Probabilistic Surfel Fusion for Dense LiDAR Mapping

Select | Print


Park, Chanoh; Kim, Soohwan; Moghadam, Peyman; Fookes, Clinton; Sridharan, Sridha


2017-10-29


Conference Material


MVR3D 2017: ICCV Workshop on Multiview Relationships in 3D Data, Venice, Italy, October 29, 2017


2418-2426


In this paper, we present a novel approach for dense LiDAR mapping using probabilistic surfel fusion. The proposed system is capable of reconstructing high-quality dense surfel map from spatially redundant multiple views. This is achieved by the proposed probabilistic surfel fusion along with a geometry considered data association. The suggested surfel data association method consider surficial resolution as well as high measurement uncertainty along its beam direction which make the mapping system being able to control surface resolution without introducing space digitization. Also, the proposed fusion method successfully suppresses the map noise level by counting measurement noise caused by laser beam incident angle and depth distance in Bayesian filtering framework. Experimental results (simulated and real data) for the dense surfel mapping prove the ability of the proposed method to accurately find the canonical form of the environment without further post-processing.


ICCV


SLAM Surfel


Information Engineering and Theory


https://doi.org/10.1109/ICCVW.2017.285


EP176119


Conference Paper - Refereed


English


Park, Chanoh; Kim, Soohwan; Moghadam, Peyman; Fookes, Clinton; Sridharan, Sridha. Probabilistic Surfel Fusion for Dense LiDAR Mapping. In: MVR3D 2017: ICCV Workshop on Multiview Relationships in 3D Data; October 29, 2017; Venice, Italy. ICCV; 2017. 2418-2426.https://doi.org/10.1109/ICCVW.2017.285



Loading citation data...

Citation counts
(Requires subscription to view)