Volume XLI-B1
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B1, 109-113, 2016
https://doi.org/10.5194/isprs-archives-XLI-B1-109-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B1, 109-113, 2016
https://doi.org/10.5194/isprs-archives-XLI-B1-109-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.

  02 Jun 2016

02 Jun 2016

PAIRWISE-SVM FOR ON-BOARD URBAN ROAD LIDAR CLASSIFICATION

Zhen Shu, Kai Sun, Kaijin Qiu, and Kou Ding Zhen Shu et al.
  • Leador Spatial Information Technology Co., Ltd. Building No. 12, Huazhong University Sci. & Tec. Park, East Lake Hi-Tech Zone, Wuhan, China

Keywords: LiDAR, on-board, classifiaction, SVM, MRF

Abstract. The common method of LiDAR classifications is Markov random fields (MRF). Based on construction of MRF energy function, spectral and directional features are extracted for on-board urban point clouds. The MRF energy function is consisted of unary and pairwise potentials. The unary terms are computed by SVM classifictaion. The initial labeling is mainly processed through geometrical shapes. The pairwise potential is estimated by Naïve Bayes. From training data, the probability of adjacent objects is computed by prior knowledge. The final labeling method is reweighted message-passing to minimization the energy function. The MRF model is difficult to process the large-scale misclassification. We propose a super-voxel clustering method for over-segment and grouping segment for large objects. Trees, poles ground, and building are classified in this paper. The experimental results show that this method improves the accuracy of classification and speed of computation.