Adaptive neighborhood size and effective geometric features selection for 3D scattered point cloud classification


Günen M. A.

Applied Soft Computing, cilt.115, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 115
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1016/j.asoc.2021.108196
  • Dergi Adı: Applied Soft Computing
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC
  • Anahtar Kelimeler: Point cloud classification, Neighborhood size selection, Geometric feature vector, Auto-Encoder, LIDAR DATA, EXTRACTION, ALGORITHMS, MULTISCALE
  • Kayseri Üniversitesi Adresli: Hayır

Özet

© 2021Classification of 3D scatter and unorganized point cloud (PC) is an ongoing hard problem due to high redundancy, unbalanced sampling density, and large data structure of PC. Geometric and spectral features derived from the PC are generally used for classification. In this paper, an Omnivariance based adaptive neighborhood size selection method and a new feature set composed of 14 features are proposed for extraction of geometric features for each individual point within the local neighborhood. Performance of 8 modern classifiers with different strategies (i.e., boosting, ensemble, and deep learning etc.) were evaluated on the Oakland, Vaihingen, and ISPRS datasets. These 3 datasets are identified by 5, 9, and 2 distinct object classes, respectively. The results were compared with different neighborhood size selection methods (i.e., eigenentropy based, fixed number of the k-nearest neighbors) and feature set (i.e., 21 features). Only 3D local features were employed to classify datasets with varying characteristics and properties. The proposed optimum neighbor selection method and feature set provided the best statistical results with Auto-Encoder classifier (the overall accuracies are over 85%, 60% and, 90% the Oakland, Vaihingen, and ISPRS datasets, respectively). Especially for the ISPRS dataset, the Auto-Encoder obtained over 94%, 90%, and 93% precision, recall, and f-score, respectively.