Boundary‐enhanced supervoxel segmentation for sparse outdoor LiDAR data. Issue 25 (1st December 2014)

• Record Type: Journal Article
• Authors: Song, Soohwan; Lee, Honggu; Jo, Sungho
• Is Part Of: Electronics letters. Volume 50:Issue 25(2014)
• Page Start: 1917
• Page End: 1919
• Publication Date: 2014-12-01
• Subjects: optical radar -- radar imaging -- image segmentation; boundary‐enhanced supervoxel segmentation -- sparse outdoor LiDAR data -- voxelisation methods -- geometric information -- BESS -- light detection and ranging -- supervoxels -- geometric properties -- spatial properties; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2014.3249
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Voxelisation methods are extensively employed for efficiently processing large point clouds. However, it is possible to lose geometric information and extract inaccurate features through these voxelisation methods. A novel, flexibly shaped 'supervoxel' algorithm, called boundary‐enhanced supervoxel segmentation, for sparse and complex outdoor light detection and ranging (LiDAR) data is proposed. The algorithm consists of two key components: (i) detecting boundaries by analysing consecutive points and (ii) clustering the points by first excluding the boundary points. The generated supervoxels include spatial and geometric properties and maintain the shape of the object's boundary. The proposed algorithm is tested using sparse LiDAR data obtained from outdoor urban environments.