Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION

Abstract: 

In the recent years, we experienced the proliferation of sensors for retrieving depth information on a scene, such as LIDAR or RGBD sensors (Kinect). However, it is still a challenge to identify the meaning of a specific point cloud to recognize the underlying object. Here, we wonder if it is possible to define a global feature for an object that is robust to noise, sampling and occlusion. We propose a local measure based on curvature. We called it Principal Curvatures because rather than using the Gaussian curvature we keep the
information of the two principal curvatures. In our approach, this local information is then aggregated as histograms that are compared with a Chi-2 metric. Results show the robustness of the method particularly when only few points are available. This means that our approach can be very suitable to match objects even with a limited resolution and possible occlusions. It could be particularly adapted to recognize objects with LIDAR inputs.

SPC.pdf

PDF icon SPC.pdf (55 downloads)
up
0 users have voted:

Paper Details

Authors:
Justin Lev , Joo-Hwee Lim , Nizar Ouarti
Submitted On:
18 September 2017 - 2:39am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Nizar Ouarti
Paper Code:
3510
Document Year:
2017
Cite

Document Files

SPC.pdf

(55 downloads)

Subscribe

[1] Justin Lev , Joo-Hwee Lim , Nizar Ouarti, "PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2221. Accessed: Dec. 18, 2017.
@article{2221-17,
url = {http://sigport.org/2221},
author = {Justin Lev ; Joo-Hwee Lim ; Nizar Ouarti },
publisher = {IEEE SigPort},
title = {PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION},
year = {2017} }
TY - EJOUR
T1 - PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION
AU - Justin Lev ; Joo-Hwee Lim ; Nizar Ouarti
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2221
ER -
Justin Lev , Joo-Hwee Lim , Nizar Ouarti. (2017). PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION. IEEE SigPort. http://sigport.org/2221
Justin Lev , Joo-Hwee Lim , Nizar Ouarti, 2017. PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION. Available at: http://sigport.org/2221.
Justin Lev , Joo-Hwee Lim , Nizar Ouarti. (2017). "PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION." Web.
1. Justin Lev , Joo-Hwee Lim , Nizar Ouarti. PRINCIPAL CURVATURE OF POINT CLOUD FOR 3D SHAPE RECOGNITION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2221