One-Class Classification of 3D Point Clouds Using Dynamic Graph CNN

Zeki Gencer, Yusuf H. Sahin, Gozde Unal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Anomaly detection is defined as a binary classification of normal and abnormal samples in a given data. In this task, anomalous samples are considered very rare and thus they are not used in training the deep learning model. Anomaly detection is thoroughly studied in 2D images, but 3D applications are not common yet. In this work, we combine studies in the field of 3D point cloud and anomaly detection and present a one-class classification method for 3D data. This method uses a pretrained Dynamic Graph Convolutional Neural Network (DG-CNN) to extract features from 3D point cloud data, and then fits a separate multivariate Gaussian distribution for each class. In the test phase, features are extracted from the test samples, and the distances to the distribution obtained in training indicate how anomalous the sample is for that class. Our method achieves 94.2% AUROC accuracy for the given setup. This is the first attempt to handle 3D point cloud classification as an anomaly detection case, and thus our findings and methods serve as a baseline for further studies.

Original languageEnglish
Title of host publicationProceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages388-392
Number of pages5
ISBN (Electronic)9781665470100
DOIs
Publication statusPublished - 2022
Event7th International Conference on Computer Science and Engineering, UBMK 2022 - Diyarbakir, Turkey
Duration: 14 Sept 202216 Sept 2022

Publication series

NameProceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022

Conference

Conference7th International Conference on Computer Science and Engineering, UBMK 2022
Country/TerritoryTurkey
CityDiyarbakir
Period14/09/2216/09/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

The work is supported by European UUnniioonn’'ss Horizon 2020 Research and IInnnnoovvaattiioonn Programme under grant agreement number 957402.

FundersFunder number
Horizon 2020957402

    Keywords

    • 3d
    • anomaly detection
    • deep learning
    • one-class classification
    • point cloud

    Fingerprint

    Dive into the research topics of 'One-Class Classification of 3D Point Clouds Using Dynamic Graph CNN'. Together they form a unique fingerprint.

    Cite this