3D Object Recognition with Ensemble Learning — A Study of Point Cloud-Based Deep Learning Models

Daniel Koguciuk , Łukasz Chechliński , Tarek El-Gaaly

Abstract

In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study of the topic of ensemble learning for 3D point clouds. First, an ensemble of multiple model instances trained on the same part of the ModelNet40 dataset was tested for seven deep learning, point cloud-based classification algorithms: PointNet, PointNet++, SO-Net, KCNet, DeepSets, DGCNN, and PointCNN. Second, the ensemble of different architectures was tested. Results of our experiments show that the tested ensemble learning methods improve over state-of-the-art on the ModelNet40 dataset, from 92.65% to 93.64% for the ensemble of single architecture instances, 94.03% for two different architectures, and 94.15% for five different architectures. We show that the ensemble of two models with different architectures can be as effective as the ensemble of 10 models with the same architecture. Third, a study on classic bagging (i.e. with different subsets used for training multiple model instances) was tested and sources of ensemble accuracy growth were investigated for best-performing architecture, i.e. SO-Net. We measure the inference time of all 3D classification architectures on a Nvidia Jetson TX2, a common embedded computer for mobile robots, to allude to the use of these models in real-life applications.
Author Daniel Koguciuk (FM / IACR)
Daniel Koguciuk,,
- The Institute of Automatic Control and Robotics
, Łukasz Chechliński (FM / IACR)
Łukasz Chechliński,,
- The Institute of Automatic Control and Robotics
, Tarek El-Gaaly - Voyage, Palo Alto
Tarek El-Gaaly,,
-
Pages100-114
Publication size in sheets0.7
Book Bebis George , Boyle Richard, Parvin Bahram, Koracin Darko, Ushizima Daniela, Chai Sek, Sueda Shinjiro, Lin Xin, Lu Aidong, Thalmann Daniel, Wang Chaoli, Xu Panpan (eds.): Advances in Visual Computing: 14th International Symposium on Visual Computing, ISVC 2019, Lake Tahoe, NV, USA, October 7-9, 2019. Proceedings, Part II , Lecture Notes In Computer Science, vol. 11845, 2019, Springer, ISBN 978-3-030-33722-3, [978-3-030-33723-0], DOI:10.1007/978-3-030-33723-0
Keywords in Englishpoint cloud, point set, classification, ensemble learning, 3D deep learning
DOIDOI:10.1007/978-3-030-33723-0_9
URL https://link.springer.com/chapter/10.1007/978-3-030-33723-0_9
Languageen angielski
Score (nominal)20
Score sourcepublisherList
ScoreMinisterial score = 20.0, 10-01-2020, ChapterFromConference
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?