Point-cloud detection of buildings based on a latent Dirichlet allocation model with waveform data

ABSTRACT

Light detection and ranging are important methods for acquiring digital surface models and can be used to extract building data. Point-cloud detection of buildings is a prerequisite for the model-based expression of buildings. Existing methods are insufficient because of their abstractness of feature extraction and poor accuracy of the detection results. This paper proposes a method for the point-cloud detection of buildings based on a latent Dirichlet allocation (LDA) model with waveform data. This method can extract waveform data via the global convergence Levenberg Marquard algorithm, convert discrete point clouds into point-cluster objects via super voxel segmentation, and detect the point clouds of buildings via the LDA model. Moreover, it supports vector machine classification. Experimental results demonstrate that waveform features and the LDA model both improve the accuracy of building detection. In addition, this method is less susceptible to variations in feature dimensions and is robust in terms of the number of topics and words.

Notes

1. Readers are referred to the following website for more information and to access datasets for potential future experiments. (Website link: http://card.westgis.ac.cn/data/b8504f8d-4f32-46b8-bb0a-b413bc0ad494).

Additional information

Funding

This work was supported by the State Key Laboratory of Geo-information Engineering [Grant No. SKLGIE2017-M-3-2], the National Natural Science Foundation of China [No. 41876105 and No. 41371436], the Foundation of Science and Technology on Near-surface Detection Laboratory [No. TCGZ2017A008], and the Information Engineering University Foundation for the Excellent Young [No. 2016610902].