality (SAR). To use SAR in our everyday life, technology to recognize and estimate the pose of projected objects in the room is necessary. However, it is not a simple task to recognize primitive shapes because of their low 3D feature values. Hence, we focused on the gradient of normal vector map to extract surfaces and used the information of the surfaces of each object to recognize target objects. With our method, it becomes possible to recognize and estimate the pose of target objects in various scenes. Additionally; we projected an image onto each of the surfaces of the physical objects.

Original language	English
Title of host publication	2016 IEEE 2nd Workshop on Everyday Virtual Reality, WEVR 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	32-35
Number of pages	4
ISBN (Electronic)	9781509008407
DOIs	https://doi.org/10.1109/WEVR.2016.7859541
Publication status	Published - 2017 Feb 21
Event	2nd IEEE Workshop on Everyday Virtual Reality, WEVR 2016 - Greenville, United States Duration: 2016 Mar 20 → …

Other

Other	2nd IEEE Workshop on Everyday Virtual Reality, WEVR 2016
Country/Territory	United States
City	Greenville
Period	16/3/20 → …

Keywords

Object recognition
Pose estimation
RGB-D camera
Spatial augmented reality

ASJC Scopus subject areas

Media Technology

Access to Document

10.1109/WEVR.2016.7859541

Cite this

Hachiuma, R & Saito, H 2017, Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality. in 2016 IEEE 2nd Workshop on Everyday Virtual Reality, WEVR 2016., 7859541, Institute of Electrical and Electronics Engineers Inc., pp. 32-35, 2nd IEEE Workshop on Everyday Virtual Reality, WEVR 2016, Greenville, United States, 16/3/20. https://doi.org/10.1109/WEVR.2016.7859541

@inproceedings{5c3a0fbeb5e2479ba70d486ee8f9e553,

title = "Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality",

abstract = "In this paper, we propose a method for recognition and pose estimation of primitive shapes from depth images for spatial augmented reality (SAR). To use SAR in our everyday life, technology to recognize and estimate the pose of projected objects in the room is necessary. However, it is not a simple task to recognize primitive shapes because of their low 3D feature values. Hence, we focused on the gradient of normal vector map to extract surfaces and used the information of the surfaces of each object to recognize target objects. With our method, it becomes possible to recognize and estimate the pose of target objects in various scenes. Additionally; we projected an image onto each of the surfaces of the physical objects.",

keywords = "Object recognition, Pose estimation, RGB-D camera, Spatial augmented reality",

author = "Ryo Hachiuma and Hideo Saito",

year = "2017",

month = feb,

day = "21",

doi = "10.1109/WEVR.2016.7859541",

language = "English",

pages = "32--35",

booktitle = "2016 IEEE 2nd Workshop on Everyday Virtual Reality, WEVR 2016",

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

note = "2nd IEEE Workshop on Everyday Virtual Reality, WEVR 2016 ; Conference date: 20-03-2016",

}

TY - GEN

T1 - Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality

AU - Hachiuma, Ryo

AU - Saito, Hideo

PY - 2017/2/21

Y1 - 2017/2/21

N2 - In this paper, we propose a method for recognition and pose estimation of primitive shapes from depth images for spatial augmented reality (SAR). To use SAR in our everyday life, technology to recognize and estimate the pose of projected objects in the room is necessary. However, it is not a simple task to recognize primitive shapes because of their low 3D feature values. Hence, we focused on the gradient of normal vector map to extract surfaces and used the information of the surfaces of each object to recognize target objects. With our method, it becomes possible to recognize and estimate the pose of target objects in various scenes. Additionally; we projected an image onto each of the surfaces of the physical objects.

AB - In this paper, we propose a method for recognition and pose estimation of primitive shapes from depth images for spatial augmented reality (SAR). To use SAR in our everyday life, technology to recognize and estimate the pose of projected objects in the room is necessary. However, it is not a simple task to recognize primitive shapes because of their low 3D feature values. Hence, we focused on the gradient of normal vector map to extract surfaces and used the information of the surfaces of each object to recognize target objects. With our method, it becomes possible to recognize and estimate the pose of target objects in various scenes. Additionally; we projected an image onto each of the surfaces of the physical objects.

KW - Object recognition

KW - Pose estimation

KW - RGB-D camera

KW - Spatial augmented reality

UR - http://www.scopus.com/inward/record.url?scp=85016223849&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016223849&partnerID=8YFLogxK

U2 - 10.1109/WEVR.2016.7859541

DO - 10.1109/WEVR.2016.7859541

M3 - Conference contribution

AN - SCOPUS:85016223849

SP - 32

EP - 35

BT - 2016 IEEE 2nd Workshop on Everyday Virtual Reality, WEVR 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE Workshop on Everyday Virtual Reality, WEVR 2016

Y2 - 20 March 2016

ER -

Recognition and pose estimation of primitive shapes from depth images for spatial augmented reality

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this