CLASSIFICATION OF AERIAL PHOTOGRAMMETRIC POINT CLOUD USING RECURRENT NEURAL NETWORKS

Atik M. E., Duran Z.

FRESENIUS ENVIRONMENTAL BULLETIN, vol.30, no.4A, pp.4270-4275, 2021 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 30 Issue: 4A
  • Publication Date: 2021
  • Journal Name: FRESENIUS ENVIRONMENTAL BULLETIN
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Aerospace Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), CAB Abstracts, Chemical Abstracts Core, Communication Abstracts, Environment Index, Geobase, Greenfile, Metadex, Pollution Abstracts, Veterinary Science Database, Civil Engineering Abstracts
  • Page Numbers: pp.4270-4275
  • Keywords: Point cloud, recurrent neural networks, classification, photogrammetry, geometric features, SEGMENTATION
  • Istanbul Technical University Affiliated: Yes

Abstract

Point clouds are widely used in many fields such as photogrammetry, remote sensing, robotics, documentation, autonomous driving. Information extraction from point clouds is becoming important. The size and complexity of the data require modern methods such as deep learning for information extraction. In the literature, many methods have been developed for the classification of point clouds with deep learning. In this study, the classification problem is defined as sequence classification. Popular recurrent neural network methods (RNN) LSTM and BiLSTM which are popular recurrent neural network (RNN) methods were used to solve this problem. Photogrammetric point clouds produced with UAV images were classified using geometric features and RGB values. Overall classification accuracy decreases when feature spaces consisting of only RGB values or only geometric features are used. The combination of RGB and geometric features increased classification accuracy. Also, with two-way learning, the BiLSTM method has higher accuracy than LSTM. The overall accuracy of 85.68% for BiLSTM and 84.12% for LSTM was obtained.