Napredna pretraga

Pregled bibliografske jedinice broj: 956055

Experimental Evaluation of Point Cloud Classification using the PointNet Neural Network


Filipović, Marko; Đurović, Petra; Cupec, Robert
Experimental Evaluation of Point Cloud Classification using the PointNet Neural Network // Proceedings of the 10th International Joint Conference on Computational Intelligence / Sabourin, Christophe ; Merelo, Juan Julian ; Barranco, Alejandro Linares ; Madani, Kurosh and Warwick, Kevin (ur.).
Seville, Spain: SCITEPRESS – Science and Technology Publications, Lda., 2018. str. 47-54 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Experimental Evaluation of Point Cloud Classification using the PointNet Neural Network

Autori
Filipović, Marko ; Đurović, Petra ; Cupec, Robert

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 10th International Joint Conference on Computational Intelligence / Sabourin, Christophe ; Merelo, Juan Julian ; Barranco, Alejandro Linares ; Madani, Kurosh and Warwick, Kevin - Seville, Spain : SCITEPRESS – Science and Technology Publications, Lda., 2018, 47-54

ISBN
978-989-758-327-8

Skup
IJCCI 2018 - 10th International Joint Conference on Computational Intelligence

Mjesto i datum
Sevilla, Španjolska, 18-20.09.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Point Cloud, Point Set, Point Cloud Classification, PointNet, RGB-D, Depth Map

Sažetak
Recently, new approaches for deep learning on unorganized point clouds have been proposed. Previous approaches used multiview 2D convolutional neural networks, volumetric representations or spectral convolutional networks on meshes (graphs). On the other hand, deep learning on point sets hasn’t yet reached the “maturity” of deep learning on RGB images. To the best of our knowledge, most of the point cloud classification approaches in the literature were based either only on synthetic models, or on a limited set of views from depth sensors. In this experimental work, we use a recent PointNet deep neural network architecture to reach the same or better level of performance as specialized hand-designed descriptors on a difficult dataset of nonsynthetic depth images of small household objects. We train the model on synthetically generated views of 3D models of objects, and test it on real depth images.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
HRZZ-IP-2014-09-3155 - Napredna 3D percepcija za mobilne robotske manipulatore (Robert Cupec, )

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Časopis indeksira:


  • Scopus